]>
Commit | Line | Data |
---|---|---|
1 | # coding: utf-8 | |
2 | ||
3 | from __future__ import unicode_literals | |
4 | ||
5 | import base64 | |
6 | import calendar | |
7 | import copy | |
8 | import datetime | |
9 | import hashlib | |
10 | import itertools | |
11 | import json | |
12 | import os.path | |
13 | import random | |
14 | import re | |
15 | import time | |
16 | import traceback | |
17 | ||
18 | from .common import InfoExtractor, SearchInfoExtractor | |
19 | from ..compat import ( | |
20 | compat_chr, | |
21 | compat_HTTPError, | |
22 | compat_parse_qs, | |
23 | compat_str, | |
24 | compat_urllib_parse_unquote_plus, | |
25 | compat_urllib_parse_urlencode, | |
26 | compat_urllib_parse_urlparse, | |
27 | compat_urlparse, | |
28 | ) | |
29 | from ..jsinterp import JSInterpreter | |
30 | from ..utils import ( | |
31 | bytes_to_intlist, | |
32 | clean_html, | |
33 | datetime_from_str, | |
34 | dict_get, | |
35 | error_to_compat_str, | |
36 | ExtractorError, | |
37 | float_or_none, | |
38 | format_field, | |
39 | int_or_none, | |
40 | intlist_to_bytes, | |
41 | is_html, | |
42 | mimetype2ext, | |
43 | network_exceptions, | |
44 | orderedSet, | |
45 | parse_codecs, | |
46 | parse_count, | |
47 | parse_duration, | |
48 | parse_iso8601, | |
49 | parse_qs, | |
50 | qualities, | |
51 | remove_end, | |
52 | remove_start, | |
53 | smuggle_url, | |
54 | str_or_none, | |
55 | str_to_int, | |
56 | traverse_obj, | |
57 | try_get, | |
58 | unescapeHTML, | |
59 | unified_strdate, | |
60 | unsmuggle_url, | |
61 | update_url_query, | |
62 | url_or_none, | |
63 | urljoin, | |
64 | variadic, | |
65 | ) | |
66 | ||
67 | ||
68 | # any clients starting with _ cannot be explicity requested by the user | |
69 | INNERTUBE_CLIENTS = { | |
70 | 'web': { | |
71 | 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', | |
72 | 'INNERTUBE_CONTEXT': { | |
73 | 'client': { | |
74 | 'clientName': 'WEB', | |
75 | 'clientVersion': '2.20210622.10.00', | |
76 | } | |
77 | }, | |
78 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 1 | |
79 | }, | |
80 | 'web_embedded': { | |
81 | 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', | |
82 | 'INNERTUBE_CONTEXT': { | |
83 | 'client': { | |
84 | 'clientName': 'WEB_EMBEDDED_PLAYER', | |
85 | 'clientVersion': '1.20210620.0.1', | |
86 | }, | |
87 | }, | |
88 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 56 | |
89 | }, | |
90 | 'web_music': { | |
91 | 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30', | |
92 | 'INNERTUBE_HOST': 'music.youtube.com', | |
93 | 'INNERTUBE_CONTEXT': { | |
94 | 'client': { | |
95 | 'clientName': 'WEB_REMIX', | |
96 | 'clientVersion': '1.20210621.00.00', | |
97 | } | |
98 | }, | |
99 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 67, | |
100 | }, | |
101 | 'web_creator': { | |
102 | 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', | |
103 | 'INNERTUBE_CONTEXT': { | |
104 | 'client': { | |
105 | 'clientName': 'WEB_CREATOR', | |
106 | 'clientVersion': '1.20210621.00.00', | |
107 | } | |
108 | }, | |
109 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 62, | |
110 | }, | |
111 | 'android': { | |
112 | 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', | |
113 | 'INNERTUBE_CONTEXT': { | |
114 | 'client': { | |
115 | 'clientName': 'ANDROID', | |
116 | 'clientVersion': '16.20', | |
117 | } | |
118 | }, | |
119 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 3, | |
120 | 'REQUIRE_JS_PLAYER': False | |
121 | }, | |
122 | 'android_embedded': { | |
123 | 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', | |
124 | 'INNERTUBE_CONTEXT': { | |
125 | 'client': { | |
126 | 'clientName': 'ANDROID_EMBEDDED_PLAYER', | |
127 | 'clientVersion': '16.20', | |
128 | }, | |
129 | }, | |
130 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 55, | |
131 | 'REQUIRE_JS_PLAYER': False | |
132 | }, | |
133 | 'android_music': { | |
134 | 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30', | |
135 | 'INNERTUBE_HOST': 'music.youtube.com', | |
136 | 'INNERTUBE_CONTEXT': { | |
137 | 'client': { | |
138 | 'clientName': 'ANDROID_MUSIC', | |
139 | 'clientVersion': '4.32', | |
140 | } | |
141 | }, | |
142 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 21, | |
143 | 'REQUIRE_JS_PLAYER': False | |
144 | }, | |
145 | 'android_creator': { | |
146 | 'INNERTUBE_CONTEXT': { | |
147 | 'client': { | |
148 | 'clientName': 'ANDROID_CREATOR', | |
149 | 'clientVersion': '21.24.100', | |
150 | }, | |
151 | }, | |
152 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 14, | |
153 | 'REQUIRE_JS_PLAYER': False | |
154 | }, | |
155 | # ios has HLS live streams | |
156 | # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680 | |
157 | 'ios': { | |
158 | 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', | |
159 | 'INNERTUBE_CONTEXT': { | |
160 | 'client': { | |
161 | 'clientName': 'IOS', | |
162 | 'clientVersion': '16.20', | |
163 | } | |
164 | }, | |
165 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 5, | |
166 | 'REQUIRE_JS_PLAYER': False | |
167 | }, | |
168 | 'ios_embedded': { | |
169 | 'INNERTUBE_API_KEY': 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8', | |
170 | 'INNERTUBE_CONTEXT': { | |
171 | 'client': { | |
172 | 'clientName': 'IOS_MESSAGES_EXTENSION', | |
173 | 'clientVersion': '16.20', | |
174 | }, | |
175 | }, | |
176 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 66, | |
177 | 'REQUIRE_JS_PLAYER': False | |
178 | }, | |
179 | 'ios_music': { | |
180 | 'INNERTUBE_API_KEY': 'AIzaSyDK3iBpDP9nHVTk2qL73FLJICfOC3c51Og', | |
181 | 'INNERTUBE_HOST': 'music.youtube.com', | |
182 | 'INNERTUBE_CONTEXT': { | |
183 | 'client': { | |
184 | 'clientName': 'IOS_MUSIC', | |
185 | 'clientVersion': '4.32', | |
186 | }, | |
187 | }, | |
188 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 26, | |
189 | 'REQUIRE_JS_PLAYER': False | |
190 | }, | |
191 | 'ios_creator': { | |
192 | 'INNERTUBE_CONTEXT': { | |
193 | 'client': { | |
194 | 'clientName': 'IOS_CREATOR', | |
195 | 'clientVersion': '21.24.100', | |
196 | }, | |
197 | }, | |
198 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 15, | |
199 | 'REQUIRE_JS_PLAYER': False | |
200 | }, | |
201 | # mweb has 'ultralow' formats | |
202 | # See: https://github.com/yt-dlp/yt-dlp/pull/557 | |
203 | 'mweb': { | |
204 | 'INNERTUBE_API_KEY': 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8', | |
205 | 'INNERTUBE_CONTEXT': { | |
206 | 'client': { | |
207 | 'clientName': 'MWEB', | |
208 | 'clientVersion': '2.20210721.07.00', | |
209 | } | |
210 | }, | |
211 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 2 | |
212 | }, | |
213 | } | |
214 | ||
215 | ||
216 | def build_innertube_clients(): | |
217 | third_party = { | |
218 | 'embedUrl': 'https://google.com', # Can be any valid URL | |
219 | } | |
220 | base_clients = ('android', 'web', 'ios', 'mweb') | |
221 | priority = qualities(base_clients[::-1]) | |
222 | ||
223 | for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()): | |
224 | ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8') | |
225 | ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com') | |
226 | ytcfg.setdefault('REQUIRE_JS_PLAYER', True) | |
227 | ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en') | |
228 | ytcfg['priority'] = 10 * priority(client.split('_', 1)[0]) | |
229 | ||
230 | if client in base_clients: | |
231 | INNERTUBE_CLIENTS[f'{client}_agegate'] = agegate_ytcfg = copy.deepcopy(ytcfg) | |
232 | agegate_ytcfg['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED' | |
233 | agegate_ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = third_party | |
234 | agegate_ytcfg['priority'] -= 1 | |
235 | elif client.endswith('_embedded'): | |
236 | ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = third_party | |
237 | ytcfg['priority'] -= 2 | |
238 | else: | |
239 | ytcfg['priority'] -= 3 | |
240 | ||
241 | ||
242 | build_innertube_clients() | |
243 | ||
244 | ||
245 | class YoutubeBaseInfoExtractor(InfoExtractor): | |
246 | """Provide base functions for Youtube extractors""" | |
247 | ||
248 | _RESERVED_NAMES = ( | |
249 | r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|' | |
250 | r'shorts|movies|results|shared|hashtag|trending|feed|feeds|' | |
251 | r'browse|oembed|get_video_info|iframe_api|s/player|' | |
252 | r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout') | |
253 | ||
254 | _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)' | |
255 | ||
256 | _NETRC_MACHINE = 'youtube' | |
257 | ||
258 | # If True it will raise an error if no login info is provided | |
259 | _LOGIN_REQUIRED = False | |
260 | ||
261 | r''' # Unused since login is broken | |
262 | _LOGIN_URL = 'https://accounts.google.com/ServiceLogin' | |
263 | _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge' | |
264 | ||
265 | _LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup' | |
266 | _CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge' | |
267 | _TFA_URL = 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}' | |
268 | ''' | |
269 | ||
270 | def _login(self): | |
271 | """ | |
272 | Attempt to log in to YouTube. | |
273 | True is returned if successful or skipped. | |
274 | False is returned if login failed. | |
275 | ||
276 | If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised. | |
277 | """ | |
278 | ||
279 | def warn(message): | |
280 | self.report_warning(message) | |
281 | ||
282 | # username+password login is broken | |
283 | if (self._LOGIN_REQUIRED | |
284 | and self.get_param('cookiefile') is None | |
285 | and self.get_param('cookiesfrombrowser') is None): | |
286 | self.raise_login_required( | |
287 | 'Login details are needed to download this content', method='cookies') | |
288 | username, password = self._get_login_info() | |
289 | if username: | |
290 | warn('Logging in using username and password is broken. %s' % self._LOGIN_HINTS['cookies']) | |
291 | return | |
292 | ||
293 | # Everything below this is broken! | |
294 | r''' | |
295 | # No authentication to be performed | |
296 | if username is None: | |
297 | if self._LOGIN_REQUIRED and self.get_param('cookiefile') is None: | |
298 | raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) | |
299 | # if self.get_param('cookiefile'): # TODO remove 'and False' later - too many people using outdated cookies and open issues, remind them. | |
300 | # self.to_screen('[Cookies] Reminder - Make sure to always use up to date cookies!') | |
301 | return True | |
302 | ||
303 | login_page = self._download_webpage( | |
304 | self._LOGIN_URL, None, | |
305 | note='Downloading login page', | |
306 | errnote='unable to fetch login page', fatal=False) | |
307 | if login_page is False: | |
308 | return | |
309 | ||
310 | login_form = self._hidden_inputs(login_page) | |
311 | ||
312 | def req(url, f_req, note, errnote): | |
313 | data = login_form.copy() | |
314 | data.update({ | |
315 | 'pstMsg': 1, | |
316 | 'checkConnection': 'youtube', | |
317 | 'checkedDomains': 'youtube', | |
318 | 'hl': 'en', | |
319 | 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]', | |
320 | 'f.req': json.dumps(f_req), | |
321 | 'flowName': 'GlifWebSignIn', | |
322 | 'flowEntry': 'ServiceLogin', | |
323 | # TODO: reverse actual botguard identifier generation algo | |
324 | 'bgRequest': '["identifier",""]', | |
325 | }) | |
326 | return self._download_json( | |
327 | url, None, note=note, errnote=errnote, | |
328 | transform_source=lambda s: re.sub(r'^[^[]*', '', s), | |
329 | fatal=False, | |
330 | data=urlencode_postdata(data), headers={ | |
331 | 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8', | |
332 | 'Google-Accounts-XSRF': 1, | |
333 | }) | |
334 | ||
335 | lookup_req = [ | |
336 | username, | |
337 | None, [], None, 'US', None, None, 2, False, True, | |
338 | [ | |
339 | None, None, | |
340 | [2, 1, None, 1, | |
341 | 'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn', | |
342 | None, [], 4], | |
343 | 1, [None, None, []], None, None, None, True | |
344 | ], | |
345 | username, | |
346 | ] | |
347 | ||
348 | lookup_results = req( | |
349 | self._LOOKUP_URL, lookup_req, | |
350 | 'Looking up account info', 'Unable to look up account info') | |
351 | ||
352 | if lookup_results is False: | |
353 | return False | |
354 | ||
355 | user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str) | |
356 | if not user_hash: | |
357 | warn('Unable to extract user hash') | |
358 | return False | |
359 | ||
360 | challenge_req = [ | |
361 | user_hash, | |
362 | None, 1, None, [1, None, None, None, [password, None, True]], | |
