]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
Fix 'postprocessor_hooks`
[yt-dlp.git] / yt_dlp / extractor / youtube.py
CommitLineData
c5e8d7af 1# coding: utf-8
c5e8d7af 2
78caa52a
PH
3from __future__ import unicode_literals
4
2d6659b9 5import base64
d92f5d5a 6import calendar
109dd3b2 7import copy
fe93e2c4 8import datetime
a5c56234 9import hashlib
0ca96d48 10import itertools
c5e8d7af 11import json
c4417ddb 12import os.path
d77ab8e2 13import random
c5e8d7af 14import re
8a784c74 15import time
e0df6211 16import traceback
c5e8d7af 17
b05654f0 18from .common import InfoExtractor, SearchInfoExtractor
4bb4a188 19from ..compat import (
edf3e38e 20 compat_chr,
29f7c58a 21 compat_HTTPError,
c5e8d7af 22 compat_parse_qs,
545cc85d 23 compat_str,
7fd002c0 24 compat_urllib_parse_unquote_plus,
15707c7e 25 compat_urllib_parse_urlencode,
7c80519c 26 compat_urllib_parse_urlparse,
7c61bd36 27 compat_urlparse,
4bb4a188 28)
545cc85d 29from ..jsinterp import JSInterpreter
4bb4a188 30from ..utils import (
2d6659b9 31 bytes_to_intlist,
c5e8d7af 32 clean_html,
d92f5d5a 33 datetime_from_str,
11f9be09 34 dict_get,
358de58c 35 error_to_compat_str,
c5e8d7af 36 ExtractorError,
2d30521a 37 float_or_none,
11f9be09 38 format_field,
dd27fd17 39 int_or_none,
2d6659b9 40 intlist_to_bytes,
641ad5d8 41 is_html,
34921b43 42 join_nonempty,
94278f72 43 mimetype2ext,
9c0d7f49 44 network_exceptions,
11f9be09 45 orderedSet,
6310acf5 46 parse_codecs,
49bd8c66 47 parse_count,
7c80519c 48 parse_duration,
7ea65411 49 parse_iso8601,
4dfbf869 50 parse_qs,
dca3ff4a 51 qualities,
c0ac49bc 52 remove_end,
3995d37d 53 remove_start,
cf7e015f 54 smuggle_url,
dbdaaa23 55 str_or_none,
c93d53f5 56 str_to_int,
7c365c21 57 traverse_obj,
556dbe7f 58 try_get,
c5e8d7af
PH
59 unescapeHTML,
60 unified_strdate,
cf7e015f 61 unsmuggle_url,
8bdd16b4 62 update_url_query,
21c340b8 63 url_or_none,
fe93e2c4 64 urljoin,
7c365c21 65 variadic,
c5e8d7af
PH
66)
67
5f6a1245 68
000c15a4 69# any clients starting with _ cannot be explicity requested by the user
70INNERTUBE_CLIENTS = {
71 'web': {
72 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
73 'INNERTUBE_CONTEXT': {
74 'client': {
75 'clientName': 'WEB',
76 'clientVersion': '2.20210622.10.00',
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',
86 'clientVersion': '1.20210620.0.1',
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',
97 'clientVersion': '1.20210621.00.00',
98 }
99 },
100 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
101 },
e7e94f2a
D
102 'web_creator': {
103 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
104 'INNERTUBE_CONTEXT': {
105 'client': {
106 'clientName': 'WEB_CREATOR',
107 'clientVersion': '1.20210621.00.00',
108 }
109 },
110 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
111 },
000c15a4 112 'android': {
113 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
114 'INNERTUBE_CONTEXT': {
115 'client': {
116 'clientName': 'ANDROID',
117 'clientVersion': '16.20',
118 }
119 },
120 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 121 'REQUIRE_JS_PLAYER': False
000c15a4 122 },
123 'android_embedded': {
124 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
125 'INNERTUBE_CONTEXT': {
126 'client': {
127 'clientName': 'ANDROID_EMBEDDED_PLAYER',
128 'clientVersion': '16.20',
129 },
130 },
b6de707d 131 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
132 'REQUIRE_JS_PLAYER': False
000c15a4 133 },
134 'android_music': {
135 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
136 'INNERTUBE_HOST': 'music.youtube.com',
137 'INNERTUBE_CONTEXT': {
138 'client': {
139 'clientName': 'ANDROID_MUSIC',
140 'clientVersion': '4.32',
141 }
142 },
143 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 144 'REQUIRE_JS_PLAYER': False
000c15a4 145 },
e7e94f2a
D
146 'android_creator': {
147 'INNERTUBE_CONTEXT': {
148 'client': {
149 'clientName': 'ANDROID_CREATOR',
150 'clientVersion': '21.24.100',
151 },
152 },
b6de707d 153 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
154 'REQUIRE_JS_PLAYER': False
e7e94f2a 155 },
3619f78d 156 # ios has HLS live streams
157 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680
000c15a4 158 'ios': {
159 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
160 'INNERTUBE_CONTEXT': {
161 'client': {
162 'clientName': 'IOS',
163 'clientVersion': '16.20',
164 }
165 },
b6de707d 166 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
167 'REQUIRE_JS_PLAYER': False
000c15a4 168 },
169 'ios_embedded': {
170 'INNERTUBE_API_KEY': 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8',
171 'INNERTUBE_CONTEXT': {
172 'client': {
173 'clientName': 'IOS_MESSAGES_EXTENSION',
174 'clientVersion': '16.20',
175 },
176 },
b6de707d 177 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
178 'REQUIRE_JS_PLAYER': False
000c15a4 179 },
180 'ios_music': {
181 'INNERTUBE_API_KEY': 'AIzaSyDK3iBpDP9nHVTk2qL73FLJICfOC3c51Og',
182 'INNERTUBE_HOST': 'music.youtube.com',
183 'INNERTUBE_CONTEXT': {
184 'client': {
185 'clientName': 'IOS_MUSIC',
186 'clientVersion': '4.32',
187 },
188 },
b6de707d 189 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
190 'REQUIRE_JS_PLAYER': False
000c15a4 191 },
e7e94f2a
D
192 'ios_creator': {
193 'INNERTUBE_CONTEXT': {
194 'client': {
195 'clientName': 'IOS_CREATOR',
196 'clientVersion': '21.24.100',
197 },
198 },
b6de707d 199 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
200 'REQUIRE_JS_PLAYER': False
e7e94f2a 201 },
3619f78d 202 # mweb has 'ultralow' formats
203 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 204 'mweb': {
205 'INNERTUBE_API_KEY': 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8',
206 'INNERTUBE_CONTEXT': {
207 'client': {
208 'clientName': 'MWEB',
209 'clientVersion': '2.20210721.07.00',
210 }
211 },
212 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
213 },
214}
215
216
217def build_innertube_clients():
65c2fde2 218 third_party = {
219 'embedUrl': 'https://google.com', # Can be any valid URL
220 }
000c15a4 221 base_clients = ('android', 'web', 'ios', 'mweb')
222 priority = qualities(base_clients[::-1])
223
224 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 225 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 226 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 227 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 228 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
229 ytcfg['priority'] = 10 * priority(client.split('_', 1)[0])
230
231 if client in base_clients:
232 INNERTUBE_CLIENTS[f'{client}_agegate'] = agegate_ytcfg = copy.deepcopy(ytcfg)
233 agegate_ytcfg['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
65c2fde2 234 agegate_ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = third_party
000c15a4 235 agegate_ytcfg['priority'] -= 1
236 elif client.endswith('_embedded'):
65c2fde2 237 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = third_party
000c15a4 238 ytcfg['priority'] -= 2
239 else:
240 ytcfg['priority'] -= 3
241
242
243build_innertube_clients()
244
245
de7f3446 246class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 247 """Provide base functions for Youtube extractors"""
e00eb564 248
3462ffa8 249 _RESERVED_NAMES = (
3cd786db 250 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
3619f78d 251 r'shorts|movies|results|shared|hashtag|trending|feed|feeds|'
252 r'browse|oembed|get_video_info|iframe_api|s/player|'
cd7c66cf 253 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
3462ffa8 254
3619f78d 255 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
256
b2e8bc1b 257 _NETRC_MACHINE = 'youtube'
3619f78d 258
b2e8bc1b
JMF
259 # If True it will raise an error if no login info is provided
260 _LOGIN_REQUIRED = False
261
d9190e44
RH
262 _INVIDIOUS_SITES = (
263 # invidious-redirect websites
264 r'(?:www\.)?redirect\.invidious\.io',
265 r'(?:(?:www|dev)\.)?invidio\.us',
266 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
267 r'(?:www\.)?invidious\.pussthecat\.org',
268 r'(?:www\.)?invidious\.zee\.li',
269 r'(?:www\.)?invidious\.ethibox\.fr',
270 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
271 # youtube-dl invidious instances list
272 r'(?:(?:www|no)\.)?invidiou\.sh',
273 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
274 r'(?:www\.)?invidious\.kabi\.tk',
275 r'(?:www\.)?invidious\.mastodon\.host',
276 r'(?:www\.)?invidious\.zapashcanon\.fr',
277 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
278 r'(?:www\.)?invidious\.tinfoil-hat\.net',
279 r'(?:www\.)?invidious\.himiko\.cloud',
280 r'(?:www\.)?invidious\.reallyancient\.tech',
281 r'(?:www\.)?invidious\.tube',
282 r'(?:www\.)?invidiou\.site',
283 r'(?:www\.)?invidious\.site',
284 r'(?:www\.)?invidious\.xyz',
285 r'(?:www\.)?invidious\.nixnet\.xyz',
286 r'(?:www\.)?invidious\.048596\.xyz',
287 r'(?:www\.)?invidious\.drycat\.fr',
288 r'(?:www\.)?inv\.skyn3t\.in',
289 r'(?:www\.)?tube\.poal\.co',
290 r'(?:www\.)?tube\.connect\.cafe',
291 r'(?:www\.)?vid\.wxzm\.sx',
292 r'(?:www\.)?vid\.mint\.lgbt',
293 r'(?:www\.)?vid\.puffyan\.us',
294 r'(?:www\.)?yewtu\.be',
295 r'(?:www\.)?yt\.elukerio\.org',
296 r'(?:www\.)?yt\.lelux\.fi',
297 r'(?:www\.)?invidious\.ggc-project\.de',
298 r'(?:www\.)?yt\.maisputain\.ovh',
299 r'(?:www\.)?ytprivate\.com',
300 r'(?:www\.)?invidious\.13ad\.de',
301 r'(?:www\.)?invidious\.toot\.koeln',
302 r'(?:www\.)?invidious\.fdn\.fr',
303 r'(?:www\.)?watch\.nettohikari\.com',
304 r'(?:www\.)?invidious\.namazso\.eu',
305 r'(?:www\.)?invidious\.silkky\.cloud',
306 r'(?:www\.)?invidious\.exonip\.de',
307 r'(?:www\.)?invidious\.riverside\.rocks',
308 r'(?:www\.)?invidious\.blamefran\.net',
309 r'(?:www\.)?invidious\.moomoo\.de',
310 r'(?:www\.)?ytb\.trom\.tf',
311 r'(?:www\.)?yt\.cyberhost\.uk',
312 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
313 r'(?:www\.)?qklhadlycap4cnod\.onion',
314 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
315 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
316 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
317 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
318 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
319 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
320 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
321 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
322 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
323 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
324 )
325
b2e8bc1b 326 def _login(self):
83317f69 327 """
328 Attempt to log in to YouTube.
83317f69 329 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
330 """
9d5d4d64 331
982ee69a
MB
332 if (self._LOGIN_REQUIRED
333 and self.get_param('cookiefile') is None
334 and self.get_param('cookiesfrombrowser') is None):
9d5d4d64 335 self.raise_login_required(
336 'Login details are needed to download this content', method='cookies')
68217024 337 username, password = self._get_login_info()
9d5d4d64 338 if username:
24b0a72b 339 self.report_warning(f'Cannot login to YouTube using username and password. {self._LOGIN_HINTS["cookies"]}')
b2e8bc1b 340
cce889b9 341 def _initialize_consent(self):
342 cookies = self._get_cookies('https://www.youtube.com/')
343 if cookies.get('__Secure-3PSID'):
344 return
345 consent_id = None
346 consent = cookies.get('CONSENT')
347 if consent:
348 if 'YES' in consent.value:
349 return
350 consent_id = self._search_regex(
351 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
352 if not consent_id:
353 consent_id = random.randint(100, 999)
354 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 355
b2e8bc1b 356 def _real_initialize(self):
cce889b9 357 self._initialize_consent()
24b0a72b 358 self._login()
c5e8d7af 359
a0566bbf 360 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
29f7c58a 361 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
362 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
a0566bbf 363
000c15a4 364 def _get_default_ytcfg(self, client='web'):
365 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 366
000c15a4 367 def _get_innertube_host(self, client='web'):
368 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 369
000c15a4 370 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 371 # try_get but with fallback to default ytcfg client values when present
372 _func = lambda y: try_get(y, getter, expected_type)
373 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
374
000c15a4 375 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 376 return self._ytcfg_get_safe(
377 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
378 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client)
109dd3b2 379
000c15a4 380 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 381 return self._ytcfg_get_safe(
382 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
383 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client)
109dd3b2 384
000c15a4 385 def _extract_api_key(self, ytcfg=None, default_client='web'):
109dd3b2 386 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
387
000c15a4 388 def _extract_context(self, ytcfg=None, default_client='web'):
109dd3b2 389 _get_context = lambda y: try_get(y, lambda x: x['INNERTUBE_CONTEXT'], dict)
390 context = _get_context(ytcfg)
391 if context:
392 return context
393
394 context = _get_context(self._get_default_ytcfg(default_client))
395 if not ytcfg:
396 return context
397
398 # Recreate the client context (required)
399 context['client'].update({
400 'clientVersion': self._extract_client_version(ytcfg, default_client),
401 'clientName': self._extract_client_name(ytcfg, default_client),
402 })
403 visitor_data = try_get(ytcfg, lambda x: x['VISITOR_DATA'], compat_str)
404 if visitor_data:
405 context['client']['visitorData'] = visitor_data
406 return context
407
cf87314d 408 _SAPISID = None
409
109dd3b2 410 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 411 time_now = round(time.time())
cf87314d 412 if self._SAPISID is None:
413 yt_cookies = self._get_cookies('https://www.youtube.com')
414 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
415 # See: https://github.com/yt-dlp/yt-dlp/issues/393
416 sapisid_cookie = dict_get(
417 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
418 if sapisid_cookie and sapisid_cookie.value:
419 self._SAPISID = sapisid_cookie.value
420 self.write_debug('Extracted SAPISID cookie')
421 # SAPISID cookie is required if not already present
422 if not yt_cookies.get('SAPISID'):
423 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
424 self._set_cookie(
425 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
426 else:
427 self._SAPISID = False
428 if not self._SAPISID:
429 return None
1974e99f 430 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
431 sapisidhash = hashlib.sha1(
cf87314d 432 f'{time_now} {self._SAPISID} {origin}'.encode('utf-8')).hexdigest()
1974e99f 433 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
434
435 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 436 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 437 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 438
109dd3b2 439 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 440 data.update(query)
11f9be09 441 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 442 real_headers.update({'content-type': 'application/json'})
443 if headers:
444 real_headers.update(headers)
545cc85d 445 return self._download_json(
109dd3b2 446 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep),
a5c56234 447 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 448 data=json.dumps(data).encode('utf8'), headers=real_headers,
449 query={'key': api_key or self._extract_api_key()})
450
ac56cf38 451 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
452 data = self._search_regex(
453 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
454 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data', fatal=fatal)
455 if data:
456 return self._parse_json(data, item_id, fatal=fatal)
0c148415 457
99e9e001 458 @staticmethod
459 def _extract_session_index(*data):
460 """
461 Index of current account in account list.
462 See: https://github.com/yt-dlp/yt-dlp/pull/519
463 """
464 for ytcfg in data:
465 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
466 if session_index is not None:
467 return session_index
468
469 # Deprecated?
470 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca
M
471 if ytcfg:
472 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
473 if token:
474 return token
99e9e001 475 if webpage:
476 return self._search_regex(
477 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
478 'identity token', default=None, fatal=False)
a1c5d2ca
M
479
480 @staticmethod
fe93e2c4 481 def _extract_account_syncid(*args):
8ea3f7b9 482 """
483 Extract syncId required to download private playlists of secondary channels
fe93e2c4 484 @params response and/or ytcfg
8ea3f7b9 485 """
fe93e2c4 486 for data in args:
487 # ytcfg includes channel_syncid if on secondary channel
488 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], compat_str)
489 if delegated_sid:
490 return delegated_sid
491 sync_ids = (try_get(
492 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
e6f21b3d 493 lambda x: x['DATASYNC_ID']), compat_str) or '').split('||')
fe93e2c4 494 if len(sync_ids) >= 2 and sync_ids[1]:
495 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
496 # and just "user_syncid||" for primary channel. We only want the channel_syncid
497 return sync_ids[0]
a1c5d2ca 498
ac56cf38 499 @staticmethod
500 def _extract_visitor_data(*args):
501 """
502 Extracts visitorData from an API response or ytcfg
503 Appears to be used to track session state
504 """
505 return traverse_obj(
506 args, (..., ('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))),
507 expected_type=compat_str, get_all=False)
508
99e9e001 509 @property
510 def is_authenticated(self):
511 return bool(self._generate_sapisidhash_header())
512
11f9be09 513 def extract_ytcfg(self, video_id, webpage):
8c54a305 514 if not webpage:
515 return {}
29f7c58a 516 return self._parse_json(
517 self._search_regex(
518 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 519 default='{}'), video_id, fatal=False) or {}
520
11f9be09 521 def generate_api_headers(
99e9e001 522 self, *, ytcfg=None, account_syncid=None, session_index=None,
523 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
524
11f9be09 525 origin = 'https://' + (api_hostname if api_hostname else self._get_innertube_host(default_client))
f4f751af 526 headers = {
109dd3b2 527 'X-YouTube-Client-Name': compat_str(
11f9be09 528 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
529 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 530 'Origin': origin,
531 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
532 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
ac56cf38 533 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
99e9e001 534 }
535 if session_index is None:
314ee305 536 session_index = self._extract_session_index(ytcfg)
537 if account_syncid or session_index is not None:
538 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 539
109dd3b2 540 auth = self._generate_sapisidhash_header(origin)
f4f751af 541 if auth is not None:
542 headers['Authorization'] = auth
109dd3b2 543 headers['X-Origin'] = origin
99e9e001 544 return {h: v for h, v in headers.items() if v is not None}
29f7c58a 545
2d6659b9 546 @staticmethod
547 def _build_api_continuation_query(continuation, ctp=None):
548 query = {
549 'continuation': continuation
550 }
551 # TODO: Inconsistency with clickTrackingParams.
552 # Currently we have a fixed ctp contained within context (from ytcfg)
553 # and a ctp in root query for continuation.