363 | [ | |
364 | None, None, [2, 1, None, 1, 'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn', None, [], 4], | |
365 | 1, [None, None, []], None, None, None, True | |
366 | ]] | |
367 | ||
368 | challenge_results = req( | |
369 | self._CHALLENGE_URL, challenge_req, | |
370 | 'Logging in', 'Unable to log in') | |
371 | ||
372 | if challenge_results is False: | |
373 | return | |
374 | ||
375 | login_res = try_get(challenge_results, lambda x: x[0][5], list) | |
376 | if login_res: | |
377 | login_msg = try_get(login_res, lambda x: x[5], compat_str) | |
378 | warn( | |
379 | 'Unable to login: %s' % 'Invalid password' | |
380 | if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg) | |
381 | return False | |
382 | ||
383 | res = try_get(challenge_results, lambda x: x[0][-1], list) | |
384 | if not res: | |
385 | warn('Unable to extract result entry') | |
386 | return False | |
387 | ||
388 | login_challenge = try_get(res, lambda x: x[0][0], list) | |
389 | if login_challenge: | |
390 | challenge_str = try_get(login_challenge, lambda x: x[2], compat_str) | |
391 | if challenge_str == 'TWO_STEP_VERIFICATION': | |
392 | # SEND_SUCCESS - TFA code has been successfully sent to phone | |
393 | # QUOTA_EXCEEDED - reached the limit of TFA codes | |
394 | status = try_get(login_challenge, lambda x: x[5], compat_str) | |
395 | if status == 'QUOTA_EXCEEDED': | |
396 | warn('Exceeded the limit of TFA codes, try later') | |
397 | return False | |
398 | ||
399 | tl = try_get(challenge_results, lambda x: x[1][2], compat_str) | |
400 | if not tl: | |
401 | warn('Unable to extract TL') | |
402 | return False | |
403 | ||
404 | tfa_code = self._get_tfa_info('2-step verification code') | |
405 | ||
406 | if not tfa_code: | |
407 | warn( | |
408 | 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>' | |
409 | '(Note that only TOTP (Google Authenticator App) codes work at this time.)') | |
410 | return False | |
411 | ||
412 | tfa_code = remove_start(tfa_code, 'G-') | |
413 | ||
414 | tfa_req = [ | |
415 | user_hash, None, 2, None, | |
416 | [ | |
417 | 9, None, None, None, None, None, None, None, | |
418 | [None, tfa_code, True, 2] | |
419 | ]] | |
420 | ||
421 | tfa_results = req( | |
422 | self._TFA_URL.format(tl), tfa_req, | |
423 | 'Submitting TFA code', 'Unable to submit TFA code') | |
424 | ||
425 | if tfa_results is False: | |
426 | return False | |
427 | ||
428 | tfa_res = try_get(tfa_results, lambda x: x[0][5], list) | |
429 | if tfa_res: | |
430 | tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str) | |
431 | warn( | |
432 | 'Unable to finish TFA: %s' % 'Invalid TFA code' | |
433 | if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg) | |
434 | return False | |
435 | ||
436 | check_cookie_url = try_get( | |
437 | tfa_results, lambda x: x[0][-1][2], compat_str) | |
438 | else: | |
439 | CHALLENGES = { | |
440 | 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.", | |
441 | 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.', | |
442 | 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.", | |
443 | } | |
444 | challenge = CHALLENGES.get( | |
445 | challenge_str, | |
446 | '%s returned error %s.' % (self.IE_NAME, challenge_str)) | |
447 | warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge) | |
448 | return False | |
449 | else: | |
450 | check_cookie_url = try_get(res, lambda x: x[2], compat_str) | |
451 | ||
452 | if not check_cookie_url: | |
453 | warn('Unable to extract CheckCookie URL') | |
454 | return False | |
455 | ||
456 | check_cookie_results = self._download_webpage( | |
457 | check_cookie_url, None, 'Checking cookie', fatal=False) | |
458 | ||
459 | if check_cookie_results is False: | |
460 | return False | |
461 | ||
462 | if 'https://myaccount.google.com/' not in check_cookie_results: | |
463 | warn('Unable to log in') | |
464 | return False | |
465 | ||
466 | return True | |
467 | ''' | |
468 | ||
469 | def _initialize_consent(self): | |
470 | cookies = self._get_cookies('https://www.youtube.com/') | |
471 | if cookies.get('__Secure-3PSID'): | |
472 | return | |
473 | consent_id = None | |
474 | consent = cookies.get('CONSENT') | |
475 | if consent: | |
476 | if 'YES' in consent.value: | |
477 | return | |
478 | consent_id = self._search_regex( | |
479 | r'PENDING\+(\d+)', consent.value, 'consent', default=None) | |
480 | if not consent_id: | |
481 | consent_id = random.randint(100, 999) | |
482 | self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id) | |
483 | ||
484 | def _real_initialize(self): | |
485 | self._initialize_consent() | |
486 | if self._downloader is None: | |
487 | return | |
488 | if not self._login(): | |
489 | return | |
490 | ||
491 | _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;' | |
492 | _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;' | |
493 | _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)' | |
494 | ||
495 | def _get_default_ytcfg(self, client='web'): | |
496 | return copy.deepcopy(INNERTUBE_CLIENTS[client]) | |
497 | ||
498 | def _get_innertube_host(self, client='web'): | |
499 | return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST'] | |
500 | ||
501 | def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'): | |
502 | # try_get but with fallback to default ytcfg client values when present | |
503 | _func = lambda y: try_get(y, getter, expected_type) | |
504 | return _func(ytcfg) or _func(self._get_default_ytcfg(default_client)) | |
505 | ||
506 | def _extract_client_name(self, ytcfg, default_client='web'): | |
507 | return self._ytcfg_get_safe( | |
508 | ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'], | |
509 | lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client) | |
510 | ||
511 | @staticmethod | |
512 | def _extract_session_index(*data): | |
513 | for ytcfg in data: | |
514 | session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX'])) | |
515 | if session_index is not None: | |
516 | return session_index | |
517 | ||
518 | def _extract_client_version(self, ytcfg, default_client='web'): | |
519 | return self._ytcfg_get_safe( | |
520 | ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'], | |
521 | lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client) | |
522 | ||
523 | def _extract_api_key(self, ytcfg=None, default_client='web'): | |
524 | return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client) | |
525 | ||
526 | def _extract_context(self, ytcfg=None, default_client='web'): | |
527 | _get_context = lambda y: try_get(y, lambda x: x['INNERTUBE_CONTEXT'], dict) | |
528 | context = _get_context(ytcfg) | |
529 | if context: | |
530 | return context | |
531 | ||
532 | context = _get_context(self._get_default_ytcfg(default_client)) | |
533 | if not ytcfg: | |
534 | return context | |
535 | ||
536 | # Recreate the client context (required) | |
537 | context['client'].update({ | |
538 | 'clientVersion': self._extract_client_version(ytcfg, default_client), | |
539 | 'clientName': self._extract_client_name(ytcfg, default_client), | |
540 | }) | |
541 | visitor_data = try_get(ytcfg, lambda x: x['VISITOR_DATA'], compat_str) | |
542 | if visitor_data: | |
543 | context['client']['visitorData'] = visitor_data | |
544 | return context | |
545 | ||
546 | _SAPISID = None | |
547 | ||
548 | def _generate_sapisidhash_header(self, origin='https://www.youtube.com'): | |
549 | time_now = round(time.time()) | |
550 | if self._SAPISID is None: | |
551 | yt_cookies = self._get_cookies('https://www.youtube.com') | |
552 | # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is. | |
553 | # See: https://github.com/yt-dlp/yt-dlp/issues/393 | |
554 | sapisid_cookie = dict_get( | |
555 | yt_cookies, ('__Secure-3PAPISID', 'SAPISID')) | |
556 | if sapisid_cookie and sapisid_cookie.value: | |
557 | self._SAPISID = sapisid_cookie.value | |
558 | self.write_debug('Extracted SAPISID cookie') | |
559 | # SAPISID cookie is required if not already present | |
560 | if not yt_cookies.get('SAPISID'): | |
561 | self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie') | |
562 | self._set_cookie( | |
563 | '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600) | |
564 | else: | |
565 | self._SAPISID = False | |
566 | if not self._SAPISID: | |
567 | return None | |
568 | # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323 | |
569 | sapisidhash = hashlib.sha1( | |
570 | f'{time_now} {self._SAPISID} {origin}'.encode('utf-8')).hexdigest() | |
571 | return f'SAPISIDHASH {time_now}_{sapisidhash}' | |
572 | ||
573 | def _call_api(self, ep, query, video_id, fatal=True, headers=None, | |
574 | note='Downloading API JSON', errnote='Unable to download API page', | |
575 | context=None, api_key=None, api_hostname=None, default_client='web'): | |
576 | ||
577 | data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)} | |
578 | data.update(query) | |
579 | real_headers = self.generate_api_headers(default_client=default_client) | |
580 | real_headers.update({'content-type': 'application/json'}) | |
581 | if headers: | |
582 | real_headers.update(headers) | |
583 | return self._download_json( | |
584 | 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep), | |
585 | video_id=video_id, fatal=fatal, note=note, errnote=errnote, | |
586 | data=json.dumps(data).encode('utf8'), headers=real_headers, | |
587 | query={'key': api_key or self._extract_api_key()}) | |
588 | ||
589 | def extract_yt_initial_data(self, video_id, webpage): | |
590 | return self._parse_json( | |
591 | self._search_regex( | |
592 | (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE), | |
593 | self._YT_INITIAL_DATA_RE), webpage, 'yt initial data'), | |
594 | video_id) | |
595 | ||
596 | def _extract_identity_token(self, webpage, item_id): | |
597 | if not webpage: | |
598 | return None | |
599 | ytcfg = self.extract_ytcfg(item_id, webpage) | |
600 | if ytcfg: | |
601 | token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str) | |
602 | if token: | |
603 | return token | |
604 | return self._search_regex( | |
605 | r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage, | |
606 | 'identity token', default=None) | |
607 | ||
608 | @staticmethod | |
609 | def _extract_account_syncid(*args): | |
610 | """ | |
611 | Extract syncId required to download private playlists of secondary channels | |
612 | @params response and/or ytcfg | |
613 | """ | |
614 | for data in args: | |
615 | # ytcfg includes channel_syncid if on secondary channel | |
616 | delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], compat_str) | |
617 | if delegated_sid: | |
618 | return delegated_sid | |
619 | sync_ids = (try_get( | |
620 | data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'], | |
621 | lambda x: x['DATASYNC_ID']), compat_str) or '').split("||") | |
622 | if len(sync_ids) >= 2 and sync_ids[1]: | |
623 | # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel | |
624 | # and just "user_syncid||" for primary channel. We only want the channel_syncid | |
625 | return sync_ids[0] | |
626 | ||
627 | def extract_ytcfg(self, video_id, webpage): | |
628 | if not webpage: | |
629 | return {} | |
630 | return self._parse_json( | |
631 | self._search_regex( | |
632 | r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg', | |
633 | default='{}'), video_id, fatal=False) or {} | |
634 | ||
635 | def generate_api_headers( | |
636 | self, ytcfg=None, identity_token=None, account_syncid=None, | |
637 | visitor_data=None, api_hostname=None, default_client='web', session_index=None): | |
638 | origin = 'https://' + (api_hostname if api_hostname else self._get_innertube_host(default_client)) | |
639 | headers = { | |
640 | 'X-YouTube-Client-Name': compat_str( | |
641 | self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)), | |
642 | 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client), | |
643 | 'Origin': origin | |
644 | } | |
645 | if not visitor_data and ytcfg: | |
646 | visitor_data = try_get( | |
647 | self._extract_context(ytcfg, default_client), lambda x: x['client']['visitorData'], compat_str) | |
648 | if identity_token: | |
649 | headers['X-Youtube-Identity-Token'] = identity_token | |
650 | if account_syncid: | |
651 | headers['X-Goog-PageId'] = account_syncid | |
652 | if session_index is None and ytcfg: | |
653 | session_index = self._extract_session_index(ytcfg) | |
654 | if account_syncid or session_index is not None: | |
655 | headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0 | |
656 | if visitor_data: | |
657 | headers['X-Goog-Visitor-Id'] = visitor_data | |