554 if ctp:
555 query['clickTracking'] = {'clickTrackingParams': ctp}
556 return query
557
2d6659b9 558 @classmethod
559 def _extract_next_continuation_data(cls, renderer):
560 next_continuation = try_get(
561 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
562 lambda x: x['continuation']['reloadContinuationData']), dict)
563 if not next_continuation:
564 return
565 continuation = next_continuation.get('continuation')
566 if not continuation:
567 return
568 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 569 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 570
571 @classmethod
572 def _extract_continuation_ep_data(cls, continuation_ep: dict):
573 if isinstance(continuation_ep, dict):
574 continuation = try_get(
575 continuation_ep, lambda x: x['continuationCommand']['token'], compat_str)
576 if not continuation:
577 return
578 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 579 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 580
581 @classmethod
582 def _extract_continuation(cls, renderer):
583 next_continuation = cls._extract_next_continuation_data(renderer)
584 if next_continuation:
585 return next_continuation
fe93e2c4 586
2d6659b9 587 contents = []
588 for key in ('contents', 'items'):
589 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
fe93e2c4 590
2d6659b9 591 for content in contents:
592 if not isinstance(content, dict):
593 continue
594 continuation_ep = try_get(
595 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
596 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
597 dict)
598 continuation = cls._extract_continuation_ep_data(continuation_ep)
599 if continuation:
600 return continuation
601
fe93e2c4 602 @classmethod
603 def _extract_alerts(cls, data):
109dd3b2 604 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
605 if not isinstance(alert_dict, dict):
606 continue
607 for alert in alert_dict.values():
608 alert_type = alert.get('type')
609 if not alert_type:
610 continue
052e1350 611 message = cls._get_text(alert, 'text')
109dd3b2 612 if message:
613 yield alert_type, message
614
c0ac49bc 615 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
109dd3b2 616 errors = []
617 warnings = []
618 for alert_type, alert_message in alerts:
641ad5d8 619 if alert_type.lower() == 'error' and fatal:
109dd3b2 620 errors.append([alert_type, alert_message])
621 else:
622 warnings.append([alert_type, alert_message])
623
624 for alert_type, alert_message in (warnings + errors[:-1]):
c0ac49bc 625 self.report_warning('YouTube said: %s - %s' % (alert_type, alert_message), only_once=only_once)
109dd3b2 626 if errors:
627 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
628
629 def _extract_and_report_alerts(self, data, *args, **kwargs):
630 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
631
47193e02 632 def _extract_badges(self, renderer: dict):
633 badges = set()
634 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
635 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], compat_str)
636 if label:
637 badges.add(label.lower())
638 return badges
639
640 @staticmethod
052e1350 641 def _get_text(data, *path_list, max_runs=None):
642 for path in path_list or [None]:
643 if path is None:
644 obj = [data]
645 else:
646 obj = traverse_obj(data, path, default=[])
647 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
648 obj = [obj]
649 for item in obj:
650 text = try_get(item, lambda x: x['simpleText'], compat_str)
651 if text:
652 return text
653 runs = try_get(item, lambda x: x['runs'], list) or []
654 if not runs and isinstance(item, list):
655 runs = item
656
657 runs = runs[:min(len(runs), max_runs or len(runs))]
658 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
659 if text:
660 return text
47193e02 661
109dd3b2 662 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
663 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 664 default_client='web'):
109dd3b2 665 response = None
666 last_error = None
667 count = -1
668 retries = self.get_param('extractor_retries', 3)
669 if check_get_keys is None:
670 check_get_keys = []
671 while count < retries:
672 count += 1
673 if last_error:
c0ac49bc 674 self.report_warning('%s. Retrying ...' % remove_end(last_error, '.'))
109dd3b2 675 try:
676 response = self._call_api(
677 ep=ep, fatal=True, headers=headers,
678 video_id=item_id, query=query,
679 context=self._extract_context(ytcfg, default_client),
680 api_key=self._extract_api_key(ytcfg, default_client),
681 api_hostname=api_hostname, default_client=default_client,
682 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
683 except ExtractorError as e:
9c0d7f49 684 if isinstance(e.cause, network_exceptions):
641ad5d8 685 if isinstance(e.cause, compat_HTTPError) and not is_html(e.cause.read(512)):
686 e.cause.seek(0)
687 yt_error = try_get(
688 self._parse_json(e.cause.read().decode(), item_id, fatal=False),
689 lambda x: x['error']['message'], compat_str)
690 if yt_error:
691 self._report_alerts([('ERROR', yt_error)], fatal=False)
109dd3b2 692 # Downloading page may result in intermittent 5xx HTTP error
693 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
9c0d7f49 694 # We also want to catch all other network exceptions since errors in later pages can be troublesome
695 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
696 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
526d74ec 697 last_error = error_to_compat_str(e.cause or e.msg)
9c0d7f49 698 if count < retries:
699 continue
109dd3b2 700 if fatal:
701 raise
702 else:
703 self.report_warning(error_to_compat_str(e))
704 return
705
706 else:
109dd3b2 707 try:
ac56cf38 708 self._extract_and_report_alerts(response, only_once=True)
109dd3b2 709 except ExtractorError as e:
c0ac49bc 710 # YouTube servers may return errors we want to retry on in a 200 OK response
711 # See: https://github.com/yt-dlp/yt-dlp/issues/839
712 if 'unknown error' in e.msg.lower():
713 last_error = e.msg
714 continue
109dd3b2 715 if fatal:
716 raise
717 self.report_warning(error_to_compat_str(e))
718 return
719 if not check_get_keys or dict_get(response, check_get_keys):
720 break
721 # Youtube sometimes sends incomplete data
722 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
723 last_error = 'Incomplete data received'
724 if count >= retries:
725 if fatal:
726 raise ExtractorError(last_error)
727 else:
728 self.report_warning(last_error)
729 return
730 return response
731
9297939e 732 @staticmethod
733 def is_music_url(url):
734 return re.match(r'https?://music\.youtube\.com/', url) is not None
735
30a074c2 736 def _extract_video(self, renderer):
737 video_id = renderer.get('videoId')
052e1350 738 title = self._get_text(renderer, 'title')
739 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 740 duration = parse_duration(self._get_text(
741 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
052e1350 742 view_count_text = self._get_text(renderer, 'viewCountText') or ''
30a074c2 743 view_count = str_to_int(self._search_regex(
744 r'^([\d,]+)', re.sub(r'\s', '', view_count_text),
745 'view count', default=None))
fe93e2c4 746
052e1350 747 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
fe93e2c4 748
30a074c2 749 return {
39ed931e 750 '_type': 'url',
30a074c2 751 'ie_key': YoutubeIE.ie_key(),
752 'id': video_id,
5e3f2f8f 753 'url': f'https://www.youtube.com/watch?v={video_id}',
30a074c2 754 'title': title,
755 'description': description,
756 'duration': duration,
757 'view_count': view_count,
758 'uploader': uploader,
759 }
760
0c148415 761
360e1ca5 762class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 763 IE_DESC = 'YouTube'
cb7dfeea 764 _VALID_URL = r"""(?x)^
c5e8d7af 765 (
edb53e2d 766 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 767 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
768 (?:www\.)?deturl\.com/www\.youtube\.com|
769 (?:www\.)?pwnyoutube\.com|
770 (?:www\.)?hooktube\.com|
771 (?:www\.)?yourepeat\.com|
772 tube\.majestyc\.net|
773 %(invidious)s|
774 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
775 (?:.*?\#/)? # handle anchor (#/) redirect urls
776 (?: # the various things that can precede the ID:
8fc54b12 777 (?:(?:v|embed|e|shorts)/(?!videoseries)) # v/ or embed/ or e/ or shorts/
c5e8d7af 778 |(?: # or the v= param in all its forms
f7000f3a 779 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 780 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 781 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
782 v=
783 )
f4b05232 784 ))
cbaed4bb
S
785 |(?:
786 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
787 vid\.plus| # or vid.plus/xxxx
788 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 789 %(invidious)s
cbaed4bb 790 )/
edb53e2d 791 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 792 )
c5e8d7af 793 )? # all until now is optional -> you can pass the naked ID
201c1459 794 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 795 (?(1).+)? # if we found the ID, everything can follow
9297939e 796 (?:\#|$)""" % {
d9190e44 797 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 798 }
e40c758c 799 _PLAYER_INFO_RE = (
cc2db878 800 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
801 r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
545cc85d 802 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 803 )
2c62dc26 804 _formats = {
c2d3cb4c 805 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
806 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
807 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
808 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
809 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
810 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
811 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
812 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 813 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 814 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
815 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
816 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
817 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
818 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
819 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 820 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 821 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
822 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 823
824
825 # 3D videos
c2d3cb4c 826 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
827 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
828 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
829 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 830 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
831 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
832 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 833
96fb5605 834 # Apple HTTP Live Streaming
11f12195 835 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 836 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
837 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
838 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
839 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
840 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 841 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
842 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
843
844 # DASH mp4 video
d23028a8
S
845 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
846 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
847 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
848 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
849 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 850 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
851 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
852 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
853 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
854 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
855 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
856 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 857
f6f1fc92 858 # Dash mp4 audio
d23028a8
S
859 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
860 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
861 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
862 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
863 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
864 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
865 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
866
867 # Dash webm
d23028a8
S
868 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
869 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
870 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
871 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
872 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
873 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
874 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
875 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
876 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
877 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
878 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
879 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
880 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
881 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
882 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 883 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
884 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
885 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
886 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
887 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
888 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
889 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
890
891 # Dash webm audio
d23028a8
S
892 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
893 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 894
0857baad 895 # Dash webm audio with opus inside
d23028a8
S
896 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
897 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
898 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 899
ce6b9a2d
PH
900 # RTMP (unnamed)
901 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
902
903 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
904 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
905 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
906 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
907 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
908 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
909 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
910 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
911 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 912 }
29f7c58a 913 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 914
fd5c4aab
S
915 _GEO_BYPASS = False
916
78caa52a 917 IE_NAME = 'youtube'
2eb88d95
PH
918 _TESTS = [
919 {
2d3d2997 920 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
921 'info_dict': {
922 'id': 'BaW_jenozKc',
923 'ext': 'mp4',
3867038a 924 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
925 'uploader': 'Philipp Hagemeister',
926 'uploader_id': 'phihag',
ec85ded8 927 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
dd4c4492
S
928 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
929 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 930 'upload_date': '20121002',
3867038a 931 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
4bc3a23e 932 'categories': ['Science & Technology'],
3867038a 933 'tags': ['youtube-dl'],
556dbe7f 934 'duration': 10,
dbdaaa23 935 'view_count': int,
3e7c1224
PH
936 'like_count': int,
937 'dislike_count': int,
7c80519c 938 'start_time': 1,
297a564b 939 'end_time': 9,
2eb88d95 940 }
0e853ca4 941 },
fccd3771 942 {
4bc3a23e
PH
943 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
944 'note': 'Embed-only video (#1746)',
945 'info_dict': {
946 'id': 'yZIXLfi8CZQ',
947 'ext': 'mp4',
948 'upload_date': '20120608',
949 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
950 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
951 'uploader': 'SET India',
94bfcd23 952 'uploader_id': 'setindia',
ec85ded8 953 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 954 'age_limit': 18,
545cc85d 955 },
956 'skip': 'Private video',
fccd3771 957 },
11b56058 958 {
8bdd16b4 959 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
960 'note': 'Use the first video ID in the URL',
961 'info_dict': {
962 'id': 'BaW_jenozKc',
963 'ext': 'mp4',
3867038a 964 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
965 'uploader': 'Philipp Hagemeister',
966 'uploader_id': 'phihag',
ec85ded8 967 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
11b56058 968 'upload_date': '20121002',
3867038a 969 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
11b56058 970 'categories': ['Science & Technology'],
3867038a 971 'tags': ['youtube-dl'],
556dbe7f 972 'duration': 10,
dbdaaa23 973 'view_count': int,
11b56058
PM
974 'like_count': int,
975 'dislike_count': int,
34a7de29
S
976 },
977 'params': {
978 'skip_download': True,
979 },
11b56058 980 },
dd27fd17 981 {
2d3d2997 982 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
983 'note': '256k DASH audio (format 141) via DASH manifest',
984 'info_dict': {
985 'id': 'a9LDPn-MO4I',
986 'ext': 'm4a',
987 'upload_date': '20121002',
988 'uploader_id': '8KVIDEO',
ec85ded8 989 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
990 'description': '',
991 'uploader': '8KVIDEO',
992 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 993 },
4bc3a23e
PH
994 'params': {
995 'youtube_include_dash_manifest': True,
996 'format': '141',
4919603f 997 },
de3c7fe0 998 'skip': 'format 141 not served anymore',
dd27fd17 999 },
8bdd16b4 1000 # DASH manifest with encrypted signature
1001 {
1002 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1003 'info_dict': {
1004 'id': 'IB3lcPjvWLA',
1005 'ext': 'm4a',
1006 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1007 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1008 'duration': 244,
1009 'uploader': 'AfrojackVEVO',
1010 'uploader_id': 'AfrojackVEVO',
1011 'upload_date': '20131011',
cc2db878 1012 'abr': 129.495,
8bdd16b4 1013 },
1014 'params': {
1015 'youtube_include_dash_manifest': True,
1016 'format': '141/bestaudio[ext=m4a]',
1017 },
1018 },
65c2fde2 1019 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1020 {
65c2fde2 1021 'note': 'Embed allowed age-gate video',
2d3d2997 1022 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1023 'info_dict': {
1024 'id': 'HtVdAasjOgU',
1025 'ext': 'mp4',
1026 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1027 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1028 'duration': 142,
c522adb1
JMF
1029 'uploader': 'The Witcher',
1030 'uploader_id': 'WitcherGame',
ec85ded8 1031 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1032 'upload_date': '20140605',
34952f09 1033 'age_limit': 18,
c522adb1
JMF
1034 },
1035 },
65c2fde2 1036 {
1037 'note': 'Age-gate video with embed allowed in public site',
1038 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1039 'info_dict': {
1040 'id': 'HsUATh_Nc2U',
1041 'ext': 'mp4',
1042 'title': 'Godzilla 2 (Official Video)',
1043 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1044 'upload_date': '20200408',
1045 'uploader_id': 'FlyingKitty900',
1046 'uploader': 'FlyingKitty',
1047 'age_limit': 18,
1048 },
1049 },
1050 {
1051 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1052 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1053 'info_dict': {
1054 'id': 'Tq92D6wQ1mg',
1055 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1056 'ext': 'mp4',
1057 'upload_date': '20191227',
65c2fde2 1058 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1059 'uploader': 'Projekt Melody',
1060 'description': 'md5:17eccca93a786d51bc67646756894066',
1061 'age_limit': 18,
1062 },
1063 },
1064 {
1065 'note': 'Non-Agegated non-embeddable video',
1066 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1067 'info_dict': {
1068 'id': 'MeJVWBSsPAY',
1069 'ext': 'mp4',
1070 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1071 'uploader': 'Herr Lurik',
1072 'uploader_id': 'st3in234',
1073 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1074 'upload_date': '20130730',
1075 },
1076 },
1077 {
1078 'note': 'Non-bypassable age-gated video',
1079 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1080 'only_matching': True,
1081 },
8bdd16b4 1082 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1083 # YouTube Red ad is not captured for creator
1084 {
1085 'url': '__2ABJjxzNo',
1086 'info_dict': {
1087 'id': '__2ABJjxzNo',
1088 'ext': 'mp4',
1089 'duration': 266,
1090 'upload_date': '20100430',
1091 'uploader_id': 'deadmau5',
1092 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1093 'creator': 'deadmau5',
1094 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1095 'uploader': 'deadmau5',
1096 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1097 'alt_title': 'Some Chords',
8bdd16b4 1098 },
1099 'expected_warnings': [
1100 'DASH manifest missing',
1101 ]
1102 },
067aa17e 1103 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1104 {
1105 'url': 'lqQg6PlCWgI',
1106 'info_dict': {
1107 'id': 'lqQg6PlCWgI',
1108 'ext': 'mp4',
556dbe7f 1109 'duration': 6085,
90227264 1110 'upload_date': '20150827',
cbe2bd91 1111 'uploader_id': 'olympic',
ec85ded8 1112 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
cbe2bd91 1113 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
11f9be09 1114 'uploader': 'Olympics',
cbe2bd91
PH
1115 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1116 },
1117 'params': {
1118 'skip_download': 'requires avconv',
e52a40ab 1119 }
cbe2bd91 1120 },
6271f1ca
PH
1121 # Non-square pixels
1122 {
1123 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1124 'info_dict': {
1125 'id': '_b-2C3KPAM0',
1126 'ext': 'mp4',
1127 'stretched_ratio': 16 / 9.,
556dbe7f 1128 'duration': 85,
6271f1ca
PH
1129 'upload_date': '20110310',
1130 'uploader_id': 'AllenMeow',
ec85ded8 1131 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1132 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯',
eb6793ba 1133 'uploader': '孫ᄋᄅ',
6271f1ca
PH
1134 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1135 },
06b491eb
S
1136 },
1137 # url_encoded_fmt_stream_map is empty string
1138 {
1139 'url': 'qEJwOuvDf7I',
1140 'info_dict': {
1141 'id': 'qEJwOuvDf7I',
f57b7835 1142 'ext': 'webm',
06b491eb
S
1143 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1144 'description': '',
1145 'upload_date': '20150404',
1146 'uploader_id': 'spbelect',
1147 'uploader': 'Наблюдатели Петербурга',
1148 },
1149 'params': {
1150 'skip_download': 'requires avconv',
e323cf3f
S
1151 },
1152 'skip': 'This live event has ended.',
06b491eb 1153 },
067aa17e 1154 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1155 {
1156 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1157 'info_dict': {
1158 'id': 'FIl7x6_3R5Y',
eb6793ba 1159 'ext': 'webm',
da77d856
S
1160 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1161 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1162 'duration': 220,
da77d856
S
1163 'upload_date': '20150625',
1164 'uploader_id': 'dorappi2000',
ec85ded8 1165 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1166 'uploader': 'dorappi2000',
eb6793ba 1167 'formats': 'mincount:31',
da77d856 1168 },
eb6793ba 1169 'skip': 'not actual anymore',
2ee8f5d8 1170 },
8a1a26ce
YCH
1171 # DASH manifest with segment_list
1172 {
1173 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1174 'md5': '8ce563a1d667b599d21064e982ab9e31',
1175 'info_dict': {
1176 'id': 'CsmdDsKjzN8',
1177 'ext': 'mp4',
17ee98e1 1178 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1179 'uploader': 'Airtek',
1180 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1181 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1182 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1183 },
1184 'params': {
1185 'youtube_include_dash_manifest': True,
1186 'format': '135', # bestvideo
be49068d
S
1187 },
1188 'skip': 'This live event has ended.',
2ee8f5d8 1189 },
cf7e015f
S
1190 {
1191 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1192 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1193 'info_dict': {
545cc85d 1194 'id': 'jvGDaLqkpTg',
1195 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1196 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1197 },
1198 'playlist': [{
1199 'info_dict': {
545cc85d 1200 'id': 'jvGDaLqkpTg',
cf7e015f 1201 'ext': 'mp4',
545cc85d 1202 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1203 'description': 'md5:e03b909557865076822aa169218d6a5d',
1204 'duration': 10643,
1205 'upload_date': '20161111',
1206 'uploader': 'Team PGP',
1207 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1208 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1209 },
1210 }, {
1211 'info_dict': {
545cc85d 1212 'id': '3AKt1R1aDnw',
cf7e015f 1213 'ext': 'mp4',
545cc85d 1214 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1215 'description': 'md5:e03b909557865076822aa169218d6a5d',
1216 'duration': 10991,
1217 'upload_date': '20161111',
1218 'uploader': 'Team PGP',
1219 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1220 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1221 },
1222 }, {
1223 'info_dict': {
545cc85d 1224 'id': 'RtAMM00gpVc',
cf7e015f 1225 'ext': 'mp4',
545cc85d 1226 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1227 'description': 'md5:e03b909557865076822aa169218d6a5d',
1228 'duration': 10995,
1229 'upload_date': '20161111',
1230 'uploader': 'Team PGP',
1231 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1232 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1233 },
1234 }, {
1235 'info_dict': {
545cc85d 1236 'id': '6N2fdlP3C5U',
cf7e015f 1237 'ext': 'mp4',
545cc85d 1238 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1239 'description': 'md5:e03b909557865076822aa169218d6a5d',
1240 'duration': 10990,
1241 'upload_date': '20161111',
1242 'uploader': 'Team PGP',
1243 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1244 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1245 },
1246 }],
1247 'params': {
1248 'skip_download': True,
1249 },
65c2fde2 1250 'skip': 'Not multifeed anymore',
cbaed4bb 1251 },
f9f49d87 1252 {
067aa17e 1253 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1254 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1255 'info_dict': {
1256 'id': 'gVfLd0zydlo',
1257 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1258 },
1259 'playlist_count': 2,
be49068d 1260 'skip': 'Not multifeed anymore',
f9f49d87 1261 },
cbaed4bb 1262 {
2d3d2997 1263 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1264 'only_matching': True,
0e49d9a6 1265 },
6d4fc66b 1266 {
2d3d2997 1267 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1268 'only_matching': True,
1269 },
0e49d9a6 1270 {
067aa17e 1271 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1272 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1273 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1274 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1275 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1276 'info_dict': {
1277 'id': 'lsguqyKfVQg',
1278 'ext': 'mp4',
1279 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1280 'alt_title': 'Dark Walk',
0e49d9a6 1281 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1282 'duration': 133,
0e49d9a6
LL
1283 'upload_date': '20151119',
1284 'uploader_id': 'IronSoulElf',
ec85ded8 1285 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1286 'uploader': 'IronSoulElf',
11f9be09 1287 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1288 'track': 'Dark Walk',
1289 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1290 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
0e49d9a6
LL
1291 },
1292 'params': {
1293 'skip_download': True,
1294 },
1295 },
61f92af1 1296 {
067aa17e 1297 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1298 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1299 'only_matching': True,
1300 },
313dfc45
LL
1301 {
1302 # Video with yt:stretch=17:0
1303 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1304 'info_dict': {
1305 'id': 'Q39EVAstoRM',
1306 'ext': 'mp4',
1307 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1308 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1309 'upload_date': '20151107',
1310 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1311 'uploader': 'CH GAMER DROID',
1312 },
1313 'params': {
1314 'skip_download': True,
1315 },
be49068d 1316 'skip': 'This video does not exist.',
313dfc45 1317 },
201c1459 1318 {
1319 # Video with incomplete 'yt:stretch=16:'
1320 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1321 'only_matching': True,
1322 },
7caf9830
S
1323 {
1324 # Video licensed under Creative Commons
1325 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1326 'info_dict': {
1327 'id': 'M4gD1WSo5mA',
1328 'ext': 'mp4',
1329 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1330 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1331 'duration': 721,
7caf9830
S
1332 'upload_date': '20150127',
1333 'uploader_id': 'BerkmanCenter',
ec85ded8 1334 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1335 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830
S
1336 'license': 'Creative Commons Attribution license (reuse allowed)',
1337 },
1338 'params': {
1339 'skip_download': True,
1340 },
1341 },
fd050249
S
1342 {
1343 # Channel-like uploader_url
1344 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1345 'info_dict': {
1346 'id': 'eQcmzGIKrzg',
1347 'ext': 'mp4',
1348 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1349 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1350 'duration': 4060,
fd050249 1351 'upload_date': '20151119',
eb6793ba 1352 'uploader': 'Bernie Sanders',
fd050249 1353 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1354 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249
S
1355 'license': 'Creative Commons Attribution license (reuse allowed)',
1356 },
1357 'params': {
1358 'skip_download': True,
1359 },
1360 },
040ac686
S
1361 {
1362 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1363 'only_matching': True,
7f29cf54
S
1364 },
1365 {
067aa17e 1366 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1367 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1368 'only_matching': True,
6496ccb4
S
1369 },
1370 {
1371 # Rental video preview
1372 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1373 'info_dict': {
1374 'id': 'uGpuVWrhIzE',
1375 'ext': 'mp4',
1376 'title': 'Piku - Trailer',
1377 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1378 'upload_date': '20150811',
1379 'uploader': 'FlixMatrix',
1380 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1381 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1382 'license': 'Standard YouTube License',
1383 },
1384 'params': {
1385 'skip_download': True,
1386 },
eb6793ba 1387 'skip': 'This video is not available.',
022a5d66 1388 },
12afdc2a
S
1389 {
1390 # YouTube Red video with episode data
1391 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1392 'info_dict': {
1393 'id': 'iqKdEhx-dD4',
1394 'ext': 'mp4',
1395 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1396 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1397 'duration': 2085,
12afdc2a
S
1398 'upload_date': '20170118',
1399 'uploader': 'Vsauce',
1400 'uploader_id': 'Vsauce',
1401 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1402 'series': 'Mind Field',
1403 'season_number': 1,
1404 'episode_number': 1,
1405 },
1406 'params': {
1407 'skip_download': True,
1408 },
1409 'expected_warnings': [
1410 'Skipping DASH manifest',
1411 ],
1412 },
c7121fa7
S
1413 {
1414 # The following content has been identified by the YouTube community
1415 # as inappropriate or offensive to some audiences.