658 | auth = self._generate_sapisidhash_header(origin) | |
659 | if auth is not None: | |
660 | headers['Authorization'] = auth | |
661 | headers['X-Origin'] = origin | |
662 | return headers | |
663 | ||
664 | @staticmethod | |
665 | def _build_api_continuation_query(continuation, ctp=None): | |
666 | query = { | |
667 | 'continuation': continuation | |
668 | } | |
669 | # TODO: Inconsistency with clickTrackingParams. | |
670 | # Currently we have a fixed ctp contained within context (from ytcfg) | |
671 | # and a ctp in root query for continuation. | |
672 | if ctp: | |
673 | query['clickTracking'] = {'clickTrackingParams': ctp} | |
674 | return query | |
675 | ||
676 | @classmethod | |
677 | def _extract_next_continuation_data(cls, renderer): | |
678 | next_continuation = try_get( | |
679 | renderer, (lambda x: x['continuations'][0]['nextContinuationData'], | |
680 | lambda x: x['continuation']['reloadContinuationData']), dict) | |
681 | if not next_continuation: | |
682 | return | |
683 | continuation = next_continuation.get('continuation') | |
684 | if not continuation: | |
685 | return | |
686 | ctp = next_continuation.get('clickTrackingParams') | |
687 | return cls._build_api_continuation_query(continuation, ctp) | |
688 | ||
689 | @classmethod | |
690 | def _extract_continuation_ep_data(cls, continuation_ep: dict): | |
691 | if isinstance(continuation_ep, dict): | |
692 | continuation = try_get( | |
693 | continuation_ep, lambda x: x['continuationCommand']['token'], compat_str) | |
694 | if not continuation: | |
695 | return | |
696 | ctp = continuation_ep.get('clickTrackingParams') | |
697 | return cls._build_api_continuation_query(continuation, ctp) | |
698 | ||
699 | @classmethod | |
700 | def _extract_continuation(cls, renderer): | |
701 | next_continuation = cls._extract_next_continuation_data(renderer) | |
702 | if next_continuation: | |
703 | return next_continuation | |
704 | ||
705 | contents = [] | |
706 | for key in ('contents', 'items'): | |
707 | contents.extend(try_get(renderer, lambda x: x[key], list) or []) | |
708 | ||
709 | for content in contents: | |
710 | if not isinstance(content, dict): | |
711 | continue | |
712 | continuation_ep = try_get( | |
713 | content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'], | |
714 | lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']), | |
715 | dict) | |
716 | continuation = cls._extract_continuation_ep_data(continuation_ep) | |
717 | if continuation: | |
718 | return continuation | |
719 | ||
720 | @classmethod | |
721 | def _extract_alerts(cls, data): | |
722 | for alert_dict in try_get(data, lambda x: x['alerts'], list) or []: | |
723 | if not isinstance(alert_dict, dict): | |
724 | continue | |
725 | for alert in alert_dict.values(): | |
726 | alert_type = alert.get('type') | |
727 | if not alert_type: | |
728 | continue | |
729 | message = cls._get_text(alert, 'text') | |
730 | if message: | |
731 | yield alert_type, message | |
732 | ||
733 | def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False): | |
734 | errors = [] | |
735 | warnings = [] | |
736 | for alert_type, alert_message in alerts: | |
737 | if alert_type.lower() == 'error' and fatal: | |
738 | errors.append([alert_type, alert_message]) | |
739 | else: | |
740 | warnings.append([alert_type, alert_message]) | |
741 | ||
742 | for alert_type, alert_message in (warnings + errors[:-1]): | |
743 | self.report_warning('YouTube said: %s - %s' % (alert_type, alert_message), only_once=only_once) | |
744 | if errors: | |
745 | raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected) | |
746 | ||
747 | def _extract_and_report_alerts(self, data, *args, **kwargs): | |
748 | return self._report_alerts(self._extract_alerts(data), *args, **kwargs) | |
749 | ||
750 | def _extract_badges(self, renderer: dict): | |
751 | badges = set() | |
752 | for badge in try_get(renderer, lambda x: x['badges'], list) or []: | |
753 | label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], compat_str) | |
754 | if label: | |
755 | badges.add(label.lower()) | |
756 | return badges | |
757 | ||
758 | @staticmethod | |
759 | def _get_text(data, *path_list, max_runs=None): | |
760 | for path in path_list or [None]: | |
761 | if path is None: | |
762 | obj = [data] | |
763 | else: | |
764 | obj = traverse_obj(data, path, default=[]) | |
765 | if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)): | |
766 | obj = [obj] | |
767 | for item in obj: | |
768 | text = try_get(item, lambda x: x['simpleText'], compat_str) | |
769 | if text: | |
770 | return text | |
771 | runs = try_get(item, lambda x: x['runs'], list) or [] | |
772 | if not runs and isinstance(item, list): | |
773 | runs = item | |
774 | ||
775 | runs = runs[:min(len(runs), max_runs or len(runs))] | |
776 | text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[])) | |
777 | if text: | |
778 | return text | |
779 | ||
780 | def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None, | |
781 | ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None, | |
782 | default_client='web'): | |
783 | response = None | |
784 | last_error = None | |
785 | count = -1 | |
786 | retries = self.get_param('extractor_retries', 3) | |
787 | if check_get_keys is None: | |
788 | check_get_keys = [] | |
789 | while count < retries: | |
790 | count += 1 | |
791 | if last_error: | |
792 | self.report_warning('%s. Retrying ...' % remove_end(last_error, '.')) | |
793 | try: | |
794 | response = self._call_api( | |
795 | ep=ep, fatal=True, headers=headers, | |
796 | video_id=item_id, query=query, | |
797 | context=self._extract_context(ytcfg, default_client), | |
798 | api_key=self._extract_api_key(ytcfg, default_client), | |
799 | api_hostname=api_hostname, default_client=default_client, | |
800 | note='%s%s' % (note, ' (retry #%d)' % count if count else '')) | |
801 | except ExtractorError as e: | |
802 | if isinstance(e.cause, network_exceptions): | |
803 | if isinstance(e.cause, compat_HTTPError) and not is_html(e.cause.read(512)): | |
804 | e.cause.seek(0) | |
805 | yt_error = try_get( | |
806 | self._parse_json(e.cause.read().decode(), item_id, fatal=False), | |
807 | lambda x: x['error']['message'], compat_str) | |
808 | if yt_error: | |
809 | self._report_alerts([('ERROR', yt_error)], fatal=False) | |
810 | # Downloading page may result in intermittent 5xx HTTP error | |
811 | # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289 | |
812 | # We also want to catch all other network exceptions since errors in later pages can be troublesome | |
813 | # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210 | |
814 | if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429): | |
815 | last_error = error_to_compat_str(e.cause or e.msg) | |
816 | if count < retries: | |
817 | continue | |
818 | if fatal: | |
819 | raise | |
820 | else: | |
821 | self.report_warning(error_to_compat_str(e)) | |
822 | return | |
823 | ||
824 | else: | |
825 | # Youtube may send alerts if there was an issue with the continuation page | |
826 | try: | |
827 | self._extract_and_report_alerts(response, expected=False, only_once=True) | |
828 | except ExtractorError as e: | |
829 | # YouTube servers may return errors we want to retry on in a 200 OK response | |
830 | # See: https://github.com/yt-dlp/yt-dlp/issues/839 | |
831 | if 'unknown error' in e.msg.lower(): | |
832 | last_error = e.msg | |
833 | continue | |
834 | if fatal: | |
835 | raise | |
836 | self.report_warning(error_to_compat_str(e)) | |
837 | return | |
838 | if not check_get_keys or dict_get(response, check_get_keys): | |
839 | break | |
840 | # Youtube sometimes sends incomplete data | |
841 | # See: https://github.com/ytdl-org/youtube-dl/issues/28194 | |
842 | last_error = 'Incomplete data received' | |
843 | if count >= retries: | |
844 | if fatal: | |
845 | raise ExtractorError(last_error) | |
846 | else: | |
847 | self.report_warning(last_error) | |
848 | return | |
849 | return response | |
850 | ||
851 | @staticmethod | |
852 | def is_music_url(url): | |
853 | return re.match(r'https?://music\.youtube\.com/', url) is not None | |
854 | ||
855 | def _extract_video(self, renderer): | |
856 | video_id = renderer.get('videoId') | |
857 | title = self._get_text(renderer, 'title') | |
858 | description = self._get_text(renderer, 'descriptionSnippet') | |
859 | duration = parse_duration(self._get_text( | |
860 | renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text'))) | |
861 | view_count_text = self._get_text(renderer, 'viewCountText') or '' | |
862 | view_count = str_to_int(self._search_regex( | |
863 | r'^([\d,]+)', re.sub(r'\s', '', view_count_text), | |
864 | 'view count', default=None)) | |
865 | ||
866 | uploader = self._get_text(renderer, 'ownerText', 'shortBylineText') | |
867 | ||
868 | return { | |
869 | '_type': 'url', | |
870 | 'ie_key': YoutubeIE.ie_key(), | |
871 | 'id': video_id, | |
872 | 'url': f'https://www.youtube.com/watch?v={video_id}', | |
873 | 'title': title, | |
874 | 'description': description, | |
875 | 'duration': duration, | |
876 | 'view_count': view_count, | |
877 | 'uploader': uploader, | |
878 | } | |
879 | ||
880 | ||
881 | class YoutubeIE(YoutubeBaseInfoExtractor): | |
882 | IE_DESC = 'YouTube.com' | |
883 | _INVIDIOUS_SITES = ( | |
884 | # invidious-redirect websites | |
885 | r'(?:www\.)?redirect\.invidious\.io', | |
886 | r'(?:(?:www|dev)\.)?invidio\.us', | |
887 | # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md | |
888 | r'(?:www\.)?invidious\.pussthecat\.org', | |
889 | r'(?:www\.)?invidious\.zee\.li', | |
890 | r'(?:www\.)?invidious\.ethibox\.fr', | |
891 | r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion', | |
892 | # youtube-dl invidious instances list | |
893 | r'(?:(?:www|no)\.)?invidiou\.sh', | |
894 | r'(?:(?:www|fi)\.)?invidious\.snopyta\.org', | |
895 | r'(?:www\.)?invidious\.kabi\.tk', | |
896 | r'(?:www\.)?invidious\.mastodon\.host', | |
897 | r'(?:www\.)?invidious\.zapashcanon\.fr', | |
898 | r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks', | |
899 | r'(?:www\.)?invidious\.tinfoil-hat\.net', | |
900 | r'(?:www\.)?invidious\.himiko\.cloud', | |
901 | r'(?:www\.)?invidious\.reallyancient\.tech', | |
902 | r'(?:www\.)?invidious\.tube', | |
903 | r'(?:www\.)?invidiou\.site', | |
904 | r'(?:www\.)?invidious\.site', | |
905 | r'(?:www\.)?invidious\.xyz', | |
906 | r'(?:www\.)?invidious\.nixnet\.xyz', | |
907 | r'(?:www\.)?invidious\.048596\.xyz', | |
908 | r'(?:www\.)?invidious\.drycat\.fr', | |
909 | r'(?:www\.)?inv\.skyn3t\.in', | |
910 | r'(?:www\.)?tube\.poal\.co', | |
911 | r'(?:www\.)?tube\.connect\.cafe', | |
912 | r'(?:www\.)?vid\.wxzm\.sx', | |
913 | r'(?:www\.)?vid\.mint\.lgbt', | |
914 | r'(?:www\.)?vid\.puffyan\.us', | |
915 | r'(?:www\.)?yewtu\.be', | |
916 | r'(?:www\.)?yt\.elukerio\.org', | |
917 | r'(?:www\.)?yt\.lelux\.fi', | |
918 | r'(?:www\.)?invidious\.ggc-project\.de', | |
919 | r'(?:www\.)?yt\.maisputain\.ovh', | |
920 | r'(?:www\.)?ytprivate\.com', | |
921 | r'(?:www\.)?invidious\.13ad\.de', | |
922 | r'(?:www\.)?invidious\.toot\.koeln', | |
923 | r'(?:www\.)?invidious\.fdn\.fr', | |
924 | r'(?:www\.)?watch\.nettohikari\.com', | |
925 | r'(?:www\.)?invidious\.namazso\.eu', | |
926 | r'(?:www\.)?invidious\.silkky\.cloud', | |
927 | r'(?:www\.)?invidious\.exonip\.de', | |
928 | r'(?:www\.)?invidious\.riverside\.rocks', | |
929 | r'(?:www\.)?invidious\.blamefran\.net', | |
930 | r'(?:www\.)?invidious\.moomoo\.de', | |
931 | r'(?:www\.)?ytb\.trom\.tf', | |
932 | r'(?:www\.)?yt\.cyberhost\.uk', | |
933 | r'(?:www\.)?kgg2m7yk5aybusll\.onion', | |
934 | r'(?:www\.)?qklhadlycap4cnod\.onion', | |
935 | r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion', | |
936 | r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion', | |
937 | r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion', | |
938 | r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion', | |
939 | r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p', | |
940 | r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion', | |
941 | r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion', | |
942 | r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion', | |
943 | r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion', | |
944 | r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion', | |
945 | ) | |
946 | _VALID_URL = r"""(?x)^ | |
947 | ( | |
948 | (?:https?://|//) # http(s):// or protocol-independent URL | |
949 | (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com| | |