1416 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1417 'info_dict': {
1418 'id': '6SJNVb0GnPI',
1419 'ext': 'mp4',
1420 'title': 'Race Differences in Intelligence',
1421 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1422 'duration': 965,
1423 'upload_date': '20140124',
1424 'uploader': 'New Century Foundation',
1425 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1426 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1427 },
1428 'params': {
1429 'skip_download': True,
1430 },
545cc85d 1431 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1432 },
022a5d66
S
1433 {
1434 # itag 212
1435 'url': '1t24XAntNCY',
1436 'only_matching': True,
fd5c4aab
S
1437 },
1438 {
1439 # geo restricted to JP
1440 'url': 'sJL6WA-aGkQ',
1441 'only_matching': True,
1442 },
cd5a74a2
S
1443 {
1444 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1445 'only_matching': True,
1446 },
bc2ca1bb 1447 {
1448 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1449 'only_matching': True,
1450 },
1451 {
1452 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1453 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1454 'only_matching': True,
1455 },
825cd268
RA
1456 {
1457 # DRM protected
1458 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1459 'only_matching': True,
4fe54c12
S
1460 },
1461 {
1462 # Video with unsupported adaptive stream type formats
1463 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1464 'info_dict': {
1465 'id': 'Z4Vy8R84T1U',
1466 'ext': 'mp4',
1467 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1468 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1469 'duration': 433,
1470 'upload_date': '20130923',
1471 'uploader': 'Amelia Putri Harwita',
1472 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1473 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1474 'formats': 'maxcount:10',
1475 },
1476 'params': {
1477 'skip_download': True,
1478 'youtube_include_dash_manifest': False,
1479 },
5429d6a9 1480 'skip': 'not actual anymore',
5caabd3c 1481 },
1482 {
822b9d9c 1483 # Youtube Music Auto-generated description
5caabd3c 1484 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1485 'info_dict': {
1486 'id': 'MgNrAu2pzNs',
1487 'ext': 'mp4',
1488 'title': 'Voyeur Girl',
1489 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1490 'upload_date': '20190312',
5429d6a9
S
1491 'uploader': 'Stephen - Topic',
1492 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1493 'artist': 'Stephen',
1494 'track': 'Voyeur Girl',
1495 'album': 'it\'s too much love to know my dear',
1496 'release_date': '20190313',
1497 'release_year': 2019,
1498 },
1499 'params': {
1500 'skip_download': True,
1501 },
1502 },
66b48727
RA
1503 {
1504 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1505 'only_matching': True,
1506 },
011e75e6
S
1507 {
1508 # invalid -> valid video id redirection
1509 'url': 'DJztXj2GPfl',
1510 'info_dict': {
1511 'id': 'DJztXj2GPfk',
1512 'ext': 'mp4',
1513 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1514 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1515 'upload_date': '20090125',
1516 'uploader': 'Prochorowka',
1517 'uploader_id': 'Prochorowka',
1518 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1519 'artist': 'Panjabi MC',
1520 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1521 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1522 },
1523 'params': {
1524 'skip_download': True,
1525 },
545cc85d 1526 'skip': 'Video unavailable',
ea74e00b
DP
1527 },
1528 {
1529 # empty description results in an empty string
1530 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1531 'info_dict': {
1532 'id': 'x41yOUIvK2k',
1533 'ext': 'mp4',
1534 'title': 'IMG 3456',
1535 'description': '',
1536 'upload_date': '20170613',
1537 'uploader_id': 'ElevageOrVert',
1538 'uploader': 'ElevageOrVert',
1539 },
1540 'params': {
1541 'skip_download': True,
1542 },
1543 },
a0566bbf 1544 {
29f7c58a 1545 # with '};' inside yt initial data (see [1])
1546 # see [2] for an example with '};' inside ytInitialPlayerResponse
1547 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1548 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1549 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1550 'info_dict': {
1551 'id': 'CHqg6qOn4no',
1552 'ext': 'mp4',
1553 'title': 'Part 77 Sort a list of simple types in c#',
1554 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1555 'upload_date': '20130831',
1556 'uploader_id': 'kudvenkat',
1557 'uploader': 'kudvenkat',
1558 },
1559 'params': {
1560 'skip_download': True,
1561 },
1562 },
29f7c58a 1563 {
1564 # another example of '};' in ytInitialData
1565 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1566 'only_matching': True,
1567 },
1568 {
1569 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1570 'only_matching': True,
1571 },
545cc85d 1572 {
cc2db878 1573 # https://github.com/ytdl-org/youtube-dl/pull/28094
1574 'url': 'OtqTfy26tG0',
1575 'info_dict': {
1576 'id': 'OtqTfy26tG0',
1577 'ext': 'mp4',
1578 'title': 'Burn Out',
1579 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1580 'upload_date': '20141120',
1581 'uploader': 'The Cinematic Orchestra - Topic',
1582 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1583 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1584 'artist': 'The Cinematic Orchestra',
1585 'track': 'Burn Out',
1586 'album': 'Every Day',
1587 'release_data': None,
1588 'release_year': None,
1589 },
1590 'params': {
1591 'skip_download': True,
1592 },
545cc85d 1593 },
bc2ca1bb 1594 {
1595 # controversial video, only works with bpctr when authenticated with cookies
1596 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1597 'only_matching': True,
1598 },
a1a7907b 1599 {
1600 # controversial video, requires bpctr/contentCheckOk
1601 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1602 'info_dict': {
1603 'id': 'SZJvDhaSDnc',
1604 'ext': 'mp4',
1605 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1606 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
1607 'uploader': 'CBS This Morning',
11f9be09 1608 'uploader_id': 'CBSThisMorning',
a1a7907b 1609 'upload_date': '20140716',
1610 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7'
1611 }
1612 },
f7ad7160 1613 {
1614 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1615 'url': 'cBvYw8_A0vQ',
1616 'info_dict': {
1617 'id': 'cBvYw8_A0vQ',
1618 'ext': 'mp4',
1619 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
1620 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
1621 'upload_date': '20201120',
1622 'uploader': 'Walk around Japan',
1623 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1624 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1625 },
1626 'params': {
1627 'skip_download': True,
1628 },
0fb983f6 1629 }, {
1630 # Has multiple audio streams
1631 'url': 'WaOKSUlf4TM',
1632 'only_matching': True
9297939e 1633 }, {
1634 # Requires Premium: has format 141 when requested using YTM url
1635 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
1636 'only_matching': True
1637 }, {
120916da 1638 # multiple subtitles with same lang_code
1639 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
1640 'only_matching': True,
109dd3b2 1641 }, {
1642 # Force use android client fallback
1643 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
1644 'info_dict': {
1645 'id': 'YOelRv7fMxY',
11f9be09 1646 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 1647 'ext': '3gp',
1648 'upload_date': '20210624',
1649 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
1650 'uploader': 'colinfurze',
11f9be09 1651 'uploader_id': 'colinfurze',
109dd3b2 1652 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
11f9be09 1653 'description': 'md5:b5096f56af7ccd7a555c84db81738b22'
109dd3b2 1654 },
1655 'params': {
1656 'format': '17', # 3gp format available on android
1657 'extractor_args': {'youtube': {'player_client': ['android']}},
1658 },
120916da 1659 },
109dd3b2 1660 {
1661 # Skip download of additional client configs (remix client config in this case)
1662 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1663 'only_matching': True,
1664 'params': {
1665 'extractor_args': {'youtube': {'player_skip': ['configs']}},
1666 },
8fc54b12 1667 }, {
1668 # shorts
1669 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
1670 'only_matching': True,
1671 },
2eb88d95
PH
1672 ]
1673
201c1459 1674 @classmethod
1675 def suitable(cls, url):
4dfbf869 1676 from ..utils import parse_qs
1677
201c1459 1678 qs = parse_qs(url)
1679 if qs.get('list', [None])[0]:
1680 return False
1681 return super(YoutubeIE, cls).suitable(url)
1682
e0df6211
PH
1683 def __init__(self, *args, **kwargs):
1684 super(YoutubeIE, self).__init__(*args, **kwargs)
545cc85d 1685 self._code_cache = {}
83799698 1686 self._player_cache = {}
e0df6211 1687
b6de707d 1688 def _extract_player_url(self, *ytcfgs, webpage=None):
1689 player_url = traverse_obj(
1690 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
1691 get_all=False, expected_type=compat_str)
11f9be09 1692 if not player_url:
b6de707d 1693 return
109dd3b2 1694 if player_url.startswith('//'):
1695 player_url = 'https:' + player_url
1696 elif not re.match(r'https?://', player_url):
1697 player_url = compat_urlparse.urljoin(
1698 'https://www.youtube.com', player_url)
1699 return player_url
1700
b6de707d 1701 def _download_player_url(self, video_id, fatal=False):
1702 res = self._download_webpage(
1703 'https://www.youtube.com/iframe_api',
1704 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
1705 if res:
1706 player_version = self._search_regex(
1707 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
1708 if player_version:
1709 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
1710
60064c53
PH
1711 def _signature_cache_id(self, example_sig):
1712 """ Return a string representation of a signature """
78caa52a 1713 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53 1714
e40c758c
S
1715 @classmethod
1716 def _extract_player_info(cls, player_url):
1717 for player_re in cls._PLAYER_INFO_RE:
1718 id_m = re.search(player_re, player_url)
1719 if id_m:
1720 break
1721 else:
c081b35c 1722 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 1723 return id_m.group('id')
e40c758c 1724
404f611f 1725 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 1726 player_id = self._extract_player_info(player_url)
1727 if player_id not in self._code_cache:
1276a43a 1728 code = self._download_webpage(
109dd3b2 1729 player_url, video_id, fatal=fatal,
1730 note='Downloading player ' + player_id,
1731 errnote='Download of %s failed' % player_url)
1276a43a 1732 if code:
1733 self._code_cache[player_id] = code
404f611f 1734 return self._code_cache.get(player_id)
109dd3b2 1735
e40c758c 1736 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 1737 player_id = self._extract_player_info(player_url)
e0df6211 1738
c4417ddb 1739 # Read from filesystem cache
545cc85d 1740 func_id = 'js_%s_%s' % (
1741 player_id, self._signature_cache_id(example_sig))
c4417ddb 1742 assert os.path.basename(func_id) == func_id
a0e07d31 1743
69ea8ca4 1744 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
a0e07d31 1745 if cache_spec is not None:
78caa52a 1746 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 1747
404f611f 1748 code = self._load_player(video_id, player_url)
1749 if code:
109dd3b2 1750 res = self._parse_sig_js(code)
e0df6211 1751
109dd3b2 1752 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1753 cache_res = res(test_string)
1754 cache_spec = [ord(c) for c in cache_res]
83799698 1755
109dd3b2 1756 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
1757 return res
83799698 1758
60064c53 1759 def _print_sig_code(self, func, example_sig):
404f611f 1760 if not self.get_param('youtube_print_sig_code'):
1761 return
1762
edf3e38e
PH
1763 def gen_sig_code(idxs):
1764 def _genslice(start, end, step):
78caa52a 1765 starts = '' if start == 0 else str(start)
8bcc8756 1766 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 1767 steps = '' if step == 1 else (':%d' % step)
78caa52a 1768 return 's[%s%s%s]' % (starts, ends, steps)
edf3e38e
PH
1769
1770 step = None
7af808a5
PH
1771 # Quelch pyflakes warnings - start will be set when step is set
1772 start = '(Never used)'
edf3e38e
PH
1773 for i, prev in zip(idxs[1:], idxs[:-1]):
1774 if step is not None:
1775 if i - prev == step:
1776 continue
1777 yield _genslice(start, prev, step)
1778 step = None
1779 continue
1780 if i - prev in [-1, 1]:
1781 step = i - prev
1782 start = prev
1783 continue
1784 else:
78caa52a 1785 yield 's[%d]' % prev
edf3e38e 1786 if step is None:
78caa52a 1787 yield 's[%d]' % i
edf3e38e
PH
1788 else:
1789 yield _genslice(start, i, step)
1790
78caa52a 1791 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 1792 cache_res = func(test_string)
edf3e38e 1793 cache_spec = [ord(c) for c in cache_res]
78caa52a 1794 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
1795 signature_id_tuple = '(%s)' % (
1796 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 1797 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 1798 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 1799 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 1800
e0df6211
PH
1801 def _parse_sig_js(self, jscode):
1802 funcname = self._search_regex(
abefc03f
S
1803 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1804 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
1805 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
1806 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
1807 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}\(a,\d+\)',
1808 r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
31ce6e99 1809 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
1810 # Obsolete patterns
1811 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 1812 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
1813 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1814 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1815 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1816 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1817 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1818 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 1819 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
1820
1821 jsi = JSInterpreter(jscode)
1822 initial_function = jsi.extract_function(funcname)
e0df6211
PH
1823 return lambda s: initial_function([s])
1824
545cc85d 1825 def _decrypt_signature(self, s, video_id, player_url):
257a2501 1826 """Turn the encrypted s field into a working signature"""
6b37f0be 1827
c8bf86d5 1828 if player_url is None:
69ea8ca4 1829 raise ExtractorError('Cannot decrypt signature without player_url')
920de7a2 1830
c8bf86d5 1831 try:
62af3a0e 1832 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5
PH
1833 if player_id not in self._player_cache:
1834 func = self._extract_signature_function(
60064c53 1835 video_id, player_url, s
c8bf86d5
PH
1836 )
1837 self._player_cache[player_id] = func
1838 func = self._player_cache[player_id]
404f611f 1839 self._print_sig_code(func, s)
c8bf86d5
PH
1840 return func(s)
1841 except Exception as e:
404f611f 1842 raise ExtractorError('Signature extraction failed: ' + traceback.format_exc(), cause=e)
1843
1844 def _decrypt_nsig(self, s, video_id, player_url):
1845 """Turn the encrypted n field into a working signature"""
1846 if player_url is None:
1847 raise ExtractorError('Cannot decrypt nsig without player_url')
1848 if player_url.startswith('//'):
1849 player_url = 'https:' + player_url
1850 elif not re.match(r'https?://', player_url):
1851 player_url = compat_urlparse.urljoin(
1852 'https://www.youtube.com', player_url)
1853
1854 sig_id = ('nsig_value', s)
1855 if sig_id in self._player_cache:
1856 return self._player_cache[sig_id]
1857
1858 try:
1859 player_id = ('nsig', player_url)
1860 if player_id not in self._player_cache:
1861 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
1862 func = self._player_cache[player_id]
1863 self._player_cache[sig_id] = func(s)
1864 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
1865 return self._player_cache[sig_id]
1866 except Exception as e:
aa9369a2 1867 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 1868
1869 def _extract_n_function_name(self, jscode):
1870 return self._search_regex(
1871 (r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]{3})\([a-zA-Z0-9]\)',),
1872 jscode, 'Initial JS player n function name', group='nfunc')
1873
1874 def _extract_n_function(self, video_id, player_url):
1875 player_id = self._extract_player_info(player_url)
1876 func_code = self._downloader.cache.load('youtube-nsig', player_id)
1877
1878 if func_code:
1879 jsi = JSInterpreter(func_code)
1880 else:
1881 jscode = self._load_player(video_id, player_url)
1882 funcname = self._extract_n_function_name(jscode)
1883 jsi = JSInterpreter(jscode)
1884 func_code = jsi.extract_function_code(funcname)
1885 self._downloader.cache.store('youtube-nsig', player_id, func_code)
1886
1887 if self.get_param('youtube_print_sig_code'):
1888 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
1889
1890 return lambda s: jsi.extract_function_from_code(*func_code)([s])
e0df6211 1891
109dd3b2 1892 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
1893 """
1894 Extract signatureTimestamp (sts)
1895 Required to tell API what sig/player version is in use.
1896 """
1897 sts = None
1898 if isinstance(ytcfg, dict):
1899 sts = int_or_none(ytcfg.get('STS'))
1900
1901 if not sts:
1902 # Attempt to extract from player
1903 if player_url is None:
1904 error_msg = 'Cannot extract signature timestamp without player_url.'