950 | (?:www\.)?deturl\.com/www\.youtube\.com| | |
951 | (?:www\.)?pwnyoutube\.com| | |
952 | (?:www\.)?hooktube\.com| | |
953 | (?:www\.)?yourepeat\.com| | |
954 | tube\.majestyc\.net| | |
955 | %(invidious)s| | |
956 | youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains | |
957 | (?:.*?\#/)? # handle anchor (#/) redirect urls | |
958 | (?: # the various things that can precede the ID: | |
959 | (?:(?:v|embed|e|shorts)/(?!videoseries)) # v/ or embed/ or e/ or shorts/ | |
960 | |(?: # or the v= param in all its forms | |
961 | (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) | |
962 | (?:\?|\#!?) # the params delimiter ? or # or #! | |
963 | (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY) | |
964 | v= | |
965 | ) | |
966 | )) | |
967 | |(?: | |
968 | youtu\.be| # just youtu.be/xxxx | |
969 | vid\.plus| # or vid.plus/xxxx | |
970 | zwearz\.com/watch| # or zwearz.com/watch/xxxx | |
971 | %(invidious)s | |
972 | )/ | |
973 | |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId= | |
974 | ) | |
975 | )? # all until now is optional -> you can pass the naked ID | |
976 | (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID | |
977 | (?(1).+)? # if we found the ID, everything can follow | |
978 | (?:\#|$)""" % { | |
979 | 'invidious': '|'.join(_INVIDIOUS_SITES), | |
980 | } | |
981 | _PLAYER_INFO_RE = ( | |
982 | r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player', | |
983 | r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$', | |
984 | r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$', | |
985 | ) | |
986 | _formats = { | |
987 | '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, | |
988 | '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, | |
989 | '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}, | |
990 | '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}, | |
991 | '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}, | |
992 | '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
993 | '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
994 | '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
995 | # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well | |
996 | '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}, | |
997 | '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
998 | '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
999 | '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
1000 | '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
1001 | '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, | |
1002 | '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, | |
1003 | '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
1004 | '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
1005 | ||
1006 | ||
1007 | # 3D videos | |
1008 | '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, | |
1009 | '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, | |
1010 | '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
1011 | '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
1012 | '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}, | |
1013 | '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
1014 | '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
1015 | ||
1016 | # Apple HTTP Live Streaming | |
1017 | '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, | |
1018 | '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, | |
1019 | '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
1020 | '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
1021 | '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
1022 | '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
1023 | '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, | |
1024 | '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}, | |
1025 | ||
1026 | # DASH mp4 video | |
1027 | '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
1028 | '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
1029 | '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
1030 | '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
1031 | '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
1032 | '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559) | |
1033 | '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
1034 | '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
1035 | '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
1036 | '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
1037 | '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
1038 | '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
1039 | ||
1040 | # Dash mp4 audio | |
1041 | '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}, | |
1042 | '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}, | |
1043 | '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}, | |
1044 | '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
1045 | '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
1046 | '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}, | |
1047 | '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}, | |
1048 | ||
1049 | # Dash webm | |
1050 | '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1051 | '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1052 | '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1053 | '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1054 | '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1055 | '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1056 | '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}, | |
1057 | '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1058 | '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1059 | '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1060 | '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1061 | '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1062 | '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1063 | '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1064 | '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1065 | # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug) | |
1066 | '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1067 | '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
1068 | '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
1069 | '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
1070 | '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1071 | '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
1072 | ||
1073 | # Dash webm audio | |
1074 | '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}, | |
1075 | '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}, | |
1076 | ||
1077 | # Dash webm audio with opus inside | |
1078 | '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}, | |
1079 | '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}, | |
1080 | '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}, | |
1081 | ||
1082 | # RTMP (unnamed) | |
1083 | '_rtmp': {'protocol': 'rtmp'}, | |
1084 | ||
1085 | # av01 video only formats sometimes served with "unknown" codecs | |
1086 | '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'}, | |
1087 | '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'}, | |
1088 | '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'}, | |
1089 | '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'}, | |
1090 | '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'}, | |
1091 | '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'}, | |
1092 | '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}, | |
1093 | '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}, | |
1094 | } | |
1095 | _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt') | |
1096 | ||
1097 | _GEO_BYPASS = False | |
1098 | ||
1099 | IE_NAME = 'youtube' | |
1100 | _TESTS = [ | |
1101 | { | |
1102 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9', | |
1103 | 'info_dict': { | |
1104 | 'id': 'BaW_jenozKc', | |
1105 | 'ext': 'mp4', | |
1106 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
1107 | 'uploader': 'Philipp Hagemeister', | |
1108 | 'uploader_id': 'phihag', | |
1109 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', | |
1110 | 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', | |
1111 | 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', | |
1112 | 'upload_date': '20121002', | |
1113 | '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 .', | |
1114 | 'categories': ['Science & Technology'], | |
1115 | 'tags': ['youtube-dl'], | |
1116 | 'duration': 10, | |
1117 | 'view_count': int, | |
1118 | 'like_count': int, | |
1119 | 'dislike_count': int, | |
1120 | 'start_time': 1, | |
1121 | 'end_time': 9, | |
1122 | } | |
1123 | }, | |
1124 | { | |
1125 | 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ', | |
1126 | 'note': 'Embed-only video (#1746)', | |
1127 | 'info_dict': { | |
1128 | 'id': 'yZIXLfi8CZQ', | |
1129 | 'ext': 'mp4', | |
1130 | 'upload_date': '20120608', | |
1131 | 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012', | |
1132 | 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7', | |
1133 | 'uploader': 'SET India', | |
1134 | 'uploader_id': 'setindia', | |
1135 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia', | |
1136 | 'age_limit': 18, | |
1137 | }, | |
1138 | 'skip': 'Private video', | |
1139 | }, | |
1140 | { | |
1141 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ', | |
1142 | 'note': 'Use the first video ID in the URL', | |
1143 | 'info_dict': { | |
1144 | 'id': 'BaW_jenozKc', | |
1145 | 'ext': 'mp4', | |
1146 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
1147 | 'uploader': 'Philipp Hagemeister', | |
1148 | 'uploader_id': 'phihag', | |
1149 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', | |
1150 | 'upload_date': '20121002', | |
1151 | '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 .', | |
1152 | 'categories': ['Science & Technology'], | |
1153 | 'tags': ['youtube-dl'], | |
1154 | 'duration': 10, | |
1155 | 'view_count': int, | |
1156 | 'like_count': int, | |
1157 | 'dislike_count': int, | |
1158 | }, | |
1159 | 'params': { | |
1160 | 'skip_download': True, | |
1161 | }, | |
1162 | }, | |
1163 | { | |
1164 | 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I', | |
1165 | 'note': '256k DASH audio (format 141) via DASH manifest', | |
1166 | 'info_dict': { | |
1167 | 'id': 'a9LDPn-MO4I', | |
1168 | 'ext': 'm4a', | |
1169 | 'upload_date': '20121002', | |
1170 | 'uploader_id': '8KVIDEO', | |
1171 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO', | |
1172 | 'description': '', | |
1173 | 'uploader': '8KVIDEO', | |
1174 | 'title': 'UHDTV TEST 8K VIDEO.mp4' | |
1175 | }, | |
1176 | 'params': { | |
1177 | 'youtube_include_dash_manifest': True, | |
1178 | 'format': '141', | |
1179 | }, | |
1180 | 'skip': 'format 141 not served anymore', | |
1181 | }, | |
1182 | # DASH manifest with encrypted signature | |
1183 | { | |
1184 | 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA', | |
1185 | 'info_dict': { | |
1186 | 'id': 'IB3lcPjvWLA', | |
1187 | 'ext': 'm4a', | |
1188 | 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson', | |
1189 | 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf', | |
1190 | 'duration': 244, | |
1191 | 'uploader': 'AfrojackVEVO', | |
1192 | 'uploader_id': 'AfrojackVEVO', | |
1193 | 'upload_date': '20131011', | |
1194 | 'abr': 129.495, | |
1195 | }, | |
1196 | 'params': { | |
1197 | 'youtube_include_dash_manifest': True, | |
1198 | 'format': '141/bestaudio[ext=m4a]', | |
1199 | }, | |
1200 | }, | |
1201 | # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000 | |
1202 | { | |
1203 | 'note': 'Embed allowed age-gate video', | |
1204 | 'url': 'https://youtube.com/watch?v=HtVdAasjOgU', | |
1205 | 'info_dict': { | |
1206 | 'id': 'HtVdAasjOgU', | |
1207 | 'ext': 'mp4', | |
1208 | 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer', | |
1209 | 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}', | |
1210 | 'duration': 142, | |
1211 | 'uploader': 'The Witcher', | |
1212 | 'uploader_id': 'WitcherGame', | |
1213 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame', | |
1214 | 'upload_date': '20140605', | |
1215 | 'age_limit': 18, | |
1216 | }, | |
1217 | }, | |
1218 | { | |
1219 | 'note': 'Age-gate video with embed allowed in public site', | |
1220 | 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U', | |
1221 | 'info_dict': { | |
1222 | 'id': 'HsUATh_Nc2U', | |
1223 | 'ext': 'mp4', | |
1224 | 'title': 'Godzilla 2 (Official Video)', | |
1225 | 'description': 'md5:bf77e03fcae5529475e500129b05668a', | |
1226 | 'upload_date': '20200408', | |
1227 | 'uploader_id': 'FlyingKitty900', | |
1228 | 'uploader': 'FlyingKitty', | |
1229 | 'age_limit': 18, | |
1230 | }, | |
1231 | }, | |
1232 | { | |
1233 | 'note': 'Age-gate video embedable only with clientScreen=EMBED', | |
1234 | 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg', | |
1235 | 'info_dict': { | |
1236 | 'id': 'Tq92D6wQ1mg', | |
1237 | 'title': '[MMD] Adios - EVERGLOW [+Motion DL]', | |
1238 | 'ext': 'mp4', | |
1239 | 'upload_date': '20191227', | |
1240 | 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ', | |
1241 | 'uploader': 'Projekt Melody', | |
1242 | 'description': 'md5:17eccca93a786d51bc67646756894066', | |
1243 | 'age_limit': 18, | |
1244 | }, | |
1245 | }, | |
1246 | { | |
1247 | 'note': 'Non-Agegated non-embeddable video', | |
1248 | 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY', | |
1249 | 'info_dict': { | |
1250 | 'id': 'MeJVWBSsPAY', | |
1251 | 'ext': 'mp4', | |
1252 | 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)', | |
1253 | 'uploader': 'Herr Lurik', | |
1254 | 'uploader_id': 'st3in234', | |
1255 | 'description': 'Fan Video. Music & Lyrics by OOMPH!.', | |
1256 | 'upload_date': '20130730', | |
1257 | }, | |
1258 | }, | |
1259 | { | |
1260 | 'note': 'Non-bypassable age-gated video', | |
1261 | 'url': 'https://youtube.com/watch?v=Cr381pDsSsA', | |
1262 | 'only_matching': True, | |
1263 | }, | |
1264 | # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421) | |
1265 | # YouTube Red ad is not captured for creator | |
1266 | { | |
1267 | 'url': '__2ABJjxzNo', | |
1268 | 'info_dict': { | |
1269 | 'id': '__2ABJjxzNo', | |
1270 | 'ext': 'mp4', | |
1271 | 'duration': 266, | |
1272 | 'upload_date': '20100430', | |
1273 | 'uploader_id': 'deadmau5', | |
1274 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5', | |
1275 | 'creator': 'deadmau5', | |
1276 | 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336', | |
1277 | 'uploader': 'deadmau5', | |
1278 | 'title': 'Deadmau5 - Some Chords (HD)', | |
1279 | 'alt_title': 'Some Chords', | |
1280 | }, | |
1281 | 'expected_warnings': [ | |
1282 | 'DASH manifest missing', | |
1283 | ] | |
1284 | }, | |
1285 | # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431) | |
1286 | { | |
1287 | 'url': 'lqQg6PlCWgI', | |
1288 | 'info_dict': { | |
1289 | 'id': 'lqQg6PlCWgI', | |
1290 | 'ext': 'mp4', | |
1291 | 'duration': 6085, | |
1292 | 'upload_date': '20150827', | |
1293 | 'uploader_id': 'olympic', | |
1294 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic', | |
1295 | 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', | |
1296 | 'uploader': 'Olympics', | |
1297 | 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', | |
1298 | }, | |
1299 | 'params': { | |
1300 | 'skip_download': 'requires avconv', | |
1301 | } | |
1302 | }, | |
1303 | # Non-square pixels | |
1304 | { | |
1305 | 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0', | |
1306 | 'info_dict': { | |
1307 | 'id': '_b-2C3KPAM0', | |
1308 | 'ext': 'mp4', | |
1309 | 'stretched_ratio': 16 / 9., | |
1310 | 'duration': 85, | |
1311 | 'upload_date': '20110310', | |
1312 | 'uploader_id': 'AllenMeow', | |
1313 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow', | |
1314 | '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', | |
1315 | 'uploader': '孫ᄋᄅ', | |
1316 | 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', | |
1317 | }, | |
1318 | }, | |
1319 | # url_encoded_fmt_stream_map is empty string | |
1320 | { | |
1321 | 'url': 'qEJwOuvDf7I', | |
1322 | 'info_dict': { | |
1323 | 'id': 'qEJwOuvDf7I', | |
1324 | 'ext': 'webm', | |
1325 | 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге', | |
1326 | 'description': '', | |
1327 | 'upload_date': '20150404', | |
1328 | 'uploader_id': 'spbelect', | |
1329 | 'uploader': 'Наблюдатели Петербурга', | |
1330 | }, | |
1331 | 'params': { | |
1332 | 'skip_download': 'requires avconv', | |
1333 | }, | |
1334 | 'skip': 'This live event has ended.', | |
1335 | }, | |
1336 | # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097) | |
1337 | { | |
1338 | 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y', | |
1339 | 'info_dict': { | |
1340 | 'id': 'FIl7x6_3R5Y', | |
1341 | 'ext': 'webm', | |
1342 | 'title': 'md5:7b81415841e02ecd4313668cde88737a', | |
1343 | 'description': 'md5:116377fd2963b81ec4ce64b542173306', | |
1344 | 'duration': 220, | |
1345 | 'upload_date': '20150625', | |
1346 | 'uploader_id': 'dorappi2000', | |
1347 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000', | |
1348 | 'uploader': 'dorappi2000', | |
1349 | 'formats': 'mincount:31', | |
1350 | }, | |
1351 | 'skip': 'not actual anymore', | |
1352 | }, | |
1353 | # DASH manifest with segment_list | |
1354 | { | |
1355 | 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8', | |
1356 | 'md5': '8ce563a1d667b599d21064e982ab9e31', | |
1357 | 'info_dict': { | |
1358 | 'id': 'CsmdDsKjzN8', | |
1359 | 'ext': 'mp4', | |
1360 | 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510 | |
1361 | 'uploader': 'Airtek', | |
1362 | 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.', | |
1363 | 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ', | |
1364 | 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015', | |
1365 | }, | |
1366 | 'params': { | |
1367 | 'youtube_include_dash_manifest': True, | |
1368 | 'format': '135', # bestvideo | |
1369 | }, | |
1370 | 'skip': 'This live event has ended.', | |
1371 | }, | |
1372 | { | |
1373 | # Multifeed videos (multiple cameras), URL is for Main Camera | |
1374 | 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg', | |
1375 | 'info_dict': { | |
1376 | 'id': 'jvGDaLqkpTg', | |
1377 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever', | |
1378 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
1379 | }, | |
1380 | 'playlist': [{ | |
1381 | 'info_dict': { | |
1382 | 'id': 'jvGDaLqkpTg', | |
1383 | 'ext': 'mp4', | |
1384 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)', | |
1385 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
1386 | 'duration': 10643, | |
1387 | 'upload_date': '20161111', | |
1388 | 'uploader': 'Team PGP', | |
1389 | 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg', | |
1390 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg', | |
1391 | }, | |
1392 | }, { | |
1393 | 'info_dict': { | |
1394 | 'id': '3AKt1R1aDnw', | |
1395 | 'ext': 'mp4', | |
1396 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)', | |
1397 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
1398 | 'duration': 10991, | |
1399 | 'upload_date': '20161111', | |
1400 | 'uploader': 'Team PGP', | |
1401 | 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg', | |
1402 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg', | |
1403 | }, | |
1404 | }, { | |
1405 | 'info_dict': { | |
1406 | 'id': 'RtAMM00gpVc', | |
1407 | 'ext': 'mp4', | |
1408 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)', | |
1409 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
1410 | 'duration': 10995, | |
1411 | 'upload_date': '20161111', | |
1412 | 'uploader': 'Team PGP', | |
1413 | 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg', | |
1414 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg', | |
1415 | }, | |
1416 | }, { | |
1417 | 'info_dict': { | |
1418 | 'id': '6N2fdlP3C5U', | |
1419 | 'ext': 'mp4', | |
1420 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)', | |
1421 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
1422 | 'duration': 10990, | |
1423 | 'upload_date': '20161111', | |
1424 | 'uploader': 'Team PGP', | |
1425 | 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg', | |
1426 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg', | |
1427 | }, | |
1428 | }], | |
1429 | 'params': { | |
1430 | 'skip_download': True, | |
1431 | }, | |
1432 | 'skip': 'Not multifeed anymore', | |
1433 | }, | |
1434 | { | |
1435 | # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536) | |
1436 | 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo', | |
1437 | 'info_dict': { | |
1438 | 'id': 'gVfLd0zydlo', | |
1439 | 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30', | |
1440 | }, | |
1441 | 'playlist_count': 2, | |
1442 | 'skip': 'Not multifeed anymore', | |
1443 | }, | |
1444 | { | |
1445 | 'url': 'https://vid.plus/FlRa-iH7PGw', | |
1446 | 'only_matching': True, | |
1447 | }, | |
1448 | { | |
1449 | 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html', | |
1450 | 'only_matching': True, | |
1451 | }, | |
1452 | { | |
1453 | # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468) | |
1454 | # Also tests cut-off URL expansion in video description (see | |
1455 | # https://github.com/ytdl-org/youtube-dl/issues/1892, | |
1456 | # https://github.com/ytdl-org/youtube-dl/issues/8164) | |
1457 | 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg', | |
1458 | 'info_dict': { | |
1459 | 'id': 'lsguqyKfVQg', | |
1460 | 'ext': 'mp4', | |
1461 | 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21', | |
1462 | 'alt_title': 'Dark Walk', | |
1463 | 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a', | |
1464 | 'duration': 133, | |
1465 | 'upload_date': '20151119', | |
1466 | 'uploader_id': 'IronSoulElf', | |
1467 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf', | |
1468 | 'uploader': 'IronSoulElf', | |
1469 | 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan', | |
1470 | 'track': 'Dark Walk', | |
1471 | 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan', | |
1472 | 'album': 'Position Music - Production Music Vol. 143 - Dark Walk', | |
1473 | }, | |
1474 | 'params': { | |
1475 | 'skip_download': True, | |
1476 | }, | |
1477 | }, | |
1478 | { | |
1479 | # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468) | |
1480 | 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8', | |
1481 | 'only_matching': True, | |
1482 | }, | |
1483 | { | |
1484 | # Video with yt:stretch=17:0 | |
1485 | 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM', | |
1486 | 'info_dict': { | |
1487 | 'id': 'Q39EVAstoRM', | |
1488 | 'ext': 'mp4', | |
1489 | 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4', | |
1490 | 'description': 'md5:ee18a25c350637c8faff806845bddee9', | |
1491 | 'upload_date': '20151107', | |
1492 | 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA', | |
1493 | 'uploader': 'CH GAMER DROID', | |
1494 | }, | |
1495 | 'params': { | |
1496 | 'skip_download': True, | |
1497 | }, | |
1498 | 'skip': 'This video does not exist.', | |
1499 | }, | |
1500 | { | |
1501 | # Video with incomplete 'yt:stretch=16:' | |
1502 | 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI', | |
1503 | 'only_matching': True, | |
1504 | }, | |
1505 | { | |
1506 | # Video licensed under Creative Commons | |
1507 | 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA', | |
1508 | 'info_dict': { | |
1509 | 'id': 'M4gD1WSo5mA', | |
1510 | 'ext': 'mp4', | |
1511 | 'title': 'md5:e41008789470fc2533a3252216f1c1d1', | |
1512 | 'description': 'md5:a677553cf0840649b731a3024aeff4cc', | |
1513 | 'duration': 721, | |
1514 | 'upload_date': '20150127', | |
1515 | 'uploader_id': 'BerkmanCenter', | |
1516 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter', | |
1517 | 'uploader': 'The Berkman Klein Center for Internet & Society', | |
1518 | 'license': 'Creative Commons Attribution license (reuse allowed)', | |
1519 | }, | |
1520 | 'params': { | |
1521 | 'skip_download': True, | |
1522 | }, | |
1523 | }, | |
1524 | { | |
1525 | # Channel-like uploader_url | |
1526 | 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg', | |
1527 | 'info_dict': { | |
1528 | 'id': 'eQcmzGIKrzg', | |
1529 | 'ext': 'mp4', | |
1530 | 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders', | |
1531 | 'description': 'md5:13a2503d7b5904ef4b223aa101628f39', | |
1532 | 'duration': 4060, | |
1533 | 'upload_date': '20151119', | |
1534 | 'uploader': 'Bernie Sanders', | |
1535 | 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg', | |
1536 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg', | |
1537 | 'license': 'Creative Commons Attribution license (reuse allowed)', | |
1538 | }, | |
1539 | 'params': { | |
1540 | 'skip_download': True, | |
1541 | }, | |
1542 | }, | |
1543 | { | |
1544 | 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY', | |
1545 | 'only_matching': True, | |
1546 | }, | |
1547 | { | |
1548 | # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059) | |