1905 if fatal:
1906 raise ExtractorError(error_msg)
1907 self.report_warning(error_msg)
1908 return
404f611f 1909 code = self._load_player(video_id, player_url, fatal=fatal)
1910 if code:
109dd3b2 1911 sts = int_or_none(self._search_regex(
1912 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
1913 'JS player signature timestamp', group='sts', fatal=fatal))
1914 return sts
1915
11f9be09 1916 def _mark_watched(self, video_id, player_responses):
352d63fd 1917 playback_url = traverse_obj(
1918 player_responses, (..., 'playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'),
1919 expected_type=url_or_none, get_all=False)
d77ab8e2 1920 if not playback_url:
352d63fd 1921 self.report_warning('Unable to mark watched')
d77ab8e2
S
1922 return
1923 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1924 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1925
1926 # cpn generation algorithm is reverse engineered from base.js.
1927 # In fact it works even with dummy cpn.
1928 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1929 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1930
1931 qs.update({
1932 'ver': ['2'],
1933 'cpn': [cpn],
1934 })
1935 playback_url = compat_urlparse.urlunparse(
15707c7e 1936 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
d77ab8e2
S
1937
1938 self._download_webpage(
1939 playback_url, video_id, 'Marking watched',
1940 'Unable to mark watched', fatal=False)
1941
66c9fa36
S
1942 @staticmethod
1943 def _extract_urls(webpage):
1944 # Embedded YouTube player
1945 entries = [
1946 unescapeHTML(mobj.group('url'))
1947 for mobj in re.finditer(r'''(?x)
1948 (?:
1949 <iframe[^>]+?src=|
1950 data-video-url=|
1951 <embed[^>]+?src=|
1952 embedSWF\(?:\s*|
1953 <object[^>]+data=|
1954 new\s+SWFObject\(
1955 )
1956 (["\'])
1957 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 1958 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
1959 \1''', webpage)]
1960
1961 # lazyYT YouTube embed
1962 entries.extend(list(map(
1963 unescapeHTML,
1964 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
1965
1966 # Wordpress "YouTube Video Importer" plugin
1967 matches = re.findall(r'''(?x)<div[^>]+
1968 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1969 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1970 entries.extend(m[-1] for m in matches)
1971
1972 return entries
1973
1974 @staticmethod
1975 def _extract_url(webpage):
1976 urls = YoutubeIE._extract_urls(webpage)
1977 return urls[0] if urls else None
1978
97665381
PH
1979 @classmethod
1980 def extract_id(cls, url):
1981 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 1982 if mobj is None:
69ea8ca4 1983 raise ExtractorError('Invalid URL: %s' % url)
5ad28e7f 1984 return mobj.group('id')
c5e8d7af 1985
7c365c21 1986 def _extract_chapters_from_json(self, data, duration):
1987 chapter_list = traverse_obj(
1988 data, (
1989 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
1990 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
1991 ), expected_type=list)
1992
1993 return self._extract_chapters(
1994 chapter_list,
1995 chapter_time=lambda chapter: float_or_none(
1996 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
1997 chapter_title=lambda chapter: traverse_obj(
1998 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
1999 duration=duration)
2000
2001 def _extract_chapters_from_engagement_panel(self, data, duration):
2002 content_list = traverse_obj(
8bdd16b4 2003 data,
7c365c21 2004 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2005 expected_type=list, default=[])
052e1350 2006 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2007 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2008
2009 return next((
2010 filter(None, (
2011 self._extract_chapters(
2012 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2013 chapter_time, chapter_title, duration)
2014 for contents in content_list
2015 ))), [])
2016
2017 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
84213ea8 2018 chapters = []
7c365c21 2019 last_chapter = {'start_time': 0}
2020 for idx, chapter in enumerate(chapter_list or []):
2021 title = chapter_title(chapter)
84213ea8
S
2022 start_time = chapter_time(chapter)
2023 if start_time is None:
2024 continue
7c365c21 2025 last_chapter['end_time'] = start_time
2026 if start_time < last_chapter['start_time']:
2027 if idx == 1:
2028 chapters.pop()
2029 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2030 else:
2031 self.report_warning(f'Invalid start time for chapter "{title}"')
2032 continue
2033 last_chapter = {'start_time': start_time, 'title': title}
2034 chapters.append(last_chapter)
2035 last_chapter['end_time'] = duration
84213ea8
S
2036 return chapters
2037
545cc85d 2038 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2039 return self._parse_json(self._search_regex(
2040 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
2041 regex), webpage, name, default='{}'), video_id, fatal=False)
84213ea8 2042
d92f5d5a 2043 @staticmethod
2044 def parse_time_text(time_text):
2045 """
2046 Parse the comment time text
2047 time_text is in the format 'X units ago (edited)'
2048 """
2049 time_text_split = time_text.split(' ')
2050 if len(time_text_split) >= 3:
da503b7a 2051 try:
2052 return datetime_from_str('now-%s%s' % (time_text_split[0], time_text_split[1]), precision='auto')
2053 except ValueError:
2054 return None
d92f5d5a 2055
a1c5d2ca
M
2056 def _extract_comment(self, comment_renderer, parent=None):
2057 comment_id = comment_renderer.get('commentId')
2058 if not comment_id:
2059 return
fe93e2c4 2060
052e1350 2061 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2062
49bd8c66 2063 # note: timestamp is an estimate calculated from the current time and time_text
052e1350 2064 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
fe93e2c4 2065 time_text_dt = self.parse_time_text(time_text)
2066 if isinstance(time_text_dt, datetime.datetime):
2067 timestamp = calendar.timegm(time_text_dt.timetuple())
052e1350 2068 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca
M
2069 author_id = try_get(comment_renderer,
2070 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
fe93e2c4 2071
49bd8c66 2072 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2073 lambda x: x['likeCount']), compat_str)) or 0
a1c5d2ca
M
2074 author_thumbnail = try_get(comment_renderer,
2075 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2076
2077 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2078 is_favorited = 'creatorHeart' in (try_get(
2079 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2080 return {
2081 'id': comment_id,
2082 'text': text,
d92f5d5a 2083 'timestamp': timestamp,
a1c5d2ca
M
2084 'time_text': time_text,
2085 'like_count': votes,
97524332 2086 'is_favorited': is_favorited,
a1c5d2ca
M
2087 'author': author,
2088 'author_id': author_id,
2089 'author_thumbnail': author_thumbnail,
2090 'author_is_uploader': author_is_uploader,
2091 'parent': parent or 'root'
2092 }
2093
99e9e001 2094 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, comment_counts=None):
2d6659b9 2095
2096 def extract_header(contents):
2d6659b9 2097 _continuation = None
2098 for content in contents:
2099 comments_header_renderer = try_get(content, lambda x: x['commentsHeaderRenderer'])
fe93e2c4 2100 expected_comment_count = parse_count(self._get_text(
052e1350 2101 comments_header_renderer, 'countText', 'commentsCount', max_runs=1))
fe93e2c4 2102
2d6659b9 2103 if expected_comment_count:
fe93e2c4 2104 comment_counts[1] = expected_comment_count
2105 self.to_screen('Downloading ~%d comments' % expected_comment_count)
2d6659b9 2106 sort_mode_str = self._configuration_arg('comment_sort', [''])[0]
2107 comment_sort_index = int(sort_mode_str != 'top') # 1 = new, 0 = top
2108
2109 sort_menu_item = try_get(
2110 comments_header_renderer,
2111 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2112 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2113
2114 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2115 if not _continuation:
2116 continue
2117
2118 sort_text = sort_menu_item.get('title')
2119 if isinstance(sort_text, compat_str):
2120 sort_text = sort_text.lower()
2121 else:
2122 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
2123 self.to_screen('Sorting comments by %s' % sort_text)
2124 break
a2160aa4 2125 return _continuation
a1c5d2ca 2126
2d6659b9 2127 def extract_thread(contents):
a1c5d2ca
M
2128 if not parent:
2129 comment_counts[2] = 0
2130 for content in contents:
2131 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
2132 comment_renderer = try_get(
2133 comment_thread_renderer, (lambda x: x['comment']['commentRenderer'], dict)) or try_get(
2134 content, (lambda x: x['commentRenderer'], dict))
2135
2136 if not comment_renderer:
2137 continue
2138 comment = self._extract_comment(comment_renderer, parent)
2139 if not comment:
2140 continue
2141 comment_counts[0] += 1
2142 yield comment
2143 # Attempt to get the replies
2144 comment_replies_renderer = try_get(
2145 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2146
2147 if comment_replies_renderer:
2148 comment_counts[2] += 1
2149 comment_entries_iter = self._comment_entries(
99e9e001 2150 comment_replies_renderer, ytcfg, video_id,
2151 parent=comment.get('id'), comment_counts=comment_counts)
a1c5d2ca
M
2152
2153 for reply_comment in comment_entries_iter:
2154 yield reply_comment
2155
2d6659b9 2156 # YouTube comments have a max depth of 2
2157 max_depth = int_or_none(self._configuration_arg('max_comment_depth', [''])[0]) or float('inf')
2158 if max_depth == 1 and parent:
2159 return
a1c5d2ca
M
2160 if not comment_counts:
2161 # comment so far, est. total comments, current comment thread #
2162 comment_counts = [0, 0, 0]
a1c5d2ca 2163
2d6659b9 2164 continuation = self._extract_continuation(root_continuation_data)
fe93e2c4 2165 if continuation and len(continuation['continuation']) < 27:
2d6659b9 2166 self.write_debug('Detected old API continuation token. Generating new API compatible token.')
2167 continuation_token = self._generate_comment_continuation(video_id)
fe93e2c4 2168 continuation = self._build_api_continuation_query(continuation_token, None)
2d6659b9 2169
aae16f6e 2170 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2171 if message and not parent:
2172 self.report_warning(message, video_id=video_id)
2173
2d6659b9 2174 visitor_data = None
2175 is_first_continuation = parent is None
a1c5d2ca
M
2176
2177 for page_num in itertools.count(0):
2178 if not continuation:
2179 break
99e9e001 2180 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=visitor_data)
2d6659b9 2181 comment_prog_str = '(%d/%d)' % (comment_counts[0], comment_counts[1])
2182 if page_num == 0:
2183 if is_first_continuation:
2184 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2185 else:
2d6659b9 2186 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
2187 comment_counts[2], comment_prog_str)
2188 else:
2189 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2190 ' ' if parent else '', ' replies' if parent else '',
2191 page_num, comment_prog_str)
2192
2193 response = self._extract_response(
fe93e2c4 2194 item_id=None, query=continuation,
2d6659b9 2195 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
2196 check_get_keys=('onResponseReceivedEndpoints', 'continuationContents'))
a1c5d2ca
M
2197 if not response:
2198 break
f4f751af 2199 visitor_data = try_get(
2200 response,
2201 lambda x: x['responseContext']['webResponseContextExtensionData']['ytConfigData']['visitorData'],
2202 compat_str) or visitor_data
a1c5d2ca 2203
2d6659b9 2204 continuation_contents = dict_get(response, ('onResponseReceivedEndpoints', 'continuationContents'))
a1c5d2ca 2205
2d6659b9 2206 continuation = None
2207 if isinstance(continuation_contents, list):
2208 for continuation_section in continuation_contents:
2209 if not isinstance(continuation_section, dict):
2210 continue
2211 continuation_items = try_get(
2212 continuation_section,
2213 (lambda x: x['reloadContinuationItemsCommand']['continuationItems'],
2214 lambda x: x['appendContinuationItemsAction']['continuationItems']),
2215 list) or []
2216 if is_first_continuation:
a2160aa4 2217 continuation = extract_header(continuation_items)
2d6659b9 2218 is_first_continuation = False
2219 if continuation:
2220 break
2221 continue
2222 count = 0
2223 for count, entry in enumerate(extract_thread(continuation_items)):
2224 yield entry
2225 continuation = self._extract_continuation({'contents': continuation_items})
2226 if continuation:
2227 # Sometimes YouTube provides a continuation without any comments
2228 # In most cases we end up just downloading these with very little comments to come.
2229 if count == 0:
2230 if not parent:
2231 self.report_warning('No comments received - assuming end of comments')
2232 continuation = None
a1c5d2ca
M
2233 break
2234
2d6659b9 2235 # Deprecated response structure
2236 elif isinstance(continuation_contents, dict):
2237 known_continuation_renderers = ('itemSectionContinuation', 'commentRepliesContinuation')
2238 for key, continuation_renderer in continuation_contents.items():
2239 if key not in known_continuation_renderers:
2240 continue
2241 if not isinstance(continuation_renderer, dict):
2242 continue
2243 if is_first_continuation:
2244 header_continuation_items = [continuation_renderer.get('header') or {}]
a2160aa4 2245 continuation = extract_header(header_continuation_items)
2d6659b9 2246 is_first_continuation = False
2247 if continuation:
2248 break
a1c5d2ca 2249
2d6659b9 2250 # Sometimes YouTube provides a continuation without any comments
2251 # In most cases we end up just downloading these with very little comments to come.
2252 count = 0
2253 for count, entry in enumerate(extract_thread(continuation_renderer.get('contents') or {})):
2254 yield entry
2255 continuation = self._extract_continuation(continuation_renderer)
2256 if count == 0:
2257 if not parent:
2258 self.report_warning('No comments received - assuming end of comments')
2259 continuation = None
2260 break
a1c5d2ca 2261
2d6659b9 2262 @staticmethod
2263 def _generate_comment_continuation(video_id):
2264 """
2265 Generates initial comment section continuation token from given video id
2266 """
2267 b64_vid_id = base64.b64encode(bytes(video_id.encode('utf-8')))
2268 parts = ('Eg0SCw==', b64_vid_id, 'GAYyJyIRIgs=', b64_vid_id, 'MAB4AjAAQhBjb21tZW50cy1zZWN0aW9u')
2269 new_continuation_intlist = list(itertools.chain.from_iterable(
2270 [bytes_to_intlist(base64.b64decode(part)) for part in parts]))
2271 return base64.b64encode(intlist_to_bytes(new_continuation_intlist)).decode('utf-8')
2272
a2160aa4 2273 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 2274 """Entry for comment extraction"""
2d6659b9 2275 def _real_comment_extract(contents):
aae16f6e 2276 renderer = next((
2277 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2278 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2279 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 2280
a2160aa4 2281 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
65524694 2282 # Force English regardless of account setting to prevent parsing issues
2283 # See: https://github.com/yt-dlp/yt-dlp/issues/532
2284 ytcfg = copy.deepcopy(ytcfg)
2285 traverse_obj(
2286 ytcfg, ('INNERTUBE_CONTEXT', 'client'), expected_type=dict, default={})['hl'] = 'en'
a2160aa4 2287 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 2288
109dd3b2 2289 @staticmethod
99e9e001 2290 def _get_checkok_params():
2291 return {'contentCheckOk': True, 'racyCheckOk': True}
2292
2293 @classmethod
2294 def _generate_player_context(cls, sts=None):
109dd3b2 2295 context = {
2296 'html5Preference': 'HTML5_PREF_WANTS',
2297 }
2298 if sts is not None:
2299 context['signatureTimestamp'] = sts
2300 return {
2301 'playbackContext': {
2302 'contentPlaybackContext': context
a1a7907b 2303 },
99e9e001 2304 **cls._get_checkok_params()
109dd3b2 2305 }
2306
e7e94f2a
D
2307 @staticmethod
2308 def _is_agegated(player_response):
2309 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 2310 return True
e7e94f2a
D
2311
2312 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2313 AGE_GATE_REASONS = (
2314 'confirm your age', 'age-restricted', 'inappropriate', # reason
2315 'age_verification_required', 'age_check_required', # status
2316 )
2317 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
2318
2319 @staticmethod
2320 def _is_unplayable(player_response):
2321 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 2322
99e9e001 2323 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
109dd3b2 2324
11f9be09 2325 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2326 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 2327 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 2328 headers = self.generate_api_headers(
99e9e001 2329 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 2330
11f9be09 2331 yt_query = {'videoId': video_id}
2332 yt_query.update(self._generate_player_context(sts))
2333 return self._extract_response(
2334 item_id=video_id, ep='player', query=yt_query,
379e44ed 2335 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 2336 default_client=client,
11f9be09 2337 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2338 ) or None
2339
11f9be09 2340 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 2341 requested_clients = []
000c15a4 2342 allowed_clients = sorted(
2343 [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'],
2344 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 2345 for client in self._configuration_arg('player_client'):
2346 if client in allowed_clients:
2347 requested_clients.append(client)
2348 elif client == 'all':
2349 requested_clients.extend(allowed_clients)
2350 else:
2351 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 2352 if not requested_clients:
2353 requested_clients = ['android', 'web']
cf7e015f 2354
11f9be09 2355 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2356 requested_clients.extend(
e7e94f2a 2357 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 2358
11f9be09 2359 return orderedSet(requested_clients)
cf7e015f 2360
c0bc527b
M
2361 def _extract_player_ytcfg(self, client, video_id):
2362 url = {
2363 'web_music': 'https://music.youtube.com',
2364 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
2365 }.get(client)
2366 if not url:
2367 return {}
2368 webpage = self._download_webpage(url, video_id, fatal=False, note=f'Downloading {client} config')
2369 return self.extract_ytcfg(video_id, webpage) or {}
2370
99e9e001 2371 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
11f9be09 2372 initial_pr = None
2373 if webpage:
2374 initial_pr = self._extract_yt_initial_variable(
2375 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2376 video_id, 'initial player response')
6b09401b 2377
c0bc527b
M
2378 original_clients = clients
2379 clients = clients[::-1]
b6de707d 2380 prs = []
e7e94f2a
D
2381
2382 def append_client(client_name):
2383 if client_name in INNERTUBE_CLIENTS and client_name not in original_clients:
2384 clients.append(client_name)
2385
379e44ed 2386 # Android player_response does not have microFormats which are needed for
2387 # extraction of some data. So we return the initial_pr with formats
2388 # stripped out even if not requested by the user
2389 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 2390 if initial_pr:
2391 pr = dict(initial_pr)
2392 pr['streamingData'] = None
b6de707d 2393 prs.append(pr)
379e44ed 2394
2395 last_error = None
b6de707d 2396 tried_iframe_fallback = False
2397 player_url = None
c0bc527b
M
2398 while clients:
2399 client = clients.pop()
11f9be09 2400 player_ytcfg = master_ytcfg if client == 'web' else {}
c0bc527b
M
2401 if 'configs' not in self._configuration_arg('player_skip'):
2402 player_ytcfg = self._extract_player_ytcfg(client, video_id) or player_ytcfg
c0bc527b 2403
b6de707d 2404 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
2405 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
2406 if 'js' in self._configuration_arg('player_skip'):
2407 require_js_player = False
2408 player_url = None
2409
2410 if not player_url and not tried_iframe_fallback and require_js_player:
2411 player_url = self._download_player_url(video_id)
2412 tried_iframe_fallback = True
2413
379e44ed 2414 try:
2415 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
99e9e001 2416 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
379e44ed 2417 except ExtractorError as e:
2418 if last_error:
2419 self.report_warning(last_error)
2420 last_error = e
2421 continue
2422
11f9be09 2423 if pr:
b6de707d 2424 prs.append(pr)
c0bc527b 2425
e7e94f2a 2426 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
99e9e001 2427 if client.endswith('_agegate') and self._is_unplayable(pr) and self.is_authenticated:
e7e94f2a
D
2428 append_client(client.replace('_agegate', '_creator'))
2429 elif self._is_agegated(pr):
2430 append_client(f'{client}_agegate')
c0bc527b 2431
379e44ed 2432 if last_error:
b6de707d 2433 if not len(prs):
379e44ed 2434 raise last_error
2435 self.report_warning(last_error)
b6de707d 2436 return prs, player_url
11f9be09 2437
2438 def _extract_formats(self, streaming_data, video_id, player_url, is_live):
a0bb6ce5 2439 itags, stream_ids = {}, []
2a9c6dcd 2440 itag_qualities, res_qualities = {}, {}
d3fc8074 2441 q = qualities([
2a9c6dcd 2442 # Normally tiny is the smallest video-only formats. But
2443 # audio-only formats with unknown quality may get tagged as tiny
2444 'tiny',
2445 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 2446 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
2447 ])
11f9be09 2448 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 2449
545cc85d 2450 for fmt in streaming_formats:
2451 if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
2452 continue
321bf820 2453
cc2db878 2454 itag = str_or_none(fmt.get('itag'))
9297939e 2455 audio_track = fmt.get('audioTrack') or {}
2456 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
2457 if stream_id in stream_ids:
2458 continue
2459
cc2db878 2460 quality = fmt.get('quality')
2a9c6dcd 2461 height = int_or_none(fmt.get('height'))
d3fc8074 2462 if quality == 'tiny' or not quality:
2463 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 2464 # The 3gp format (17) in android client has a quality of "small",
2465 # but is actually worse than other formats
2466 if itag == '17':
2467 quality = 'tiny'
2468 if quality:
2469 if itag:
2470 itag_qualities[itag] = quality
2471 if height:
2472 res_qualities[height] = quality
cc2db878 2473 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
2474 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
2475 # number of fragment that would subsequently requested with (`&sq=N`)
2476 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
2477 continue
2478
545cc85d 2479 fmt_url = fmt.get('url')
2480 if not fmt_url:
2481 sc = compat_parse_qs(fmt.get('signatureCipher'))
2482 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
2483 encrypted_sig = try_get(sc, lambda x: x['s'][0])
2484 if not (sc and fmt_url and encrypted_sig):
2485 continue
545cc85d 2486 if not player_url:
201e9eaa 2487 continue