1549 | 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo', | |
1550 | 'only_matching': True, | |
1551 | }, | |
1552 | { | |
1553 | # Rental video preview | |
1554 | 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg', | |
1555 | 'info_dict': { | |
1556 | 'id': 'uGpuVWrhIzE', | |
1557 | 'ext': 'mp4', | |
1558 | 'title': 'Piku - Trailer', | |
1559 | 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb', | |
1560 | 'upload_date': '20150811', | |
1561 | 'uploader': 'FlixMatrix', | |
1562 | 'uploader_id': 'FlixMatrixKaravan', | |
1563 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan', | |
1564 | 'license': 'Standard YouTube License', | |
1565 | }, | |
1566 | 'params': { | |
1567 | 'skip_download': True, | |
1568 | }, | |
1569 | 'skip': 'This video is not available.', | |
1570 | }, | |
1571 | { | |
1572 | # YouTube Red video with episode data | |
1573 | 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4', | |
1574 | 'info_dict': { | |
1575 | 'id': 'iqKdEhx-dD4', | |
1576 | 'ext': 'mp4', | |
1577 | 'title': 'Isolation - Mind Field (Ep 1)', | |
1578 | 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd', | |
1579 | 'duration': 2085, | |
1580 | 'upload_date': '20170118', | |
1581 | 'uploader': 'Vsauce', | |
1582 | 'uploader_id': 'Vsauce', | |
1583 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce', | |
1584 | 'series': 'Mind Field', | |
1585 | 'season_number': 1, | |
1586 | 'episode_number': 1, | |
1587 | }, | |
1588 | 'params': { | |
1589 | 'skip_download': True, | |
1590 | }, | |
1591 | 'expected_warnings': [ | |
1592 | 'Skipping DASH manifest', | |
1593 | ], | |
1594 | }, | |
1595 | { | |
1596 | # The following content has been identified by the YouTube community | |
1597 | # as inappropriate or offensive to some audiences. | |
1598 | 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI', | |
1599 | 'info_dict': { | |
1600 | 'id': '6SJNVb0GnPI', | |
1601 | 'ext': 'mp4', | |
1602 | 'title': 'Race Differences in Intelligence', | |
1603 | 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1', | |
1604 | 'duration': 965, | |
1605 | 'upload_date': '20140124', | |
1606 | 'uploader': 'New Century Foundation', | |
1607 | 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg', | |
1608 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg', | |
1609 | }, | |
1610 | 'params': { | |
1611 | 'skip_download': True, | |
1612 | }, | |
1613 | 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.', | |
1614 | }, | |
1615 | { | |
1616 | # itag 212 | |
1617 | 'url': '1t24XAntNCY', | |
1618 | 'only_matching': True, | |
1619 | }, | |
1620 | { | |
1621 | # geo restricted to JP | |
1622 | 'url': 'sJL6WA-aGkQ', | |
1623 | 'only_matching': True, | |
1624 | }, | |
1625 | { | |
1626 | 'url': 'https://invidio.us/watch?v=BaW_jenozKc', | |
1627 | 'only_matching': True, | |
1628 | }, | |
1629 | { | |
1630 | 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc', | |
1631 | 'only_matching': True, | |
1632 | }, | |
1633 | { | |
1634 | # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m | |
1635 | 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA', | |
1636 | 'only_matching': True, | |
1637 | }, | |
1638 | { | |
1639 | # DRM protected | |
1640 | 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc', | |
1641 | 'only_matching': True, | |
1642 | }, | |
1643 | { | |
1644 | # Video with unsupported adaptive stream type formats | |
1645 | 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U', | |
1646 | 'info_dict': { | |
1647 | 'id': 'Z4Vy8R84T1U', | |
1648 | 'ext': 'mp4', | |
1649 | 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta', | |
1650 | 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', | |
1651 | 'duration': 433, | |
1652 | 'upload_date': '20130923', | |
1653 | 'uploader': 'Amelia Putri Harwita', | |
1654 | 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q', | |
1655 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q', | |
1656 | 'formats': 'maxcount:10', | |
1657 | }, | |
1658 | 'params': { | |
1659 | 'skip_download': True, | |
1660 | 'youtube_include_dash_manifest': False, | |
1661 | }, | |
1662 | 'skip': 'not actual anymore', | |
1663 | }, | |
1664 | { | |
1665 | # Youtube Music Auto-generated description | |
1666 | 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs', | |
1667 | 'info_dict': { | |
1668 | 'id': 'MgNrAu2pzNs', | |
1669 | 'ext': 'mp4', | |
1670 | 'title': 'Voyeur Girl', | |
1671 | 'description': 'md5:7ae382a65843d6df2685993e90a8628f', | |
1672 | 'upload_date': '20190312', | |
1673 | 'uploader': 'Stephen - Topic', | |
1674 | 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA', | |
1675 | 'artist': 'Stephen', | |
1676 | 'track': 'Voyeur Girl', | |
1677 | 'album': 'it\'s too much love to know my dear', | |
1678 | 'release_date': '20190313', | |
1679 | 'release_year': 2019, | |
1680 | }, | |
1681 | 'params': { | |
1682 | 'skip_download': True, | |
1683 | }, | |
1684 | }, | |
1685 | { | |
1686 | 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q', | |
1687 | 'only_matching': True, | |
1688 | }, | |
1689 | { | |
1690 | # invalid -> valid video id redirection | |
1691 | 'url': 'DJztXj2GPfl', | |
1692 | 'info_dict': { | |
1693 | 'id': 'DJztXj2GPfk', | |
1694 | 'ext': 'mp4', | |
1695 | 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)', | |
1696 | 'description': 'md5:bf577a41da97918e94fa9798d9228825', | |
1697 | 'upload_date': '20090125', | |
1698 | 'uploader': 'Prochorowka', | |
1699 | 'uploader_id': 'Prochorowka', | |
1700 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka', | |
1701 | 'artist': 'Panjabi MC', | |
1702 | 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix', | |
1703 | 'album': 'Beware of the Boys (Mundian To Bach Ke)', | |
1704 | }, | |
1705 | 'params': { | |
1706 | 'skip_download': True, | |
1707 | }, | |
1708 | 'skip': 'Video unavailable', | |
1709 | }, | |
1710 | { | |
1711 | # empty description results in an empty string | |
1712 | 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k', | |
1713 | 'info_dict': { | |
1714 | 'id': 'x41yOUIvK2k', | |
1715 | 'ext': 'mp4', | |
1716 | 'title': 'IMG 3456', | |
1717 | 'description': '', | |
1718 | 'upload_date': '20170613', | |
1719 | 'uploader_id': 'ElevageOrVert', | |
1720 | 'uploader': 'ElevageOrVert', | |
1721 | }, | |
1722 | 'params': { | |
1723 | 'skip_download': True, | |
1724 | }, | |
1725 | }, | |
1726 | { | |
1727 | # with '};' inside yt initial data (see [1]) | |
1728 | # see [2] for an example with '};' inside ytInitialPlayerResponse | |
1729 | # 1. https://github.com/ytdl-org/youtube-dl/issues/27093 | |
1730 | # 2. https://github.com/ytdl-org/youtube-dl/issues/27216 | |
1731 | 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no', | |
1732 | 'info_dict': { | |
1733 | 'id': 'CHqg6qOn4no', | |
1734 | 'ext': 'mp4', | |
1735 | 'title': 'Part 77 Sort a list of simple types in c#', | |
1736 | 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc', | |
1737 | 'upload_date': '20130831', | |
1738 | 'uploader_id': 'kudvenkat', | |
1739 | 'uploader': 'kudvenkat', | |
1740 | }, | |
1741 | 'params': { | |
1742 | 'skip_download': True, | |
1743 | }, | |
1744 | }, | |
1745 | { | |
1746 | # another example of '};' in ytInitialData | |
1747 | 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY', | |
1748 | 'only_matching': True, | |
1749 | }, | |
1750 | { | |
1751 | 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ', | |
1752 | 'only_matching': True, | |
1753 | }, | |
1754 | { | |
1755 | # https://github.com/ytdl-org/youtube-dl/pull/28094 | |
1756 | 'url': 'OtqTfy26tG0', | |
1757 | 'info_dict': { | |
1758 | 'id': 'OtqTfy26tG0', | |
1759 | 'ext': 'mp4', | |
1760 | 'title': 'Burn Out', | |
1761 | 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131', | |
1762 | 'upload_date': '20141120', | |
1763 | 'uploader': 'The Cinematic Orchestra - Topic', | |
1764 | 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw', | |
1765 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw', | |
1766 | 'artist': 'The Cinematic Orchestra', | |
1767 | 'track': 'Burn Out', | |
1768 | 'album': 'Every Day', | |
1769 | 'release_data': None, | |
1770 | 'release_year': None, | |
1771 | }, | |
1772 | 'params': { | |
1773 | 'skip_download': True, | |
1774 | }, | |
1775 | }, | |
1776 | { | |
1777 | # controversial video, only works with bpctr when authenticated with cookies | |
1778 | 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg', | |
1779 | 'only_matching': True, | |
1780 | }, | |
1781 | { | |
1782 | # controversial video, requires bpctr/contentCheckOk | |
1783 | 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc', | |
1784 | 'info_dict': { | |
1785 | 'id': 'SZJvDhaSDnc', | |
1786 | 'ext': 'mp4', | |
1787 | 'title': 'San Diego teen commits suicide after bullying over embarrassing video', | |
1788 | 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ', | |
1789 | 'uploader': 'CBS This Morning', | |
1790 | 'uploader_id': 'CBSThisMorning', | |
1791 | 'upload_date': '20140716', | |
1792 | 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7' | |
1793 | } | |
1794 | }, | |
1795 | { | |
1796 | # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685 | |
1797 | 'url': 'cBvYw8_A0vQ', | |
1798 | 'info_dict': { | |
1799 | 'id': 'cBvYw8_A0vQ', | |
1800 | 'ext': 'mp4', | |
1801 | 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き', | |
1802 | 'description': 'md5:ea770e474b7cd6722b4c95b833c03630', | |
1803 | 'upload_date': '20201120', | |
1804 | 'uploader': 'Walk around Japan', | |
1805 | 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw', | |
1806 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw', | |
1807 | }, | |
1808 | 'params': { | |
1809 | 'skip_download': True, | |
1810 | }, | |
1811 | }, { | |
1812 | # Has multiple audio streams | |
1813 | 'url': 'WaOKSUlf4TM', | |
1814 | 'only_matching': True | |
1815 | }, { | |
1816 | # Requires Premium: has format 141 when requested using YTM url | |
1817 | 'url': 'https://music.youtube.com/watch?v=XclachpHxis', | |
1818 | 'only_matching': True | |
1819 | }, { | |
1820 | # multiple subtitles with same lang_code | |
1821 | 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug', | |
1822 | 'only_matching': True, | |
1823 | }, { | |
1824 | # Force use android client fallback | |
1825 | 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY', | |
1826 | 'info_dict': { | |
1827 | 'id': 'YOelRv7fMxY', | |
1828 | 'title': 'DIGGING A SECRET TUNNEL Part 1', | |
1829 | 'ext': '3gp', | |
1830 | 'upload_date': '20210624', | |
1831 | 'channel_id': 'UCp68_FLety0O-n9QU6phsgw', | |
1832 | 'uploader': 'colinfurze', | |
1833 | 'uploader_id': 'colinfurze', | |
1834 | 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw', | |
1835 | 'description': 'md5:b5096f56af7ccd7a555c84db81738b22' | |
1836 | }, | |
1837 | 'params': { | |
1838 | 'format': '17', # 3gp format available on android | |
1839 | 'extractor_args': {'youtube': {'player_client': ['android']}}, | |
1840 | }, | |
1841 | }, | |
1842 | { | |
1843 | # Skip download of additional client configs (remix client config in this case) | |
1844 | 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs', | |
1845 | 'only_matching': True, | |
1846 | 'params': { | |
1847 | 'extractor_args': {'youtube': {'player_skip': ['configs']}}, | |
1848 | }, | |
1849 | }, { | |
1850 | # shorts | |
1851 | 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY', | |
1852 | 'only_matching': True, | |
1853 | }, | |
1854 | ] | |
1855 | ||
1856 | @classmethod | |
1857 | def suitable(cls, url): | |
1858 | from ..utils import parse_qs | |
1859 | ||
1860 | qs = parse_qs(url) | |
1861 | if qs.get('list', [None])[0]: | |
1862 | return False | |
1863 | return super(YoutubeIE, cls).suitable(url) | |
1864 | ||
1865 | def __init__(self, *args, **kwargs): | |
1866 | super(YoutubeIE, self).__init__(*args, **kwargs) | |
1867 | self._code_cache = {} | |
1868 | self._player_cache = {} | |
1869 | ||
1870 | def _extract_player_url(self, *ytcfgs, webpage=None): | |
1871 | player_url = traverse_obj( | |
1872 | ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'), | |
1873 | get_all=False, expected_type=compat_str) | |
1874 | if not player_url: | |
1875 | return | |
1876 | if player_url.startswith('//'): | |
1877 | player_url = 'https:' + player_url | |
1878 | elif not re.match(r'https?://', player_url): | |
1879 | player_url = compat_urlparse.urljoin( | |
1880 | 'https://www.youtube.com', player_url) | |
1881 | return player_url | |
1882 | ||
1883 | def _download_player_url(self, video_id, fatal=False): | |