545cc85d 2488 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
2489 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
2490 fmt_url += '&' + sp + '=' + signature
2491
404f611f 2492 query = parse_qs(fmt_url)
2493 throttled = False
2494 if query.get('ratebypass') != ['yes'] and query.get('n'):
2495 try:
2496 fmt_url = update_url_query(fmt_url, {
2497 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
2498 except ExtractorError as e:
aa9369a2 2499 self.report_warning(
2500 f'nsig extraction failed: You may experience throttling for some formats\n'
2501 f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True)
404f611f 2502 throttled = True
2503
545cc85d 2504 if itag:
a0bb6ce5 2505 itags[itag] = 'https'
9297939e 2506 stream_ids.append(stream_id)
2507
cc2db878 2508 tbr = float_or_none(
2509 fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
545cc85d 2510 dct = {
2511 'asr': int_or_none(fmt.get('audioSampleRate')),
2512 'filesize': int_or_none(fmt.get('contentLength')),
2513 'format_id': itag,
34921b43 2514 'format_note': join_nonempty(
26e8e044 2515 '%s%s' % (audio_track.get('displayName') or '',
2516 ' (default)' if audio_track.get('audioIsDefault') else ''),
404f611f 2517 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
34921b43 2518 throttled and 'THROTTLED', delim=', '),
c18d4482 2519 'source_preference': -10 if throttled else -1,
a4211baf 2520 'fps': int_or_none(fmt.get('fps')) or None,
2a9c6dcd 2521 'height': height,
dca3ff4a 2522 'quality': q(quality),
cc2db878 2523 'tbr': tbr,
545cc85d 2524 'url': fmt_url,
2a9c6dcd 2525 'width': int_or_none(fmt.get('width')),
0fb983f6 2526 'language': audio_track.get('id', '').split('.')[0],
26e8e044 2527 'language_preference': 1 if audio_track.get('audioIsDefault') else -1,
545cc85d 2528 }
60bdb7bd 2529 mime_mobj = re.match(
2530 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
2531 if mime_mobj:
2532 dct['ext'] = mimetype2ext(mime_mobj.group(1))
2533 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 2534 no_audio = dct.get('acodec') == 'none'
2535 no_video = dct.get('vcodec') == 'none'
2536 if no_audio:
2537 dct['vbr'] = tbr
2538 if no_video:
2539 dct['abr'] = tbr
2540 if no_audio or no_video:
545cc85d 2541 dct['downloader_options'] = {
2542 # Youtube throttles chunks >~10M
2543 'http_chunk_size': 10485760,
bf1317d2 2544 }
7c60c33e 2545 if dct.get('ext'):
2546 dct['container'] = dct['ext'] + '_dash'
11f9be09 2547 yield dct
545cc85d 2548
4bb6b02f 2549 skip_manifests = self._configuration_arg('skip')
57015a4a 2550 get_dash = (
2551 (not is_live or self._configuration_arg('include_live_dash'))
2552 and 'dash' not in skip_manifests and self.get_param('youtube_include_dash_manifest', True))
5d3a0e79 2553 get_hls = 'hls' not in skip_manifests and self.get_param('youtube_include_hls_manifest', True)
2554
a0bb6ce5 2555 def process_manifest_format(f, proto, itag):
2556 if itag in itags:
2557 if itags[itag] == proto or f'{itag}-{proto}' in itags:
2558 return False
2559 itag = f'{itag}-{proto}'
2560 if itag:
2561 f['format_id'] = itag
2562 itags[itag] = proto
2563
2564 f['quality'] = next((
2565 q(qdict[val])
e339d25a 2566 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
a0bb6ce5 2567 if val in qdict), -1)
2568 return True
2a9c6dcd 2569
11f9be09 2570 for sd in streaming_data:
5d3a0e79 2571 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 2572 if hls_manifest_url:
2a9c6dcd 2573 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
a0bb6ce5 2574 if process_manifest_format(f, 'hls', self._search_regex(
2575 r'/itag/(\d+)', f['url'], 'itag', default=None)):
2576 yield f
545cc85d 2577
5d3a0e79 2578 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
2579 if dash_manifest_url:
2a9c6dcd 2580 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
a0bb6ce5 2581 if process_manifest_format(f, 'dash', f['format_id']):
2582 f['filesize'] = int_or_none(self._search_regex(
2583 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
2584 yield f
11f9be09 2585
2586 def _real_extract(self, url):
2587 url, smuggled_data = unsmuggle_url(url, {})
2588 video_id = self._match_id(url)
2589
2590 base_url = self.http_scheme() + '//www.youtube.com/'
2591 webpage_url = base_url + 'watch?v=' + video_id
b6de707d 2592 webpage = None
2593 if 'webpage' not in self._configuration_arg('player_skip'):
2594 webpage = self._download_webpage(
2595 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
11f9be09 2596
2597 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 2598
b6de707d 2599 player_responses, player_url = self._extract_player_responses(
11f9be09 2600 self._get_requested_clients(url, smuggled_data),
99e9e001 2601 video_id, webpage, master_ytcfg)
11f9be09 2602
352d63fd 2603 get_first = lambda obj, keys, **kwargs: traverse_obj(obj, (..., *variadic(keys)), **kwargs, get_all=False)
11f9be09 2604
2605 playability_statuses = traverse_obj(
2606 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
2607
2608 trailer_video_id = get_first(
2609 playability_statuses,
2610 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
2611 expected_type=str)
2612 if trailer_video_id:
2613 return self.url_result(
2614 trailer_video_id, self.ie_key(), trailer_video_id)
2615
2616 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
2617 if webpage else (lambda x: None))
2618
2619 video_details = traverse_obj(
2620 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
2621 microformats = traverse_obj(
2622 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
2623 expected_type=dict, default=[])
2624 video_title = (
2625 get_first(video_details, 'title')
2626 or self._get_text(microformats, (..., 'title'))
2627 or search_meta(['og:title', 'twitter:title', 'title']))
2628 video_description = get_first(video_details, 'shortDescription')
2629
d89257f3 2630 multifeed_metadata_list = get_first(
2631 player_responses,
2632 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
2633 expected_type=str)
2634 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
2635 if self.get_param('noplaylist'):
11f9be09 2636 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 2637 else:
2638 entries = []
2639 feed_ids = []
2640 for feed in multifeed_metadata_list.split(','):
2641 # Unquote should take place before split on comma (,) since textual
2642 # fields may contain comma as well (see
2643 # https://github.com/ytdl-org/youtube-dl/issues/8536)
2644 feed_data = compat_parse_qs(
2645 compat_urllib_parse_unquote_plus(feed))
2646
2647 def feed_entry(name):
2648 return try_get(
2649 feed_data, lambda x: x[name][0], compat_str)
2650
2651 feed_id = feed_entry('id')
2652 if not feed_id:
2653 continue
2654 feed_title = feed_entry('title')
2655 title = video_title
2656 if feed_title:
2657 title += ' (%s)' % feed_title
2658 entries.append({
2659 '_type': 'url_transparent',
2660 'ie_key': 'Youtube',
2661 'url': smuggle_url(
2662 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
2663 {'force_singlefeed': True}),
2664 'title': title,
2665 })
2666 feed_ids.append(feed_id)
2667 self.to_screen(
2668 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
2669 % (', '.join(feed_ids), video_id))
2670 return self.playlist_result(
2671 entries, video_id, video_title, video_description)
11f9be09 2672
7ea65411 2673 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
11f9be09 2674 is_live = get_first(video_details, 'isLive')
7ea65411 2675 if is_live is None:
2676 is_live = get_first(live_broadcast_details, 'isLiveNow')
11f9be09 2677
2678 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
2679 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live))
bf1317d2 2680
545cc85d 2681 if not formats:
11f9be09 2682 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 2683 self.report_drm(video_id)
11f9be09 2684 pemr = get_first(
2685 playability_statuses,
2686 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
2687 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
2688 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 2689 if subreason:
545cc85d 2690 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 2691 countries = get_first(microformats, 'availableCountries')
545cc85d 2692 if not countries:
2693 regions_allowed = search_meta('regionsAllowed')
2694 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 2695 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 2696 reason += f'. {subreason}'
545cc85d 2697 if reason:
b7da73eb 2698 self.raise_no_formats(reason, expected=True)
bf1317d2 2699
2a9c6dcd 2700 # Source is given priority since formats that throttle are given lower source_preference
2701 # When throttling issue is fully fixed, remove this
c18d4482 2702 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
bf1317d2 2703
11f9be09 2704 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 2705 if not keywords and webpage:
2706 keywords = [
2707 unescapeHTML(m.group('content'))
2708 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
2709 for keyword in keywords:
2710 if keyword.startswith('yt:stretch='):
201c1459 2711 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
2712 if mobj:
2713 # NB: float is intentional for forcing float division
2714 w, h = (float(v) for v in mobj.groups())
2715 if w > 0 and h > 0:
2716 ratio = w / h
2717 for f in formats:
2718 if f.get('vcodec') != 'none':
2719 f['stretched_ratio'] = ratio
2720 break
6449cd80 2721
545cc85d 2722 thumbnails = []
11f9be09 2723 thumbnail_dicts = traverse_obj(
2724 (video_details, microformats), (..., ..., 'thumbnail', 'thumbnails', ...),
2725 expected_type=dict, default=[])
2726 for thumbnail in thumbnail_dicts:
2727 thumbnail_url = thumbnail.get('url')
2728 if not thumbnail_url:
2729 continue
2730 # Sometimes youtube gives a wrong thumbnail URL. See:
2731 # https://github.com/yt-dlp/yt-dlp/issues/233
2732 # https://github.com/ytdl-org/youtube-dl/issues/28023
2733 if 'maxresdefault' in thumbnail_url:
2734 thumbnail_url = thumbnail_url.split('?')[0]
2735 thumbnails.append({
2736 'url': thumbnail_url,
2737 'height': int_or_none(thumbnail.get('height')),
2738 'width': int_or_none(thumbnail.get('width')),
2739 })
ff2751ac 2740 thumbnail_url = search_meta(['og:image', 'twitter:image'])
2741 if thumbnail_url:
2742 thumbnails.append({
2743 'url': thumbnail_url,
ff2751ac 2744 })
fccf5021 2745 original_thumbnails = thumbnails.copy()
2746
0ba692ac 2747 # The best resolution thumbnails sometimes does not appear in the webpage
2748 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 2749 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 2750 thumbnail_names = [
2751 'maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3',
cca80fe6 2752 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
2753 'mqdefault', 'mq1', 'mq2', 'mq3',
2754 'default', '1', '2', '3'
2755 ]
cca80fe6 2756 n_thumbnail_names = len(thumbnail_names)
0ba692ac 2757 thumbnails.extend({
2758 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
2759 video_id=video_id, name=name, ext=ext,
2760 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 2761 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 2762 for thumb in thumbnails:
cca80fe6 2763 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 2764 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 2765 self._remove_duplicate_formats(thumbnails)
fccf5021 2766 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 2767
7ea65411 2768 category = get_first(microformats, 'category') or search_meta('genre')
2769 channel_id = str_or_none(
2770 get_first(video_details, 'channelId')
2771 or get_first(microformats, 'externalChannelId')
2772 or search_meta('channelId'))
2773 duration = int_or_none(
2774 get_first(video_details, 'lengthSeconds')
2775 or get_first(microformats, 'lengthSeconds')
2776 or parse_duration(search_meta('duration'))) or None
2777 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
2778
2779 live_content = get_first(video_details, 'isLiveContent')
2780 is_upcoming = get_first(video_details, 'isUpcoming')
2781 if is_live is None:
2782 if is_upcoming or live_content is False:
2783 is_live = False
2784 if is_upcoming is None and (live_content or is_live):
2785 is_upcoming = False
2786 live_starttime = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
2787 live_endtime = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
2788 if not duration and live_endtime and live_starttime:
2789 duration = live_endtime - live_starttime
2790
545cc85d 2791 info = {
2792 'id': video_id,
2793 'title': self._live_title(video_title) if is_live else video_title,
2794 'formats': formats,
2795 'thumbnails': thumbnails,
fccf5021 2796 # The best thumbnail that we are sure exists. Prevents unnecessary
2797 # URL checking if user don't care about getting the best possible thumbnail
2798 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 2799 'description': video_description,
2800 'upload_date': unified_strdate(
11f9be09 2801 get_first(microformats, 'uploadDate')
545cc85d 2802 or search_meta('uploadDate')),
11f9be09 2803 'uploader': get_first(video_details, 'author'),
545cc85d 2804 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
2805 'uploader_url': owner_profile_url,
2806 'channel_id': channel_id,
11f9be09 2807 'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None,
545cc85d 2808 'duration': duration,
2809 'view_count': int_or_none(
11f9be09 2810 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 2811 or search_meta('interactionCount')),
11f9be09 2812 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 2813 'age_limit': 18 if (
11f9be09 2814 get_first(microformats, 'isFamilySafe') is False
545cc85d 2815 or search_meta('isFamilyFriendly') == 'false'
2816 or search_meta('og:restrictions:age') == '18+') else 0,
2817 'webpage_url': webpage_url,
2818 'categories': [category] if category else None,
2819 'tags': keywords,
11f9be09 2820 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 2821 'is_live': is_live,
2822 'was_live': (False if is_live or is_upcoming or live_content is False
2823 else None if is_live is None or is_upcoming is None
2824 else live_content),
2825 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
2826 'release_timestamp': live_starttime,
545cc85d 2827 }
b477fc13 2828
3944e7af 2829 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 2830 if pctr:
ecdc9049 2831 def get_lang_code(track):
2832 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
2833 or track.get('languageCode'))
2834
2835 # Converted into dicts to remove duplicates
2836 captions = {
2837 get_lang_code(sub): sub
2838 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
2839 translation_languages = {
2840 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
2841 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
2842
774d79cc 2843 def process_language(container, base_url, lang_code, sub_name, query):
120916da 2844 lang_subs = container.setdefault(lang_code, [])
545cc85d 2845 for fmt in self._SUBTITLE_FORMATS:
2846 query.update({
2847 'fmt': fmt,
2848 })
2849 lang_subs.append({
2850 'ext': fmt,
2851 'url': update_url_query(base_url, query),
774d79cc 2852 'name': sub_name,
545cc85d 2853 })
7e72694b 2854
ecdc9049 2855 subtitles, automatic_captions = {}, {}
2856 for lang_code, caption_track in captions.items():
2857 base_url = caption_track.get('baseUrl')
545cc85d 2858 if not base_url:
2859 continue
ecdc9049 2860 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 2861 if caption_track.get('kind') != 'asr':
545cc85d 2862 if not lang_code:
2863 continue
2864 process_language(
ecdc9049 2865 subtitles, base_url, lang_code, lang_name, {})
2866 if not caption_track.get('isTranslatable'):
2867 continue
3944e7af 2868 for trans_code, trans_name in translation_languages.items():
2869 if not trans_code:
545cc85d 2870 continue
ecdc9049 2871 if caption_track.get('kind') != 'asr':
2872 trans_code += f'-{lang_code}'
2873 trans_name += format_field(lang_name, template=' from %s')
545cc85d 2874 process_language(
ecdc9049 2875 automatic_captions, base_url, trans_code, trans_name, {'tlang': trans_code})
2876 info['automatic_captions'] = automatic_captions
2877 info['subtitles'] = subtitles
7e72694b 2878
545cc85d 2879 parsed_url = compat_urllib_parse_urlparse(url)
2880 for component in [parsed_url.fragment, parsed_url.query]:
2881 query = compat_parse_qs(component)
2882 for k, v in query.items():
2883 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
2884 d_k += '_time'
2885 if d_k not in info and k in s_ks:
2886 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
2887
2888 # Youtube Music Auto-generated description
822b9d9c 2889 if video_description:
38d70284 2890 mobj = re.search(r'(?s)(?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+(?P<album>[^\n]+)(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?(?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?(.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?.+\nAuto-generated by YouTube\.\s*$', video_description)
822b9d9c 2891 if mobj:
822b9d9c
RA
2892 release_year = mobj.group('release_year')
2893 release_date = mobj.group('release_date')
2894 if release_date:
2895 release_date = release_date.replace('-', '')
2896 if not release_year:
545cc85d 2897 release_year = release_date[:4]
2898 info.update({
2899 'album': mobj.group('album'.strip()),
2900 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
2901 'track': mobj.group('track').strip(),
2902 'release_date': release_date,
cc2db878 2903 'release_year': int_or_none(release_year),
545cc85d 2904 })
7e72694b 2905
545cc85d 2906 initial_data = None
2907 if webpage:
2908 initial_data = self._extract_yt_initial_variable(
2909 webpage, self._YT_INITIAL_DATA_RE, video_id,
2910 'yt initial data')
2911 if not initial_data:
99e9e001 2912 query = {'videoId': video_id}
2913 query.update(self._get_checkok_params())
109dd3b2 2914 initial_data = self._extract_response(
2915 item_id=video_id, ep='next', fatal=False,
99e9e001 2916 ytcfg=master_ytcfg, query=query,
2917 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 2918 note='Downloading initial data API JSON')
545cc85d 2919
c60ee3a2 2920 try:
2921 # This will error if there is no livechat
2922 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
ecdc9049 2923 info.setdefault('subtitles', {})['live_chat'] = [{
c60ee3a2 2924 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
2925 'video_id': video_id,
2926 'ext': 'json',
f6745c49 2927 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 2928 }]
2929 except (KeyError, IndexError, TypeError):
2930 pass
545cc85d 2931
2932 if initial_data:
7c365c21 2933 info['chapters'] = (
2934 self._extract_chapters_from_json(initial_data, duration)
2935 or self._extract_chapters_from_engagement_panel(initial_data, duration)
2936 or None)
545cc85d 2937
2938 contents = try_get(
2939 initial_data,
2940 lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'],
2941 list) or []
2942 for content in contents:
2943 vpir = content.get('videoPrimaryInfoRenderer')
2944 if vpir:
2945 stl = vpir.get('superTitleLink')
2946 if stl:
fe93e2c4 2947 stl = self._get_text(stl)
545cc85d 2948 if try_get(
2949 vpir,
2950 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
2951 info['location'] = stl
2952 else:
2953 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
2954 if mobj:
2955 info.update({
2956 'series': mobj.group(1),
2957 'season_number': int(mobj.group(2)),
2958 'episode_number': int(mobj.group(3)),
2959 })
2960 for tlb in (try_get(
2961 vpir,
2962 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
2963 list) or []):
2964 tbr = tlb.get('toggleButtonRenderer') or {}
2965 for getter, regex in [(
2966 lambda x: x['defaultText']['accessibility']['accessibilityData'],
2967 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
2968 lambda x: x['accessibility'],
2969 lambda x: x['accessibilityData']['accessibilityData'],
2970 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
2971 label = (try_get(tbr, getter, dict) or {}).get('label')
2972 if label:
2973 mobj = re.match(regex, label)
2974 if mobj:
2975 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
2976 break
2977 sbr_tooltip = try_get(
2978 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
2979 if sbr_tooltip:
2980 like_count, dislike_count = sbr_tooltip.split(' / ')
2981 info.update({
2982 'like_count': str_to_int(like_count),
2983 'dislike_count': str_to_int(dislike_count),
2984 })
2985 vsir = content.get('videoSecondaryInfoRenderer')
2986 if vsir:
052e1350 2987 info['channel'] = self._get_text(vsir, ('owner', 'videoOwnerRenderer', 'title'))
545cc85d 2988 rows = try_get(
2989 vsir,
2990 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
2991 list) or []
2992 multiple_songs = False
2993 for row in rows:
2994 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
2995 multiple_songs = True
2996 break
2997 for row in rows:
2998 mrr = row.get('metadataRowRenderer') or {}
2999 mrr_title = mrr.get('title')
3000 if not mrr_title:
3001 continue
052e1350 3002 mrr_title = self._get_text(mrr, 'title')
3003 mrr_contents_text = self._get_text(mrr, ('contents', 0))
545cc85d 3004 if mrr_title == 'License':
3005 info['license'] = mrr_contents_text
3006 elif not multiple_songs:
3007 if mrr_title == 'Album':
3008 info['album'] = mrr_contents_text
3009 elif mrr_title == 'Artist':
3010 info['artist'] = mrr_contents_text
3011 elif mrr_title == 'Song':
3012 info['track'] = mrr_contents_text
3013
3014 fallbacks = {
3015 'channel': 'uploader',
3016 'channel_id': 'uploader_id',
3017 'channel_url': 'uploader_url',
3018 }
3019 for to, frm in fallbacks.items():
3020 if not info.get(to):
3021 info[to] = info.get(frm)
3022
3023 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3024 v = info.get(s_k)
3025 if v:
3026 info[d_k] = v
b84071c0 3027
11f9be09 3028 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3029 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3030 is_membersonly = None
b28f8d24 3031 is_premium = None
c224251a
M
3032 if initial_data and is_private is not None:
3033 is_membersonly = False
b28f8d24 3034 is_premium = False
47193e02 3035 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3036 badge_labels = set()
3037 for content in contents:
3038 if not isinstance(content, dict):
3039 continue
3040 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3041 for badge_label in badge_labels:
3042 if badge_label.lower() == 'members only':
3043 is_membersonly = True
3044 elif badge_label.lower() == 'premium':
3045 is_premium = True
3046 elif badge_label.lower() == 'unlisted':
3047 is_unlisted = True
c224251a 3048
c224251a
M
3049 info['availability'] = self._availability(
3050 is_private=is_private,
b28f8d24 3051 needs_premium=is_premium,
c224251a
M
3052 needs_subscription=is_membersonly,
3053 needs_auth=info['age_limit'] >= 18,
3054 is_unlisted=None if is_private is None else is_unlisted)
3055
a2160aa4 3056 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3057
11f9be09 3058 self.mark_watched(video_id, player_responses)
d77ab8e2 3059
545cc85d 3060 return info
c5e8d7af 3061
5f6a1245 3062
8bdd16b4 3063class YoutubeTabIE(YoutubeBaseInfoExtractor):
96565c7e 3064 IE_DESC = 'YouTube Tabs'
70d5c17b 3065 _VALID_URL = r'''(?x)
3066 https?://
3067 (?:\w+\.)?
3068 (?:
3069 youtube(?:kids)?\.com|
d9190e44 3070 %(invidious)s
70d5c17b 3071 )/
3072 (?:
fe03a6cd 3073 (?P<channel_type>channel|c|user|browse)/|
70d5c17b 3074 (?P<not_channel>
9ba5705a 3075 feed/|hashtag/|
70d5c17b 3076 (?:playlist|watch)\?.*?\blist=
3077 )|
d9190e44 3078 (?!(?:%(reserved_names)s)\b) # Direct URLs
70d5c17b 3079 )
3080 (?P<id>[^/?\#&]+)
d9190e44
RH
3081 ''' % {
3082 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
3083 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
3084 }
8bdd16b4 3085 IE_NAME = 'youtube:tab'
3086
81127aa5 3087 _TESTS = [{
da692b79 3088 'note': 'playlists, multipage',
8bdd16b4 3089 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
3090 'playlist_mincount': 94,
3091 'info_dict': {
3092 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
3093 'title': 'Игорь Клейнер - Playlists',
3094 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
deaec5af 3095 'uploader': 'Игорь Клейнер',
3096 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
8bdd16b4 3097 },
3098 }, {
da692b79 3099 'note': 'playlists, multipage, different order',
8bdd16b4 3100 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
3101 'playlist_mincount': 94,
3102 'info_dict': {
3103 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
3104 'title': 'Игорь Клейнер - Playlists',
3105 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
deaec5af 3106 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
3107 'uploader': 'Игорь Клейнер',
8bdd16b4 3108 },
201c1459 3109 }, {
da692b79 3110 'note': 'playlists, series',
201c1459 3111 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
3112 'playlist_mincount': 5,
3113 'info_dict': {
3114 'id': 'UCYO_jab_esuFRV4b17AJtAw',
3115 'title': '3Blue1Brown - Playlists',
3116 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
da692b79 3117 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
3118 'uploader': '3Blue1Brown',
201c1459 3119 },
8bdd16b4 3120 }, {
da692b79 3121 'note': 'playlists, singlepage',
8bdd16b4 3122 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
3123 'playlist_mincount': 4,
3124 'info_dict': {
3125 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
3126 'title': 'ThirstForScience - Playlists',
3127 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
deaec5af 3128 'uploader': 'ThirstForScience',
3129 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
8bdd16b4 3130 }
3131 }, {
3132 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
3133 'only_matching': True,
3134 }, {
da692b79 3135 'note': 'basic, single video playlist',
0e30a7b9 3136 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
81127aa5 3137 'info_dict': {
0e30a7b9 3138 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
3139 'uploader': 'Sergey M.',
3140 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
3867038a 3141 'title': 'youtube-dl public playlist',
81127aa5 3142 },
0e30a7b9 3143 'playlist_count': 1,
9291475f 3144 }, {
da692b79 3145 'note': 'empty playlist',
0e30a7b9 3146 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
9291475f 3147 'info_dict': {
0e30a7b9 3148 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
3149 'uploader': 'Sergey M.',
3150 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
3867038a 3151 'title': 'youtube-dl empty playlist',
9291475f
PH
3152 },
3153 'playlist_count': 0,
3154 }, {
da692b79 3155 'note': 'Home tab',
8bdd16b4 3156 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
9291475f 3157 'info_dict': {
8bdd16b4 3158 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3159 'title': 'lex will - Home',
3160 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
deaec5af 3161 'uploader': 'lex will',
3162 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
9291475f 3163 },
8bdd16b4 3164 'playlist_mincount': 2,
9291475f 3165 }, {
da692b79 3166 'note': 'Videos tab',
8bdd16b4 3167 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
9291475f 3168 'info_dict': {
8bdd16b4 3169 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3170 'title': 'lex will - Videos',
3171 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
deaec5af 3172 'uploader': 'lex will',
3173 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
9291475f 3174 },
8bdd16b4 3175 'playlist_mincount': 975,
9291475f 3176 }, {
da692b79 3177 'note': 'Videos tab, sorted by popular',
8bdd16b4 3178 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
9291475f 3179 'info_dict': {
8bdd16b4 3180 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3181 'title': 'lex will - Videos',
3182 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
deaec5af 3183 'uploader': 'lex will',
3184 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
9291475f 3185 },
8bdd16b4 3186 'playlist_mincount': 199,
9291475f 3187 }, {
da692b79 3188 'note': 'Playlists tab',
8bdd16b4 3189 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
9291475f 3190 'info_dict': {
8bdd16b4 3191 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3192 'title': 'lex will - Playlists',
3193 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
deaec5af 3194 'uploader': 'lex will',
3195 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
9291475f 3196 },
8bdd16b4 3197 'playlist_mincount': 17,
ac7553d0 3198 }, {
da692b79 3199 'note': 'Community tab',
8bdd16b4 3200 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
ac7553d0 3201 'info_dict': {
8bdd16b4 3202 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3203 'title': 'lex will - Community',
3204 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
deaec5af 3205 'uploader': 'lex will',
3206 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
8bdd16b4 3207 },
3208 'playlist_mincount': 18,
87dadd45 3209 }, {
da692b79 3210 'note': 'Channels tab',
8bdd16b4 3211 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
87dadd45 3212 'info_dict': {
8bdd16b4 3213 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3214 'title': 'lex will - Channels',
3215 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
deaec5af 3216 'uploader': 'lex will',
3217 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
8bdd16b4 3218 },
deaec5af 3219 'playlist_mincount': 12,
cd684175 3220 }, {
3221 'note': 'Search tab',
3222 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
3223 'playlist_mincount': 40,
3224 'info_dict': {
3225 'id': 'UCYO_jab_esuFRV4b17AJtAw',
3226 'title': '3Blue1Brown - Search - linear algebra',
3227 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
3228 'uploader': '3Blue1Brown',
3229 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
3230 },
6b08cdf6 3231 }, {
a0566bbf 3232 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
8bdd16b4 3233 'only_matching': True,
3234 }, {
a0566bbf 3235 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
8bdd16b4 3236 'only_matching': True,
3237 }, {
a0566bbf 3238 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
8bdd16b4 3239 'only_matching': True,
3240 }, {
3241 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
3242 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
3243 'info_dict': {
3244 'title': '29C3: Not my department',
3245 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
3246 'uploader': 'Christiaan008',
3247 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
deaec5af 3248 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
8bdd16b4 3249 },
3250 'playlist_count': 96,
3251 }, {
3252 'note': 'Large playlist',
3253 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
6b08cdf6 3254 'info_dict': {
8bdd16b4 3255 'title': 'Uploads from Cauchemar',
3256 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
3257 'uploader': 'Cauchemar',
3258 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
13a75688 3259 },
8bdd16b4 3260 'playlist_mincount': 1123,
3261 }, {
da692b79 3262 'note': 'even larger playlist, 8832 videos',
8bdd16b4 3263 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
3264 'only_matching': True,
4b7df0d3
JMF
3265 }, {
3266 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
3267 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
3268 'info_dict': {
acf757f4
PH
3269 'title': 'Uploads from Interstellar Movie',
3270 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
13a75688 3271 'uploader': 'Interstellar Movie',
8bdd16b4 3272 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4b7df0d3 3273 },
481cc733 3274 'playlist_mincount': 21,
358de58c 3275 }, {
3276 'note': 'Playlist with "show unavailable videos" button',
3277 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
3278 'info_dict': {
3279 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
3280 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
3281 'uploader': 'Phim Siêu Nhân Nhật Bản',
3282 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
3283 },
da692b79 3284 'playlist_mincount': 200,
5d342002 3285 }, {
da692b79 3286 'note': 'Playlist with unavailable videos in page 7',
5d342002 3287 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
3288 'info_dict': {
3289 'title': 'Uploads from BlankTV',
3290 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
3291 'uploader': 'BlankTV',
3292 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
3293 },
da692b79 3294 'playlist_mincount': 1000,
8bdd16b4 3295 }, {
da692b79 3296 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
8bdd16b4 3297 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
3298 'info_dict': {
3299 'title': 'Data Analysis with Dr Mike Pound',
3300 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
3301 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
3302 'uploader': 'Computerphile',
deaec5af 3303 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
8bdd16b4 3304 },
3305 'playlist_mincount': 11,
3306 }, {
a0566bbf 3307 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
8bdd16b4 3308 'only_matching': True,
dacb3a86 3309 }, {
da692b79 3310 'note': 'Playlist URL that does not actually serve a playlist',
dacb3a86
S
3311 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
3312 'info_dict': {
3313 'id': 'FqZTN594JQw',
3314 'ext': 'webm',
3315 'title': "Smiley's People 01 detective, Adventure Series, Action",
3316 'uploader': 'STREEM',
3317 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
ec85ded8 3318 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
dacb3a86
S
3319 'upload_date': '20150526',
3320 'license': 'Standard YouTube License',
3321 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
3322 'categories': ['People & Blogs'],
3323 'tags': list,
dbdaaa23 3324 'view_count': int,
dacb3a86
S
3325 'like_count': int,
3326 'dislike_count': int,
3327 },
3328 'params': {
3329 'skip_download': True,
3330 },
13a75688 3331 'skip': 'This video is not available.',
dacb3a86 3332 'add_ie': [YoutubeIE.ie_key()],
481cc733 3333 }, {
8bdd16b4 3334 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
c0345b82 3335 'only_matching': True,
66b48727 3336 }, {
8bdd16b4 3337 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
66b48727 3338 'only_matching': True,
a0566bbf 3339 }, {
3340 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
3341 'info_dict': {
57015a4a 3342 'id': '3yImotZU3tw', # This will keep changing
a0566bbf 3343 'ext': 'mp4',
deaec5af 3344 'title': compat_str,
a0566bbf 3345 'uploader': 'Sky News',
3346 'uploader_id': 'skynews',
3347 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
da692b79 3348 'upload_date': r're:\d{8}',
3349 'description': compat_str,
a0566bbf 3350 'categories': ['News & Politics'],
3351 'tags': list,
3352 'like_count': int,
3353 'dislike_count': int,
3354 },
3355 'params': {
3356 'skip_download': True,
3357 },
da692b79 3358 'expected_warnings': ['Downloading just video ', 'Ignoring subtitle tracks found in '],
a0566bbf 3359 }, {
3360 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
3361 'info_dict': {
3362 'id': 'a48o2S1cPoo',
3363 'ext': 'mp4',
3364 'title': 'The Young Turks - Live Main Show',
3365 'uploader': 'The Young Turks',
3366 'uploader_id': 'TheYoungTurks',
3367 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
3368 'upload_date': '20150715',
3369 'license': 'Standard YouTube License',
3370 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
3371 'categories': ['News & Politics'],
3372 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
3373 'like_count': int,
3374 'dislike_count': int,
3375 },
3376 'params': {
3377 'skip_download': True,
3378 },
3379 'only_matching': True,
3380 }, {
3381 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
3382 'only_matching': True,
3383 }, {
3384 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
3385 'only_matching': True,
09f1580e 3386 }, {
3387 'note': 'A channel that is not live. Should raise error',
3388 'url': 'https://www.youtube.com/user/numberphile/live',
3389 'only_matching': True,
3d3dddc9 3390 }, {
3391 'url': 'https://www.youtube.com/feed/trending',
3392 'only_matching': True,
3393 }, {
3d3dddc9 3394 'url': 'https://www.youtube.com/feed/library',
3395 'only_matching': True,
3396 }, {
3d3dddc9 3397 'url': 'https://www.youtube.com/feed/history',
3398 'only_matching': True,
3399 }, {
3d3dddc9 3400 'url': 'https://www.youtube.com/feed/subscriptions',
3401 'only_matching': True,
3402 }, {
3d3dddc9 3403 'url': 'https://www.youtube.com/feed/watch_later',
3404 'only_matching': True,
3405 }, {
ac56cf38 3406 'note': 'Recommended - redirects to home page.',
3d3dddc9 3407 'url': 'https://www.youtube.com/feed/recommended',
3408 'only_matching': True,
29f7c58a 3409 }, {
da692b79 3410 'note': 'inline playlist with not always working continuations',
29f7c58a 3411 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
3412 'only_matching': True,
3413 }, {
3414 'url': 'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8',
3415 'only_matching': True,
3416 }, {
3417 'url': 'https://www.youtube.com/course',
3418 'only_matching': True,
3419 }, {
3420 'url': 'https://www.youtube.com/zsecurity',
3421 'only_matching': True,
3422 }, {
3423 'url': 'http://www.youtube.com/NASAgovVideo/videos',
3424 'only_matching': True,
3425 }, {
3426 'url': 'https://www.youtube.com/TheYoungTurks/live',
3427 'only_matching': True,
39ed931e 3428 }, {
3429 'url': 'https://www.youtube.com/hashtag/cctv9',
3430 'info_dict': {
3431 'id': 'cctv9',
3432 'title': '#cctv9',
3433 },
3434 'playlist_mincount': 350,
201c1459 3435 }, {
3436 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
3437 'only_matching': True,
9297939e 3438 }, {
da692b79 3439 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
9297939e 3440 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
3441 'only_matching': True
fe03a6cd 3442 }, {
3443 'note': '/browse/ should redirect to /channel/',
3444 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
3445 'only_matching': True
3446 }, {
3447 'note': 'VLPL, should redirect to playlist?list=PL...',
3448 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
3449 'info_dict': {
3450 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
3451 'uploader': 'NoCopyrightSounds',
3452 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
3453 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
3454 'title': 'NCS Releases',
3455 },
3456 'playlist_mincount': 166,
18db7548 3457 }, {
3458 'note': 'Topic, should redirect to playlist?list=UU...',
3459 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
3460 'info_dict': {
3461 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
3462 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
3463 'title': 'Uploads from Royalty Free Music - Topic',
3464 'uploader': 'Royalty Free Music - Topic',
3465 },
3466 'expected_warnings': [
3467 'A channel/user page was given',
3468 'The URL does not have a videos tab',
3469 ],
3470 'playlist_mincount': 101,
3471 }, {
3472 'note': 'Topic without a UU playlist',
3473 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
3474 'info_dict': {
3475 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
3476 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
3477 },
3478 'expected_warnings': [
3479 'A channel/user page was given',
3480 'The URL does not have a videos tab',
3481 'Falling back to channel URL',
3482 ],
3483 'playlist_mincount': 9,
abcdd12b 3484 }, {
3485 'note': 'Youtube music Album',
3486 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
3487 'info_dict': {
3488 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
3489 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
3490 },
3491 'playlist_count': 50,
47193e02 3492 }, {
3493 'note': 'unlisted single video playlist',
3494 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
3495 'info_dict': {
3496 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
3497 'uploader': 'colethedj',
3498 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
3499 'title': 'yt-dlp unlisted playlist test',
3500 'availability': 'unlisted'
3501 },
3502 'playlist_count': 1,
ac56cf38 3503 }, {
3504 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
3505 'url': 'https://www.youtube.com/feed/recommended',
3506 'info_dict': {
3507 'id': 'recommended',
3508 'title': 'recommended',
3509 },
3510 'playlist_mincount': 50,
3511 'params': {
3512 'skip_download': True,
3513 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
3514 },
3515 }, {
3516 'note': 'API Fallback: /videos tab, sorted by oldest first',
3517 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
3518 'info_dict': {
3519 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
3520 'title': 'Cody\'sLab - Videos',
3521 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
3522 'uploader': 'Cody\'sLab',
3523 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
3524 },
3525 'playlist_mincount': 650,
3526 'params': {
3527 'skip_download': True,
3528 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
3529 },
3530 }, {
3531 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
3532 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
3533 'info_dict': {
3534 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
3535 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
3536 'title': 'Uploads from Royalty Free Music - Topic',
3537 'uploader': 'Royalty Free Music - Topic',
3538 },
3539 'expected_warnings': [
3540 'A channel/user page was given',
3541 'The URL does not have a videos tab',
3542 ],
3543 'playlist_mincount': 101,
3544 'params': {
3545 'skip_download': True,
3546 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
3547 },
29f7c58a 3548 }]
3549
3550 @classmethod
3551 def suitable(cls, url):
3552 return False if YoutubeIE.suitable(url) else super(
3553 YoutubeTabIE, cls).suitable(url)
8bdd16b4 3554
3555 def _extract_channel_id(self, webpage):
3556 channel_id = self._html_search_meta(
3557 'channelId', webpage, 'channel id', default=None)
3558 if channel_id:
3559 return channel_id
3560 channel_url = self._html_search_meta(
3561 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3562 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3563 'twitter:app:url:googleplay'), webpage, 'channel url')
3564 return self._search_regex(
3565 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3566 channel_url, 'channel id')
15f6397c 3567
8bdd16b4 3568 @staticmethod
cd7c66cf 3569 def _extract_basic_item_renderer(item):
3570 # Modified from _extract_grid_item_renderer
201c1459 3571 known_basic_renderers = (
3572 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
cd7c66cf 3573 )
3574 for key, renderer in item.items():
201c1459 3575 if not isinstance(renderer, dict):
cd7c66cf 3576 continue
201c1459 3577 elif key in known_basic_renderers:
3578 return renderer
3579 elif key.startswith('grid') and key.endswith('Renderer'):
3580 return renderer
8bdd16b4 3581
8bdd16b4 3582 def _grid_entries(self, grid_renderer):
3583 for item in grid_renderer['items']:
3584 if not isinstance(item, dict):
39b62db1 3585 continue
cd7c66cf 3586 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3587 if not isinstance(renderer, dict):
3588 continue
052e1350 3589 title = self._get_text(renderer, 'title')
fe93e2c4 3590
8bdd16b4 3591 # playlist
3592 playlist_id = renderer.get('playlistId')
3593 if playlist_id:
3594 yield self.url_result(
3595 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3596 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3597 video_title=title)
201c1459 3598 continue
8bdd16b4 3599 # video
3600 video_id = renderer.get('videoId')
3601 if video_id:
3602 yield self._extract_video(renderer)
201c1459 3603 continue
8bdd16b4 3604 # channel
3605 channel_id = renderer.get('channelId')
3606 if channel_id:
8bdd16b4 3607 yield self.url_result(
3608 'https://www.youtube.com/channel/%s' % channel_id,
3609 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3610 continue
3611 # generic endpoint URL support
3612 ep_url = urljoin('https://www.youtube.com/', try_get(
3613 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3614 compat_str))
3615 if ep_url:
3616 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3617 if ie.suitable(ep_url):
3618 yield self.url_result(
3619 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3620 break