1884 | res = self._download_webpage( | |
1885 | 'https://www.youtube.com/iframe_api', | |
1886 | note='Downloading iframe API JS', video_id=video_id, fatal=fatal) | |
1887 | if res: | |
1888 | player_version = self._search_regex( | |
1889 | r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal) | |
1890 | if player_version: | |
1891 | return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js' | |
1892 | ||
1893 | def _signature_cache_id(self, example_sig): | |
1894 | """ Return a string representation of a signature """ | |
1895 | return '.'.join(compat_str(len(part)) for part in example_sig.split('.')) | |
1896 | ||
1897 | @classmethod | |
1898 | def _extract_player_info(cls, player_url): | |
1899 | for player_re in cls._PLAYER_INFO_RE: | |
1900 | id_m = re.search(player_re, player_url) | |
1901 | if id_m: | |
1902 | break | |
1903 | else: | |
1904 | raise ExtractorError('Cannot identify player %r' % player_url) | |
1905 | return id_m.group('id') | |
1906 | ||
1907 | def _load_player(self, video_id, player_url, fatal=True) -> bool: | |
1908 | player_id = self._extract_player_info(player_url) | |
1909 | if player_id not in self._code_cache: | |
1910 | self._code_cache[player_id] = self._download_webpage( | |
1911 | player_url, video_id, fatal=fatal, | |
1912 | note='Downloading player ' + player_id, | |
1913 | errnote='Download of %s failed' % player_url) | |
1914 | return player_id in self._code_cache | |
1915 | ||
1916 | def _extract_signature_function(self, video_id, player_url, example_sig): | |
1917 | player_id = self._extract_player_info(player_url) | |
1918 | ||
1919 | # Read from filesystem cache | |
1920 | func_id = 'js_%s_%s' % ( | |
1921 | player_id, self._signature_cache_id(example_sig)) | |
1922 | assert os.path.basename(func_id) == func_id | |
1923 | ||
1924 | cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id) | |
1925 | if cache_spec is not None: | |
1926 | return lambda s: ''.join(s[i] for i in cache_spec) | |
1927 | ||
1928 | if self._load_player(video_id, player_url): | |
1929 | code = self._code_cache[player_id] | |
1930 | res = self._parse_sig_js(code) | |
1931 | ||
1932 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) | |
1933 | cache_res = res(test_string) | |
1934 | cache_spec = [ord(c) for c in cache_res] | |
1935 | ||
1936 | self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec) | |
1937 | return res | |
1938 | ||
1939 | def _print_sig_code(self, func, example_sig): | |
1940 | def gen_sig_code(idxs): | |
1941 | def _genslice(start, end, step): | |
1942 | starts = '' if start == 0 else str(start) | |
1943 | ends = (':%d' % (end + step)) if end + step >= 0 else ':' | |
1944 | steps = '' if step == 1 else (':%d' % step) | |
1945 | return 's[%s%s%s]' % (starts, ends, steps) | |
1946 | ||
1947 | step = None | |
1948 | # Quelch pyflakes warnings - start will be set when step is set | |
1949 | start = '(Never used)' | |
1950 | for i, prev in zip(idxs[1:], idxs[:-1]): | |
1951 | if step is not None: | |
1952 | if i - prev == step: | |
1953 | continue | |
1954 | yield _genslice(start, prev, step) | |
1955 | step = None | |
1956 | continue | |
1957 | if i - prev in [-1, 1]: | |
1958 | step = i - prev | |
1959 | start = prev | |
1960 | continue | |
1961 | else: | |
1962 | yield 's[%d]' % prev | |
1963 | if step is None: | |
1964 | yield 's[%d]' % i | |
1965 | else: | |
1966 | yield _genslice(start, i, step) | |
1967 | ||
1968 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) | |
1969 | cache_res = func(test_string) | |
1970 | cache_spec = [ord(c) for c in cache_res] | |
1971 | expr_code = ' + '.join(gen_sig_code(cache_spec)) | |
1972 | signature_id_tuple = '(%s)' % ( | |
1973 | ', '.join(compat_str(len(p)) for p in example_sig.split('.'))) | |
1974 | code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n' | |
1975 | ' return %s\n') % (signature_id_tuple, expr_code) | |
1976 | self.to_screen('Extracted signature function:\n' + code) | |
1977 | ||
1978 | def _parse_sig_js(self, jscode): | |
1979 | funcname = self._search_regex( | |
1980 | (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1981 | r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1982 | r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)', | |
1983 | r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)', | |
1984 | 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}\(a,\d+\)', | |
1985 | 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\(\s*""\s*\)', | |
1986 | r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)', | |
1987 | # Obsolete patterns | |
1988 | r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1989 | r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(', | |
1990 | r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1991 | r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1992 | r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1993 | r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1994 | r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1995 | r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('), | |
1996 | jscode, 'Initial JS player signature function name', group='sig') | |
1997 | ||
1998 | jsi = JSInterpreter(jscode) | |
1999 | initial_function = jsi.extract_function(funcname) | |
2000 | return lambda s: initial_function([s]) | |
2001 | ||
2002 | def _decrypt_signature(self, s, video_id, player_url): | |
2003 | """Turn the encrypted s field into a working signature""" | |
2004 | ||
2005 | if player_url is None: | |
2006 | raise ExtractorError('Cannot decrypt signature without player_url') | |
2007 | ||
2008 | try: | |
2009 | player_id = (player_url, self._signature_cache_id(s)) | |
2010 | if player_id not in self._player_cache: | |
2011 | func = self._extract_signature_function( | |
2012 | video_id, player_url, s | |
2013 | ) | |
2014 | self._player_cache[player_id] = func | |
2015 | func = self._player_cache[player_id] | |
2016 | if self.get_param('youtube_print_sig_code'): | |
2017 | self._print_sig_code(func, s) | |
2018 | return func(s) | |
2019 | except Exception as e: | |
2020 | tb = traceback.format_exc() | |
2021 | raise ExtractorError( | |
2022 | 'Signature extraction failed: ' + tb, cause=e) | |
2023 | ||
2024 | def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False): | |
2025 | """ | |
2026 | Extract signatureTimestamp (sts) | |
2027 | Required to tell API what sig/player version is in use. | |
2028 | """ | |
2029 | sts = None | |
2030 | if isinstance(ytcfg, dict): | |
2031 | sts = int_or_none(ytcfg.get('STS')) | |
2032 | ||
2033 | if not sts: | |
2034 | # Attempt to extract from player | |
2035 | if player_url is None: | |
2036 | error_msg = 'Cannot extract signature timestamp without player_url.' | |
2037 | if fatal: | |
2038 | raise ExtractorError(error_msg) | |
2039 | self.report_warning(error_msg) | |
2040 | return | |
2041 | if self._load_player(video_id, player_url, fatal=fatal): | |
2042 | player_id = self._extract_player_info(player_url) | |
2043 | code = self._code_cache[player_id] | |
2044 | sts = int_or_none(self._search_regex( | |
2045 | r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code, | |
2046 | 'JS player signature timestamp', group='sts', fatal=fatal)) | |
2047 | return sts | |
2048 | ||
2049 | def _mark_watched(self, video_id, player_responses): | |
2050 | playback_url = traverse_obj( | |
2051 | player_responses, (..., 'playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'), | |
2052 | expected_type=url_or_none, get_all=False) | |
2053 | if not playback_url: | |
2054 | self.report_warning('Unable to mark watched') | |
2055 | return | |
2056 | parsed_playback_url = compat_urlparse.urlparse(playback_url) | |
2057 | qs = compat_urlparse.parse_qs(parsed_playback_url.query) | |
2058 | ||
2059 | # cpn generation algorithm is reverse engineered from base.js. | |
2060 | # In fact it works even with dummy cpn. | |
2061 | CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_' | |
2062 | cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))) | |
2063 | ||
2064 | qs.update({ | |
2065 | 'ver': ['2'], | |
2066 | 'cpn': [cpn], | |
2067 | }) | |
2068 | playback_url = compat_urlparse.urlunparse( | |
2069 | parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True))) | |
2070 | ||
2071 | self._download_webpage( | |
2072 | playback_url, video_id, 'Marking watched', | |
2073 | 'Unable to mark watched', fatal=False) | |
2074 | ||
2075 | @staticmethod | |
2076 | def _extract_urls(webpage): | |
2077 | # Embedded YouTube player | |
2078 | entries = [ | |
2079 | unescapeHTML(mobj.group('url')) | |
2080 | for mobj in re.finditer(r'''(?x) | |
2081 | (?: | |
2082 | <iframe[^>]+?src=| | |
2083 | data-video-url=| | |
2084 | <embed[^>]+?src=| | |
2085 | embedSWF\(?:\s*| | |
2086 | <object[^>]+data=| | |
2087 | new\s+SWFObject\( | |
2088 | ) | |
2089 | (["\']) | |
2090 | (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/ | |
2091 | (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?) | |
2092 | \1''', webpage)] | |
2093 | ||
2094 | # lazyYT YouTube embed | |
2095 | entries.extend(list(map( | |
2096 | unescapeHTML, | |
2097 | re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)))) | |
2098 | ||
2099 | # Wordpress "YouTube Video Importer" plugin | |
2100 | matches = re.findall(r'''(?x)<div[^>]+ | |
2101 | class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+ | |
2102 | data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage) | |
2103 | entries.extend(m[-1] for m in matches) | |
2104 | ||
2105 | return entries | |
2106 | ||
2107 | @staticmethod | |
2108 | def _extract_url(webpage): | |
2109 | urls = YoutubeIE._extract_urls(webpage) | |
2110 | return urls[0] if urls else None | |
2111 | ||
2112 | @classmethod | |
2113 | def extract_id(cls, url): | |
2114 | mobj = re.match(cls._VALID_URL, url, re.VERBOSE) | |
2115 | if mobj is None: | |
2116 | raise ExtractorError('Invalid URL: %s' % url) | |
2117 | return mobj.group('id') | |
2118 | ||
2119 | def _extract_chapters_from_json(self, data, duration): | |
2120 | chapter_list = traverse_obj( | |
2121 | data, ( | |
2122 | 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer', | |
2123 | 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters' | |
2124 | ), expected_type=list) | |
2125 | ||
2126 | return self._extract_chapters( | |
2127 | chapter_list, | |
2128 | chapter_time=lambda chapter: float_or_none( | |
2129 | traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000), | |
2130 | chapter_title=lambda chapter: traverse_obj( | |
2131 | chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str), | |
2132 | duration=duration) | |
2133 | ||
2134 | def _extract_chapters_from_engagement_panel(self, data, duration): | |
2135 | content_list = traverse_obj( | |
2136 | data, | |
2137 | ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'), | |
2138 | expected_type=list, default=[]) | |
2139 | chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription')) | |
2140 | chapter_title = lambda chapter: self._get_text(chapter, 'title') | |
2141 | ||
2142 | return next(( | |
2143 | filter(None, ( | |
2144 | self._extract_chapters( | |
2145 | traverse_obj(contents, (..., 'macroMarkersListItemRenderer')), | |
2146 | chapter_time, chapter_title, duration) | |
2147 | for contents in content_list | |
2148 | ))), []) | |
2149 | ||
2150 | def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration): | |
2151 | chapters = [] | |
2152 | last_chapter = {'start_time': 0} | |
2153 | for idx, chapter in enumerate(chapter_list or []): | |
2154 | title = chapter_title(chapter) | |
2155 | start_time = chapter_time(chapter) | |
2156 | if start_time is None: | |
2157 | continue | |
2158 | last_chapter['end_time'] = start_time | |
2159 | if start_time < last_chapter['start_time']: | |
2160 | if idx == 1: | |
2161 | chapters.pop() | |
2162 | self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title']) | |
2163 | else: | |
2164 | self.report_warning(f'Invalid start time for chapter "{title}"') | |
2165 | continue | |
2166 | last_chapter = {'start_time': start_time, 'title': title} | |
2167 | chapters.append(last_chapter) | |
2168 | last_chapter['end_time'] = duration | |
2169 | return chapters | |
2170 | ||
2171 | def _extract_yt_initial_variable(self, webpage, regex, video_id, name): | |
2172 | return self._parse_json(self._search_regex( | |
2173 | (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE), | |
2174 | regex), webpage, name, default='{}'), video_id, fatal=False) | |
2175 | ||
2176 | @staticmethod | |