8bdd16b4 3621
3d3dddc9 3622 def _shelf_entries_from_content(self, shelf_renderer):
3623 content = shelf_renderer.get('content')
3624 if not isinstance(content, dict):
8bdd16b4 3625 return
cd7c66cf 3626 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 3627 if renderer:
3628 # TODO: add support for nested playlists so each shelf is processed
3629 # as separate playlist
3630 # TODO: this includes only first N items
3631 for entry in self._grid_entries(renderer):
3632 yield entry
3633 renderer = content.get('horizontalListRenderer')
3634 if renderer:
3635 # TODO
3636 pass
8bdd16b4 3637
29f7c58a 3638 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 3639 ep = try_get(
3640 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3641 compat_str)
3642 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 3643 if shelf_url:
29f7c58a 3644 # Skipping links to another channels, note that checking for
3645 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3646 # will not work
3647 if skip_channels and '/channels?' in shelf_url:
3648 return
052e1350 3649 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 3650 yield self.url_result(shelf_url, video_title=title)
3651 # Shelf may not contain shelf URL, fallback to extraction from content
3652 for entry in self._shelf_entries_from_content(shelf_renderer):
3653 yield entry
c5e8d7af 3654
8bdd16b4 3655 def _playlist_entries(self, video_list_renderer):
3656 for content in video_list_renderer['contents']:
3657 if not isinstance(content, dict):
3658 continue
3659 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3660 if not isinstance(renderer, dict):
3661 continue
3662 video_id = renderer.get('videoId')
3663 if not video_id:
3664 continue
3665 yield self._extract_video(renderer)
07aeced6 3666
3462ffa8 3667 def _rich_entries(self, rich_grid_renderer):
3668 renderer = try_get(
70d5c17b 3669 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 3670 video_id = renderer.get('videoId')
3671 if not video_id:
3672 return
3673 yield self._extract_video(renderer)
3674
8bdd16b4 3675 def _video_entry(self, video_renderer):
3676 video_id = video_renderer.get('videoId')
3677 if video_id:
3678 return self._extract_video(video_renderer)
dacb3a86 3679
8bdd16b4 3680 def _post_thread_entries(self, post_thread_renderer):
3681 post_renderer = try_get(
3682 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3683 if not post_renderer:
3684 return
3685 # video attachment
3686 video_renderer = try_get(
895b0931 3687 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3688 video_id = video_renderer.get('videoId')
3689 if video_id:
3690 entry = self._extract_video(video_renderer)
8bdd16b4 3691 if entry:
3692 yield entry
895b0931 3693 # playlist attachment
3694 playlist_id = try_get(
3695 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3696 if playlist_id:
3697 yield self.url_result(
e28f1c0a 3698 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3699 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 3700 # inline video links
3701 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3702 for run in runs:
3703 if not isinstance(run, dict):
3704 continue
3705 ep_url = try_get(
3706 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3707 if not ep_url:
3708 continue
3709 if not YoutubeIE.suitable(ep_url):
3710 continue
3711 ep_video_id = YoutubeIE._match_id(ep_url)
3712 if video_id == ep_video_id:
3713 continue
895b0931 3714 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 3715
8bdd16b4 3716 def _post_thread_continuation_entries(self, post_thread_continuation):
3717 contents = post_thread_continuation.get('contents')
3718 if not isinstance(contents, list):
3719 return
3720 for content in contents:
3721 renderer = content.get('backstagePostThreadRenderer')
3722 if not isinstance(renderer, dict):
3723 continue
3724 for entry in self._post_thread_entries(renderer):
3725 yield entry
07aeced6 3726
39ed931e 3727 r''' # unused
3728 def _rich_grid_entries(self, contents):
3729 for content in contents:
3730 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
3731 if video_renderer:
3732 entry = self._video_entry(video_renderer)
3733 if entry:
3734 yield entry
3735 '''
ac56cf38 3736 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
3462ffa8 3737
70d5c17b 3738 def extract_entries(parent_renderer): # this needs to called again for continuation to work with feeds
3739 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3740 for content in contents:
3741 if not isinstance(content, dict):
8bdd16b4 3742 continue
70d5c17b 3743 is_renderer = try_get(content, lambda x: x['itemSectionRenderer'], dict)
3462ffa8 3744 if not is_renderer:
70d5c17b 3745 renderer = content.get('richItemRenderer')
3462ffa8 3746 if renderer:
3747 for entry in self._rich_entries(renderer):
3748 yield entry
3749 continuation_list[0] = self._extract_continuation(parent_renderer)
8bdd16b4 3750 continue
3462ffa8 3751 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3752 for isr_content in isr_contents:
3753 if not isinstance(isr_content, dict):
3754 continue
69184e41 3755
3756 known_renderers = {
3757 'playlistVideoListRenderer': self._playlist_entries,
3758 'gridRenderer': self._grid_entries,
3759 'shelfRenderer': lambda x: self._shelf_entries(x, tab.get('title') != 'Channels'),
3760 'backstagePostThreadRenderer': self._post_thread_entries,
3761 'videoRenderer': lambda x: [self._video_entry(x)],
3762 }
3763 for key, renderer in isr_content.items():
3764 if key not in known_renderers:
3765 continue
3766 for entry in known_renderers[key](renderer):
3767 if entry:
3768 yield entry
3462ffa8 3769 continuation_list[0] = self._extract_continuation(renderer)
69184e41 3770 break
70d5c17b 3771
3462ffa8 3772 if not continuation_list[0]:
3773 continuation_list[0] = self._extract_continuation(is_renderer)
70d5c17b 3774
3775 if not continuation_list[0]:
3776 continuation_list[0] = self._extract_continuation(parent_renderer)
3462ffa8 3777
ac56cf38 3778 continuation_list = [None] # Python 2 does not support nonlocal
29f7c58a 3779 tab_content = try_get(tab, lambda x: x['content'], dict)
3780 if not tab_content:
3781 return
3462ffa8 3782 parent_renderer = (
29f7c58a 3783 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3784 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
70d5c17b 3785 for entry in extract_entries(parent_renderer):
3786 yield entry
3462ffa8 3787 continuation = continuation_list[0]
d069eca7 3788
8bdd16b4 3789 for page_num in itertools.count(1):
3790 if not continuation:
3791 break
99e9e001 3792 headers = self.generate_api_headers(
3793 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 3794 response = self._extract_response(
3795 item_id='%s page %s' % (item_id, page_num),
fe93e2c4 3796 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 3797 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
3798
3799 if not response:
8bdd16b4 3800 break
ac56cf38 3801 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
3802 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
3803 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 3804
69184e41 3805 known_continuation_renderers = {
3806 'playlistVideoListContinuation': self._playlist_entries,
3807 'gridContinuation': self._grid_entries,
3808 'itemSectionContinuation': self._post_thread_continuation_entries,
3809 'sectionListContinuation': extract_entries, # for feeds
3810 }
8bdd16b4 3811 continuation_contents = try_get(
69184e41 3812 response, lambda x: x['continuationContents'], dict) or {}
3813 continuation_renderer = None
3814 for key, value in continuation_contents.items():
3815 if key not in known_continuation_renderers:
3462ffa8 3816 continue
69184e41 3817 continuation_renderer = value
3818 continuation_list = [None]
3819 for entry in known_continuation_renderers[key](continuation_renderer):
3820 yield entry
3821 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
3822 break
3823 if continuation_renderer:
3824 continue
c5e8d7af 3825
a1b535bd 3826 known_renderers = {
3827 'gridPlaylistRenderer': (self._grid_entries, 'items'),
3828 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 3829 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 3830 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 3831 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 3832 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 3833 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 3834 }
cce889b9 3835 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 3836 continuation_items = try_get(
cce889b9 3837 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 3838 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
3839 video_items_renderer = None
3840 for key, value in continuation_item.items():
3841 if key not in known_renderers:
8bdd16b4 3842 continue
a1b535bd 3843 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 3844 continuation_list = [None]
a1b535bd 3845 for entry in known_renderers[key][0](video_items_renderer):
3846 yield entry
9ba5705a 3847 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 3848 break
3849 if video_items_renderer:
3850 continue
8bdd16b4 3851 break
9558dcec 3852
8bdd16b4 3853 @staticmethod
3854 def _extract_selected_tab(tabs):
3855 for tab in tabs:
cd684175 3856 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
3857 if renderer.get('selected') is True:
3858 return renderer
2b3c2546 3859 else:
8bdd16b4 3860 raise ExtractorError('Unable to find selected tab')
b82f815f 3861
47193e02 3862 @classmethod
3863 def _extract_uploader(cls, data):
8bdd16b4 3864 uploader = {}
47193e02 3865 renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
3866 owner = try_get(
3867 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
3868 if owner:
3869 uploader['uploader'] = owner.get('text')
3870 uploader['uploader_id'] = try_get(
3871 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
3872 uploader['uploader_url'] = urljoin(
3873 'https://www.youtube.com/',
3874 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
9c3fe2ef 3875 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 3876
ac56cf38 3877 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 3878 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 3879 thumbnails_list = []
3880 tags = []
b60419c5 3881
8bdd16b4 3882 selected_tab = self._extract_selected_tab(tabs)
3883 renderer = try_get(
3884 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
3885 if renderer:
b60419c5 3886 channel_name = renderer.get('title')
3887 channel_url = renderer.get('channelUrl')
3888 channel_id = renderer.get('externalId')
39ed931e 3889 else:
64c0d954 3890 renderer = try_get(
3891 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 3892
8bdd16b4 3893 if renderer:
3894 title = renderer.get('title')
ecc97af3 3895 description = renderer.get('description', '')
b60419c5 3896 playlist_id = channel_id
3897 tags = renderer.get('keywords', '').split()
3898 thumbnails_list = (
3899 try_get(renderer, lambda x: x['avatar']['thumbnails'], list)
ff84930c 3900 or try_get(
47193e02 3901 self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer'),
3902 lambda x: x['thumbnailRenderer']['playlistVideoThumbnailRenderer']['thumbnail']['thumbnails'],
ff84930c 3903 list)
b60419c5 3904 or [])
3905
3906 thumbnails = []
3907 for t in thumbnails_list:
3908 if not isinstance(t, dict):
3909 continue
3910 thumbnail_url = url_or_none(t.get('url'))
3911 if not thumbnail_url:
3912 continue
3913 thumbnails.append({
3914 'url': thumbnail_url,
3915 'width': int_or_none(t.get('width')),
3916 'height': int_or_none(t.get('height')),
3917 })
3462ffa8 3918 if playlist_id is None:
70d5c17b 3919 playlist_id = item_id
3920 if title is None:
39ed931e 3921 title = (
3922 try_get(data, lambda x: x['header']['hashtagHeaderRenderer']['hashtag']['simpleText'])
3923 or playlist_id)
b60419c5 3924 title += format_field(selected_tab, 'title', ' - %s')
cd684175 3925 title += format_field(selected_tab, 'expandedText', ' - %s')
b60419c5 3926 metadata = {
3927 'playlist_id': playlist_id,
3928 'playlist_title': title,
3929 'playlist_description': description,
3930 'uploader': channel_name,
3931 'uploader_id': channel_id,
3932 'uploader_url': channel_url,
3933 'thumbnails': thumbnails,
3934 'tags': tags,
3935 }
47193e02 3936 availability = self._extract_availability(data)
3937 if availability:
3938 metadata['availability'] = availability
b60419c5 3939 if not channel_id:
3940 metadata.update(self._extract_uploader(data))
3941 metadata.update({
3942 'channel': metadata['uploader'],
3943 'channel_id': metadata['uploader_id'],
3944 'channel_url': metadata['uploader_url']})
3945 return self.playlist_result(
d069eca7 3946 self._entries(
ac56cf38 3947 selected_tab, playlist_id, ytcfg,
3948 self._extract_account_syncid(ytcfg, data),
3949 self._extract_visitor_data(data, ytcfg)),
b60419c5 3950 **metadata)
73c4ac2c 3951
ac56cf38 3952 def _extract_mix_playlist(self, playlist, playlist_id, data, ytcfg):
3953 first_id = last_id = response = None
2be71994 3954 for page_num in itertools.count(1):
cd7c66cf 3955 videos = list(self._playlist_entries(playlist))
3956 if not videos:
3957 return
2be71994 3958 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
3959 if start >= len(videos):
3960 return
3961 for video in videos[start:]:
3962 if video['id'] == first_id:
3963 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
3964 return
3965 yield video
3966 first_id = first_id or videos[0]['id']
3967 last_id = videos[-1]['id']
79360d99 3968 watch_endpoint = try_get(
3969 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 3970 headers = self.generate_api_headers(
3971 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
3972 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 3973 query = {
3974 'playlistId': playlist_id,
3975 'videoId': watch_endpoint.get('videoId') or last_id,
3976 'index': watch_endpoint.get('index') or len(videos),
3977 'params': watch_endpoint.get('params') or 'OAE%3D'
3978 }
3979 response = self._extract_response(
3980 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 3981 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 3982 check_get_keys='contents'
3983 )
cd7c66cf 3984 playlist = try_get(
79360d99 3985 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 3986
ac56cf38 3987 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 3988 title = playlist.get('title') or try_get(
3989 data, lambda x: x['titleText']['simpleText'], compat_str)
3990 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 3991
3992 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 3993 playlist_url = urljoin(url, try_get(
3994 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3995 compat_str))
3996 if playlist_url and playlist_url != url:
3997 return self.url_result(
3998 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3999 video_title=title)
cd7c66cf 4000
8bdd16b4 4001 return self.playlist_result(
ac56cf38 4002 self._extract_mix_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4003 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4004
47193e02 4005 def _extract_availability(self, data):
4006 """
4007 Gets the availability of a given playlist/tab.
4008 Note: Unless YouTube tells us explicitly, we do not assume it is public
4009 @param data: response
4010 """
4011 is_private = is_unlisted = None
4012 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4013 badge_labels = self._extract_badges(renderer)
4014
4015 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4016 privacy_dropdown_entries = try_get(
4017 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4018 for renderer_dict in privacy_dropdown_entries:
4019 is_selected = try_get(
4020 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4021 if not is_selected:
4022 continue
052e1350 4023 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4024 if label:
4025 badge_labels.add(label.lower())
4026 break
4027
4028 for badge_label in badge_labels:
4029 if badge_label == 'unlisted':
4030 is_unlisted = True
4031 elif badge_label == 'private':
4032 is_private = True
4033 elif badge_label == 'public':
4034 is_unlisted = is_private = False
4035 return self._availability(is_private, False, False, False, is_unlisted)
4036
4037 @staticmethod
4038 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4039 sidebar_renderer = try_get(
4040 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4041 for item in sidebar_renderer:
4042 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4043 if renderer:
4044 return renderer
4045
ac56cf38 4046 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4047 """
4048 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4049 """
5d342002 4050 browse_id = params = None
47193e02 4051 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4052 if not renderer:
4053 return
4054 menu_renderer = try_get(
4055 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4056 for menu_item in menu_renderer:
4057 if not isinstance(menu_item, dict):
358de58c 4058 continue
47193e02 4059 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4060 text = try_get(
4061 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4062 if not text or text.lower() != 'show unavailable videos':
4063 continue
4064 browse_endpoint = try_get(
4065 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4066 browse_id = browse_endpoint.get('browseId')
4067 params = browse_endpoint.get('params')
4068 break
5d342002 4069
11f9be09 4070 headers = self.generate_api_headers(
99e9e001 4071 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4072 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4073 query = {
4074 'params': params or 'wgYCCAA=',
4075 'browseId': browse_id or 'VL%s' % item_id
4076 }
4077 return self._extract_response(
4078 item_id=item_id, headers=headers, query=query,
fe93e2c4 4079 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4080 note='Downloading API JSON with unavailable videos')
358de58c 4081
ac56cf38 4082 def _extract_webpage(self, url, item_id, fatal=True):
a06916d9 4083 retries = self.get_param('extractor_retries', 3)
62bff2c1 4084 count = -1
ac56cf38 4085 webpage = data = last_error = None
14fdfea9 4086 while count < retries:
62bff2c1 4087 count += 1
14fdfea9 4088 # Sometimes youtube returns a webpage with incomplete ytInitialData
62bff2c1 4089 # See: https://github.com/yt-dlp/yt-dlp/issues/116
ac56cf38 4090 if last_error:
c705177d 4091 self.report_warning('%s. Retrying ...' % last_error)
ac56cf38 4092 try:
4093 webpage = self._download_webpage(
4094 url, item_id,
4095 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4096 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4097 except ExtractorError as e:
4098 if isinstance(e.cause, network_exceptions):
4099 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4100 last_error = error_to_compat_str(e.cause or e.msg)
4101 if count < retries:
4102 continue
4103 if fatal:
4104 raise
4105 self.report_warning(error_to_compat_str(e))
14fdfea9 4106 break
ac56cf38 4107 else:
4108 try:
4109 self._extract_and_report_alerts(data)
4110 except ExtractorError as e:
4111 if fatal:
4112 raise
4113 self.report_warning(error_to_compat_str(e))
4114 break
4115
4116 if dict_get(data, ('contents', 'currentVideoEndpoint')):
4117 break
4118
4119 last_error = 'Incomplete yt initial data received'
4120 if count >= retries:
4121 if fatal:
4122 raise ExtractorError(last_error)
4123 self.report_warning(last_error)
4124 break
4125
cd7c66cf 4126 return webpage, data
4127
ac56cf38 4128 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4129 data = None
4130 if 'webpage' not in self._configuration_arg('skip'):
4131 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4132 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
4133 if not data:
4134 if not ytcfg and self.is_authenticated:
4135 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download.'
4136 if 'authcheck' not in self._configuration_arg('skip') and fatal:
4137 raise ExtractorError(
4138 msg + ' If you are not downloading private content, or your cookies are only for the first account and channel,'
4139 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4140 expected=True)
4141 self.report_warning(msg, only_once=True)
4142 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4143 return data, ytcfg
4144
4145 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4146 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4147 resolve_response = self._extract_response(
4148 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4149 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4150 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4151 for ep_key, ep in endpoints.items():
4152 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4153 if params:
4154 return self._extract_response(
4155 item_id=item_id, query=params, ep=ep, headers=headers,
4156 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
4157 check_get_keys=('contents', 'currentVideoEndpoint'))
4158 err_note = 'Failed to resolve url (does the playlist exist?)'
4159 if fatal:
4160 raise ExtractorError(err_note, expected=True)
4161 self.report_warning(err_note, item_id)
4162
9297939e 4163 @staticmethod
4164 def _smuggle_data(entries, data):
4165 for entry in entries:
4166 if data:
4167 entry['url'] = smuggle_url(entry['url'], data)
4168 yield entry
4169
cd7c66cf 4170 def _real_extract(self, url):
9297939e 4171 url, smuggled_data = unsmuggle_url(url, {})
4172 if self.is_music_url(url):
4173 smuggled_data['is_music_url'] = True
fe03a6cd 4174 info_dict = self.__real_extract(url, smuggled_data)
9297939e 4175 if info_dict.get('entries'):
4176 info_dict['entries'] = self._smuggle_data(info_dict['entries'], smuggled_data)
4177 return info_dict
4178
fe03a6cd 4179 _url_re = re.compile(r'(?P<pre>%s)(?(channel_type)(?P<tab>/\w+))?(?P<post>.*)$' % _VALID_URL)
4180
4181 def __real_extract(self, url, smuggled_data):
cd7c66cf 4182 item_id = self._match_id(url)
4183 url = compat_urlparse.urlunparse(
4184 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 4185 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 4186
fe03a6cd 4187 def get_mobj(url):
4188 mobj = self._url_re.match(url).groupdict()
07cce701 4189 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 4190 return mobj
4191
4192 mobj = get_mobj(url)
4193 # Youtube returns incomplete data if tabname is not lower case
4194 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 4195 if is_channel:
4196 if smuggled_data.get('is_music_url'):
4197 if item_id[:2] == 'VL':
4198 # Youtube music VL channels have an equivalent playlist
4199 item_id = item_id[2:]
4200 pre, tab, post, is_channel = 'https://www.youtube.com/playlist?list=%s' % item_id, '', '', False
abcdd12b 4201 elif item_id[:2] == 'MP':
ac56cf38 4202 # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
4203 mdata = self._extract_tab_endpoint(
4204 'https://music.youtube.com/channel/%s' % item_id, item_id, default_client='web_music')
4205 murl = traverse_obj(
4206 mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'), get_all=False, expected_type=compat_str)
4207 if not murl:
4208 raise ExtractorError('Failed to resolve album to playlist.')
4209 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
fe03a6cd 4210 elif mobj['channel_type'] == 'browse':
4211 # Youtube music /browse/ should be changed to /channel/
4212 pre = 'https://www.youtube.com/channel/%s' % item_id
4213 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
4214 # Home URLs should redirect to /videos/
6a39ee13 4215 self.report_warning(
cd7c66cf 4216 'A channel/user page was given. All the channel\'s videos will be downloaded. '
4217 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 4218 tab = '/videos'
4219
4220 url = ''.join((pre, tab, post))
4221 mobj = get_mobj(url)
cd7c66cf 4222
4223 # Handle both video/playlist URLs
201c1459 4224 qs = parse_qs(url)
cd7c66cf 4225 video_id = qs.get('v', [None])[0]
4226 playlist_id = qs.get('list', [None])[0]
4227
fe03a6cd 4228 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 4229 if not playlist_id:
fe03a6cd 4230 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 4231 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 4232 # Common mistake: https://www.youtube.com/watch?list=playlist_id
6a39ee13 4233 self.report_warning('A video URL was given without video ID. Trying to download playlist %s' % playlist_id)
cd7c66cf 4234 url = 'https://www.youtube.com/playlist?list=%s' % playlist_id
18db7548 4235 mobj = get_mobj(url)
cd7c66cf 4236
4237 if video_id and playlist_id:
a06916d9 4238 if self.get_param('noplaylist'):
cd7c66cf 4239 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
5e3f2f8f 4240 return self.url_result(f'https://www.youtube.com/watch?v={video_id}', ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 4241 self.to_screen('Downloading playlist %s; add --no-playlist to just download video %s' % (playlist_id, video_id))
4242
ac56cf38 4243 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 4244
18db7548 4245 tabs = try_get(
4246 data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
4247 if tabs:
4248 selected_tab = self._extract_selected_tab(tabs)
4249 tab_name = selected_tab.get('title', '')
09f1580e 4250 if 'no-youtube-channel-redirect' not in compat_opts:
4251 if mobj['tab'] == '/live':
4252 # Live tab should have redirected to the video
4253 raise ExtractorError('The channel is not currently live', expected=True)
4254 if mobj['tab'] == '/videos' and tab_name.lower() != mobj['tab'][1:]:
4255 if not mobj['not_channel'] and item_id[:2] == 'UC':
4256 # Topic channels don't have /videos. Use the equivalent playlist instead
4257 self.report_warning('The URL does not have a %s tab. Trying to redirect to playlist UU%s instead' % (mobj['tab'][1:], item_id[2:]))
4258 pl_id = 'UU%s' % item_id[2:]
4259 pl_url = 'https://www.youtube.com/playlist?list=%s%s' % (pl_id, mobj['post'])
4260 try:
ac56cf38 4261 data, ytcfg, item_id, url = *self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True), pl_id, pl_url
09f1580e 4262 except ExtractorError:
4263 self.report_warning('The playlist gave error. Falling back to channel URL')
4264 else:
4265 self.report_warning('The URL does not have a %s tab. %s is being downloaded instead' % (mobj['tab'][1:], tab_name))
18db7548 4266
4267 self.write_debug('Final URL: %s' % url)
4268
358de58c 4269 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 4270 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 4271 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 4272 self._extract_and_report_alerts(data, only_once=True)
8bdd16b4 4273 tabs = try_get(
4274 data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
4275 if tabs:
ac56cf38 4276 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 4277
8bdd16b4 4278 playlist = try_get(
4279 data, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4280 if playlist:
ac56cf38 4281 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 4282
a0566bbf 4283 video_id = try_get(
4284 data, lambda x: x['currentVideoEndpoint']['watchEndpoint']['videoId'],
4285 compat_str) or video_id
8bdd16b4 4286 if video_id:
09f1580e 4287 if mobj['tab'] != '/live': # live tab is expected to redirect to video
4288 self.report_warning('Unable to recognize playlist. Downloading just video %s' % video_id)
5e3f2f8f 4289 return self.url_result(f'https://www.youtube.com/watch?v={video_id}', ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 4290
8bdd16b4 4291 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 4292
c5e8d7af 4293
8bdd16b4 4294class YoutubePlaylistIE(InfoExtractor):
96565c7e 4295 IE_DESC = 'YouTube playlists'
8bdd16b4 4296 _VALID_URL = r'''(?x)(?:
4297 (?:https?://)?
4298 (?:\w+\.)?
4299 (?:
4300 (?:
4301 youtube(?:kids)?\.com|
d9190e44 4302 %(invidious)s
8bdd16b4 4303 )
4304 /.*?\?.*?\blist=
4305 )?
4306 (?P<id>%(playlist_id)s)
d9190e44
RH
4307 )''' % {
4308 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
4309 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4310 }
8bdd16b4 4311 IE_NAME = 'youtube:playlist'
cdc628a4 4312 _TESTS = [{
8bdd16b4 4313 'note': 'issue #673',
4314 'url': 'PLBB231211A4F62143',
cdc628a4 4315 'info_dict': {
8bdd16b4 4316 'title': '[OLD]Team Fortress 2 (Class-based LP)',
4317 'id': 'PLBB231211A4F62143',
4318 'uploader': 'Wickydoo',
4319 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 4320 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
8bdd16b4 4321 },
4322 'playlist_mincount': 29,
4323 }, {
4324 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
4325 'info_dict': {
4326 'title': 'YDL_safe_search',
4327 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
4328 },
4329 'playlist_count': 2,
4330 'skip': 'This playlist is private',
9558dcec 4331 }, {
8bdd16b4 4332 'note': 'embedded',
4333 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
4334 'playlist_count': 4,
9558dcec 4335 'info_dict': {
8bdd16b4 4336 'title': 'JODA15',
4337 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
4338 'uploader': 'milan',
4339 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
9558dcec 4340 }
cdc628a4 4341 }, {
8bdd16b4 4342 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
11f9be09 4343 'playlist_mincount': 654,
8bdd16b4 4344 'info_dict': {
4345 'title': '2018 Chinese New Singles (11/6 updated)',
4346 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
4347 'uploader': 'LBK',
4348 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 4349 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
8bdd16b4 4350 }
daa0df9e 4351 }, {
29f7c58a 4352 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
4353 'only_matching': True,
4354 }, {
4355 # music album playlist
4356 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
4357 'only_matching': True,
4358 }]
4359
4360 @classmethod
4361 def suitable(cls, url):
201c1459 4362 if YoutubeTabIE.suitable(url):
4363 return False
49a57e70 4364 from ..utils import parse_qs
201c1459 4365 qs = parse_qs(url)
4366 if qs.get('v', [None])[0]:
4367 return False
4368 return super(YoutubePlaylistIE, cls).suitable(url)
29f7c58a 4369
4370 def _real_extract(self, url):
4371 playlist_id = self._match_id(url)
46953e7e 4372 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 4373 url = update_url_query(
4374 'https://www.youtube.com/playlist',
4375 parse_qs(url) or {'list': playlist_id})
4376 if is_music_url:
4377 url = smuggle_url(url, {'is_music_url': True})
4378 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 4379
4380
4381class YoutubeYtBeIE(InfoExtractor):
c76eb41b 4382 IE_DESC = 'youtu.be'
29f7c58a 4383 _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}
4384 _TESTS = [{
8bdd16b4 4385 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
4386 'info_dict': {
4387 'id': 'yeWKywCrFtk',
4388 'ext': 'mp4',
4389 'title': 'Small Scale Baler and Braiding Rugs',
4390 'uploader': 'Backus-Page House Museum',
4391 'uploader_id': 'backuspagemuseum',
4392 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
4393 'upload_date': '20161008',
4394 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
4395 'categories': ['Nonprofits & Activism'],
4396 'tags': list,
4397 'like_count': int,
4398 'dislike_count': int,
4399 },
4400 'params': {
4401 'noplaylist': True,
4402 'skip_download': True,
4403 },
39e7107d 4404 }, {
8bdd16b4 4405 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 4406 'only_matching': True,
cdc628a4
PH
4407 }]
4408
8bdd16b4 4409 def _real_extract(self, url):
5ad28e7f 4410 mobj = self._match_valid_url(url)
29f7c58a 4411 video_id = mobj.group('id')
4412 playlist_id = mobj.group('playlist_id')
8bdd16b4 4413 return self.url_result(
29f7c58a 4414 update_url_query('https://www.youtube.com/watch', {
4415 'v': video_id,
4416 'list': playlist_id,
4417 'feature': 'youtu.be',
4418 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4419
4420
4421class YoutubeYtUserIE(InfoExtractor):
96565c7e 4422 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
8bdd16b4 4423 _VALID_URL = r'ytuser:(?P<id>.+)'
4424 _TESTS = [{
4425 'url': 'ytuser:phihag',
4426 'only_matching': True,
4427 }]
4428
4429 def _real_extract(self, url):
4430 user_id = self._match_id(url)
4431 return self.url_result(
c586f9e8 4432 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 4433 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 4434
b05654f0 4435
3d3dddc9 4436class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 4437 IE_NAME = 'youtube:favorites'
96565c7e 4438 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 4439 _VALID_URL = r':ytfav(?:ou?rite)?s?'
4440 _LOGIN_REQUIRED = True
4441 _TESTS = [{
4442 'url': ':ytfav',
4443 'only_matching': True,
4444 }, {
4445 'url': ':ytfavorites',
4446 'only_matching': True,
4447 }]
4448
4449 def _real_extract(self, url):
4450 return self.url_result(
4451 'https://www.youtube.com/playlist?list=LL',
4452 ie=YoutubeTabIE.ie_key())
4453
4454
79360d99 4455class YoutubeSearchIE(SearchInfoExtractor, YoutubeTabIE):
96565c7e 4456 IE_DESC = 'YouTube searches'
78caa52a 4457 IE_NAME = 'youtube:search'
b05654f0 4458 _SEARCH_KEY = 'ytsearch'
6c894ea1 4459 _SEARCH_PARAMS = None
9dd8e46a 4460 _TESTS = []
b05654f0 4461
cc16383f 4462 def _search_results(self, query):
a5c56234 4463 data = {'query': query}
6c894ea1
U
4464 if self._SEARCH_PARAMS:
4465 data['params'] = self._SEARCH_PARAMS
fe93e2c4 4466 continuation = {}
6c894ea1 4467 for page_num in itertools.count(1):
fe93e2c4 4468 data.update(continuation)
79360d99 4469 search = self._extract_response(
4470 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
4471 check_get_keys=('contents', 'onResponseReceivedCommands')
4472 )
6c894ea1 4473 if not search:
b4c08069 4474 break
6c894ea1
U
4475 slr_contents = try_get(
4476 search,
4477 (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'],
4478 lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']),
4479 list)
4480 if not slr_contents:
a22b2fd1 4481 break
0366ae87 4482
0366ae87
M
4483 # Youtube sometimes adds promoted content to searches,
4484 # changing the index location of videos and token.
4485 # So we search through all entries till we find them.
fe93e2c4 4486 continuation = None
30a074c2 4487 for slr_content in slr_contents:
fe93e2c4 4488 if not continuation:
4489 continuation = self._extract_continuation({'contents': [slr_content]})
a96c6d15 4490
30a074c2 4491 isr_contents = try_get(
4492 slr_content,
4493 lambda x: x['itemSectionRenderer']['contents'],
4494 list)
9da76d30 4495 if not isr_contents:
30a074c2 4496 continue
4497 for content in isr_contents:
4498 if not isinstance(content, dict):
4499 continue
4500 video = content.get('videoRenderer')
4501 if not isinstance(video, dict):
4502 continue
4503 video_id = video.get('videoId')
4504 if not video_id:
4505 continue
4506
4507 yield self._extract_video(video)
0366ae87 4508
fe93e2c4 4509 if not continuation:
6c894ea1 4510 break
b05654f0 4511
c9ae7b95 4512
a3dd9248 4513class YoutubeSearchDateIE(YoutubeSearchIE):
cb7fb546 4514 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 4515 _SEARCH_KEY = 'ytsearchdate'
96565c7e 4516 IE_DESC = 'YouTube searches, newest videos first'
6c894ea1 4517 _SEARCH_PARAMS = 'CAI%3D'
75dff0ee 4518
c9ae7b95 4519
386e1dd9 4520class YoutubeSearchURLIE(YoutubeSearchIE):
96565c7e 4521 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 4522 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
96565c7e 4523 _SEARCH_KEY = None
386e1dd9 4524 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)'
ef2f3c7f 4525 # _MAX_RESULTS = 100
3462ffa8 4526 _TESTS = [{
4527 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
4528 'playlist_mincount': 5,
4529 'info_dict': {
11f9be09 4530 'id': 'youtube-dl test video',
3462ffa8 4531 'title': 'youtube-dl test video',
4532 }
4533 }, {
4534 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
4535 'only_matching': True,
4536 }]
4537
386e1dd9 4538 @classmethod
4539 def _make_valid_url(cls):
4540 return cls._VALID_URL
4541
3462ffa8 4542 def _real_extract(self, url):
4dfbf869 4543 qs = parse_qs(url)
386e1dd9 4544 query = (qs.get('search_query') or qs.get('q'))[0]
4545 self._SEARCH_PARAMS = qs.get('sp', ('',))[0]
4546 return self._get_n_results(query, self._MAX_RESULTS)
3462ffa8 4547
4548
4549class YoutubeFeedsInfoExtractor(YoutubeTabIE):
d7ae0639 4550 """
25f14e9f 4551 Base class for feed extractors
3d3dddc9 4552 Subclasses must define the _FEED_NAME property.
d7ae0639 4553 """
b2e8bc1b 4554 _LOGIN_REQUIRED = True
ef2f3c7f 4555 _TESTS = []
d7ae0639
JMF
4556
4557 @property
4558 def IE_NAME(self):
78caa52a 4559 return 'youtube:%s' % self._FEED_NAME
04cc9617 4560
3853309f 4561 def _real_extract(self, url):
3d3dddc9 4562 return self.url_result(
4563 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
4564 ie=YoutubeTabIE.ie_key())
25f14e9f
S
4565
4566
ef2f3c7f 4567class YoutubeWatchLaterIE(InfoExtractor):
4568 IE_NAME = 'youtube:watchlater'
96565c7e 4569 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 4570 _VALID_URL = r':ytwatchlater'
bc7a9cd8 4571 _TESTS = [{
8bdd16b4 4572 'url': ':ytwatchlater',
bc7a9cd8
S
4573 'only_matching': True,
4574 }]
25f14e9f
S
4575
4576 def _real_extract(self, url):
ef2f3c7f 4577 return self.url_result(
4578 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 4579
4580
25f14e9f 4581class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 4582 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 4583 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 4584 _FEED_NAME = 'recommended'
45db527f 4585 _LOGIN_REQUIRED = False
3d3dddc9 4586 _TESTS = [{
4587 'url': ':ytrec',
4588 'only_matching': True,
4589 }, {
4590 'url': ':ytrecommended',
4591 'only_matching': True,
4592 }, {
4593 'url': 'https://youtube.com',
4594 'only_matching': True,
4595 }]
1ed5b5c9 4596
1ed5b5c9 4597
25f14e9f 4598class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 4599 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 4600 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 4601 _FEED_NAME = 'subscriptions'
3d3dddc9 4602 _TESTS = [{
4603 'url': ':ytsubs',
4604 'only_matching': True,
4605 }, {
4606 'url': ':ytsubscriptions',
4607 'only_matching': True,
4608 }]
1ed5b5c9 4609
1ed5b5c9 4610
25f14e9f 4611class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 4612 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 4613 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 4614 _FEED_NAME = 'history'
3d3dddc9 4615 _TESTS = [{
4616 'url': ':ythistory',
4617 'only_matching': True,
4618 }]
1ed5b5c9
JMF
4619
4620
15870e90
PH
4621class YoutubeTruncatedURLIE(InfoExtractor):
4622 IE_NAME = 'youtube:truncated_url'
4623 IE_DESC = False # Do not list
975d35db 4624 _VALID_URL = r'''(?x)
b95aab84
PH
4625 (?:https?://)?
4626 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
4627 (?:watch\?(?:
c4808c60 4628 feature=[a-z_]+|
b95aab84
PH
4629 annotation_id=annotation_[^&]+|
4630 x-yt-cl=[0-9]+|
c1708b89 4631 hl=[^&]*|
287be8c6 4632 t=[0-9]+
b95aab84
PH
4633 )?
4634 |
4635 attribution_link\?a=[^&]+
4636 )
4637 $
975d35db 4638 '''
15870e90 4639
c4808c60 4640 _TESTS = [{
2d3d2997 4641 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 4642 'only_matching': True,
dc2fc736 4643 }, {
2d3d2997 4644 'url': 'https://www.youtube.com/watch?',
dc2fc736 4645 'only_matching': True,
b95aab84
PH
4646 }, {
4647 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
4648 'only_matching': True,
4649 }, {
4650 'url': 'https://www.youtube.com/watch?feature=foo',
4651 'only_matching': True,
c1708b89
PH
4652 }, {
4653 'url': 'https://www.youtube.com/watch?hl=en-GB',
4654 'only_matching': True,
287be8c6
PH
4655 }, {
4656 'url': 'https://www.youtube.com/watch?t=2372',
4657 'only_matching': True,
c4808c60
PH
4658 }]
4659
15870e90
PH
4660 def _real_extract(self, url):
4661 raise ExtractorError(
78caa52a
PH
4662 'Did you forget to quote the URL? Remember that & is a meta '
4663 'character in most shells, so you want to put the URL in quotes, '
3867038a 4664 'like youtube-dl '
2d3d2997 4665 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 4666 ' or simply youtube-dl BaW_jenozKc .',
15870e90 4667 expected=True)
772fd5cc
PH
4668
4669
3cd786db 4670class YoutubeClipIE(InfoExtractor):
4671 IE_NAME = 'youtube:clip'
4672 IE_DESC = False # Do not list
4673 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/'
4674
4675 def _real_extract(self, url):
4676 self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead')
4677 return self.url_result(url, 'Generic')
4678
4679
772fd5cc
PH
4680class YoutubeTruncatedIDIE(InfoExtractor):
4681 IE_NAME = 'youtube:truncated_id'
4682 IE_DESC = False # Do not list
b95aab84 4683 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
4684
4685 _TESTS = [{
4686 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
4687 'only_matching': True,
4688 }]
4689
4690 def _real_extract(self, url):
4691 video_id = self._match_id(url)
4692 raise ExtractorError(
4693 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
4694 expected=True)