2177 | def parse_time_text(time_text): | |
2178 | """ | |
2179 | Parse the comment time text | |
2180 | time_text is in the format 'X units ago (edited)' | |
2181 | """ | |
2182 | time_text_split = time_text.split(' ') | |
2183 | if len(time_text_split) >= 3: | |
2184 | try: | |
2185 | return datetime_from_str('now-%s%s' % (time_text_split[0], time_text_split[1]), precision='auto') | |
2186 | except ValueError: | |
2187 | return None | |
2188 | ||
2189 | def _extract_comment(self, comment_renderer, parent=None): | |
2190 | comment_id = comment_renderer.get('commentId') | |
2191 | if not comment_id: | |
2192 | return | |
2193 | ||
2194 | text = self._get_text(comment_renderer, 'contentText') | |
2195 | ||
2196 | # note: timestamp is an estimate calculated from the current time and time_text | |
2197 | time_text = self._get_text(comment_renderer, 'publishedTimeText') or '' | |
2198 | time_text_dt = self.parse_time_text(time_text) | |
2199 | if isinstance(time_text_dt, datetime.datetime): | |
2200 | timestamp = calendar.timegm(time_text_dt.timetuple()) | |
2201 | author = self._get_text(comment_renderer, 'authorText') | |
2202 | author_id = try_get(comment_renderer, | |
2203 | lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str) | |
2204 | ||
2205 | votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'], | |
2206 | lambda x: x['likeCount']), compat_str)) or 0 | |
2207 | author_thumbnail = try_get(comment_renderer, | |
2208 | lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str) | |
2209 | ||
2210 | author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool) | |
2211 | is_favorited = 'creatorHeart' in (try_get( | |
2212 | comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {}) | |
2213 | return { | |
2214 | 'id': comment_id, | |
2215 | 'text': text, | |
2216 | 'timestamp': timestamp, | |
2217 | 'time_text': time_text, | |
2218 | 'like_count': votes, | |
2219 | 'is_favorited': is_favorited, | |
2220 | 'author': author, | |
2221 | 'author_id': author_id, | |
2222 | 'author_thumbnail': author_thumbnail, | |
2223 | 'author_is_uploader': author_is_uploader, | |
2224 | 'parent': parent or 'root' | |
2225 | } | |
2226 | ||
2227 | def _comment_entries(self, root_continuation_data, identity_token, account_syncid, | |
2228 | ytcfg, video_id, parent=None, comment_counts=None): | |
2229 | ||
2230 | def extract_header(contents): | |
2231 | _total_comments = 0 | |
2232 | _continuation = None | |
2233 | for content in contents: | |
2234 | comments_header_renderer = try_get(content, lambda x: x['commentsHeaderRenderer']) | |
2235 | expected_comment_count = parse_count(self._get_text( | |
2236 | comments_header_renderer, 'countText', 'commentsCount', max_runs=1)) | |
2237 | ||
2238 | if expected_comment_count: | |
2239 | comment_counts[1] = expected_comment_count | |
2240 | self.to_screen('Downloading ~%d comments' % expected_comment_count) | |
2241 | _total_comments = comment_counts[1] | |
2242 | sort_mode_str = self._configuration_arg('comment_sort', [''])[0] | |
2243 | comment_sort_index = int(sort_mode_str != 'top') # 1 = new, 0 = top | |
2244 | ||
2245 | sort_menu_item = try_get( | |
2246 | comments_header_renderer, | |
2247 | lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {} | |
2248 | sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {} | |
2249 | ||
2250 | _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item) | |
2251 | if not _continuation: | |
2252 | continue | |
2253 | ||
2254 | sort_text = sort_menu_item.get('title') | |
2255 | if isinstance(sort_text, compat_str): | |
2256 | sort_text = sort_text.lower() | |
2257 | else: | |
2258 | sort_text = 'top comments' if comment_sort_index == 0 else 'newest first' | |
2259 | self.to_screen('Sorting comments by %s' % sort_text) | |
2260 | break | |
2261 | return _total_comments, _continuation | |
2262 | ||
2263 | def extract_thread(contents): | |
2264 | if not parent: | |
2265 | comment_counts[2] = 0 | |
2266 | for content in contents: | |
2267 | comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer']) | |
2268 | comment_renderer = try_get( | |
2269 | comment_thread_renderer, (lambda x: x['comment']['commentRenderer'], dict)) or try_get( | |
2270 | content, (lambda x: x['commentRenderer'], dict)) | |
2271 | ||
2272 | if not comment_renderer: | |
2273 | continue | |
2274 | comment = self._extract_comment(comment_renderer, parent) | |
2275 | if not comment: | |
2276 | continue | |
2277 | comment_counts[0] += 1 | |
2278 | yield comment | |
2279 | # Attempt to get the replies | |
2280 | comment_replies_renderer = try_get( | |
2281 | comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict) | |
2282 | ||
2283 | if comment_replies_renderer: | |
2284 | comment_counts[2] += 1 | |
2285 | comment_entries_iter = self._comment_entries( | |
2286 | comment_replies_renderer, identity_token, account_syncid, ytcfg, | |
2287 | video_id, parent=comment.get('id'), comment_counts=comment_counts) | |
2288 | ||
2289 | for reply_comment in comment_entries_iter: | |
2290 | yield reply_comment | |
2291 | ||
2292 | # YouTube comments have a max depth of 2 | |
2293 | max_depth = int_or_none(self._configuration_arg('max_comment_depth', [''])[0]) or float('inf') | |
2294 | if max_depth == 1 and parent: | |
2295 | return | |
2296 | if not comment_counts: | |
2297 | # comment so far, est. total comments, current comment thread # | |
2298 | comment_counts = [0, 0, 0] | |
2299 | ||
2300 | continuation = self._extract_continuation(root_continuation_data) | |
2301 | if continuation and len(continuation['continuation']) < 27: | |
2302 | self.write_debug('Detected old API continuation token. Generating new API compatible token.') | |
2303 | continuation_token = self._generate_comment_continuation(video_id) | |
2304 | continuation = self._build_api_continuation_query(continuation_token, None) | |
2305 | ||
2306 | visitor_data = None | |
2307 | is_first_continuation = parent is None | |
2308 | ||
2309 | for page_num in itertools.count(0): | |
2310 | if not continuation: | |
2311 | break | |
2312 | headers = self.generate_api_headers(ytcfg, identity_token, account_syncid, visitor_data) | |
2313 | comment_prog_str = '(%d/%d)' % (comment_counts[0], comment_counts[1]) | |
2314 | if page_num == 0: | |
2315 | if is_first_continuation: | |
2316 | note_prefix = 'Downloading comment section API JSON' | |
2317 | else: | |
2318 | note_prefix = ' Downloading comment API JSON reply thread %d %s' % ( | |
2319 | comment_counts[2], comment_prog_str) | |
2320 | else: | |
2321 | note_prefix = '%sDownloading comment%s API JSON page %d %s' % ( | |
2322 | ' ' if parent else '', ' replies' if parent else '', | |
2323 | page_num, comment_prog_str) | |
2324 | ||
2325 | response = self._extract_response( | |
2326 | item_id=None, query=continuation, | |
2327 | ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix, | |
2328 | check_get_keys=('onResponseReceivedEndpoints', 'continuationContents')) | |
2329 | if not response: | |
2330 | break | |
2331 | visitor_data = try_get( | |
2332 | response, | |
2333 | lambda x: x['responseContext']['webResponseContextExtensionData']['ytConfigData']['visitorData'], | |
2334 | compat_str) or visitor_data | |
2335 | ||
2336 | continuation_contents = dict_get(response, ('onResponseReceivedEndpoints', 'continuationContents')) | |
2337 | ||
2338 | continuation = None | |
2339 | if isinstance(continuation_contents, list): | |
2340 | for continuation_section in continuation_contents: | |
2341 | if not isinstance(continuation_section, dict): | |
2342 | continue | |
2343 | continuation_items = try_get( | |
2344 | continuation_section, | |
2345 | (lambda x: x['reloadContinuationItemsCommand']['continuationItems'], | |
2346 | lambda x: x['appendContinuationItemsAction']['continuationItems']), | |
2347 | list) or [] | |
2348 | if is_first_continuation: | |
2349 | total_comments, continuation = extract_header(continuation_items) | |
2350 | if total_comments: | |
2351 | yield total_comments | |
2352 | is_first_continuation = False | |
2353 | if continuation: | |
2354 | break | |
2355 | continue | |
2356 | count = 0 | |
2357 | for count, entry in enumerate(extract_thread(continuation_items)): | |
2358 | yield entry | |
2359 | continuation = self._extract_continuation({'contents': continuation_items}) | |
2360 | if continuation: | |
2361 | # Sometimes YouTube provides a continuation without any comments | |
2362 | # In most cases we end up just downloading these with very little comments to come. | |
2363 | if count == 0: | |
2364 | if not parent: | |
2365 | self.report_warning('No comments received - assuming end of comments') | |
2366 | continuation = None | |
2367 | break | |
2368 | ||
2369 | # Deprecated response structure | |
2370 | elif isinstance(continuation_contents, dict): | |
2371 | known_continuation_renderers = ('itemSectionContinuation', 'commentRepliesContinuation') | |
2372 | for key, continuation_renderer in continuation_contents.items(): | |
2373 | if key not in known_continuation_renderers: | |
2374 | continue | |
2375 | if not isinstance(continuation_renderer, dict): | |
2376 | continue | |
2377 | if is_first_continuation: | |
2378 | header_continuation_items = [continuation_renderer.get('header') or {}] | |
2379 | total_comments, continuation = extract_header(header_continuation_items) | |
2380 | if total_comments: | |
2381 | yield total_comments | |
2382 | is_first_continuation = False | |
2383 | if continuation: | |
2384 | break | |
2385 | ||
2386 | # Sometimes YouTube provides a continuation without any comments | |
2387 | # In most cases we end up just downloading these with very little comments to come. | |
2388 | count = 0 | |
2389 | for count, entry in enumerate(extract_thread(continuation_renderer.get('contents') or {})): | |
2390 | yield entry | |
2391 | continuation = self._extract_continuation(continuation_renderer) | |
2392 | if count == 0: | |
2393 | if not parent: | |
2394 | self.report_warning('No comments received - assuming end of comments') | |
2395 | continuation = None | |
2396 | break | |
2397 | ||
2398 | @staticmethod | |
2399 | def _generate_comment_continuation(video_id): | |
2400 | """ | |
2401 | Generates initial comment section continuation token from given video id | |
2402 | """ | |
2403 | b64_vid_id = base64.b64encode(bytes(video_id.encode('utf-8'))) | |
2404 | parts = ('Eg0SCw==', b64_vid_id, 'GAYyJyIRIgs=', b64_vid_id, 'MAB4AjAAQhBjb21tZW50cy1zZWN0aW9u') | |
2405 | new_continuation_intlist = list(itertools.chain.from_iterable( | |
2406 | [bytes_to_intlist(base64.b64decode(part)) for part in parts])) | |
2407 | return base64.b64encode(intlist_to_bytes(new_continuation_intlist)).decode('utf-8') | |
2408 | ||
2409 | def _extract_comments(self, ytcfg, video_id, contents, webpage): | |
2410 | """Entry for comment extraction""" | |
2411 | def _real_comment_extract(contents): | |
2412 | if isinstance(contents, list): | |
2413 | for entry in contents: | |
2414 | for key, renderer in entry.items(): | |
2415 | if key not in known_entry_comment_renderers: | |
2416 | continue | |
2417 | yield from self._comment_entries( | |
2418 | renderer, video_id=video_id, ytcfg=ytcfg, | |
2419 | identity_token=self._extract_identity_token(webpage, item_id=video_id), | |
2420 | account_syncid=self._extract_account_syncid(ytcfg)) | |
2421 | break | |
2422 | comments = [] | |
2423 | known_entry_comment_renderers = ('itemSectionRenderer',) | |
2424 | estimated_total = 0 | |
2425 | max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0]) or float('inf') | |
2426 | # Force English regardless of account setting to prevent parsing issues | |
2427 | # See: https://github.com/yt-dlp/yt-dlp/issues/532 | |
2428 | ytcfg = copy.deepcopy(ytcfg) | |
2429 | traverse_obj( | |
2430 | ytcfg, ('INNERTUBE_CONTEXT', 'client'), expected_type=dict, default={})['hl'] = 'en' | |
2431 | try: | |
2432 | for comment in _real_comment_extract(contents): | |
2433 | if len(comments) >= max_comments: | |
2434 | break | |
2435 | if isinstance(comment, int): | |
2436 | estimated_total = comment | |
2437 | continue | |
2438 | comments.append(comment) | |
2439 | except KeyboardInterrupt: | |
2440 | self.to_screen('Interrupted by user') | |
2441 | self.to_screen('Downloaded %d/%d comments' % (len(comments), estimated_total)) | |
2442 | return { | |
2443 | 'comments': comments, | |
2444 | 'comment_count': len(comments), | |
2445 | } | |
2446 | ||
2447 | @staticmethod | |
2448 | def _generate_player_context(sts=None): | |
2449 | context = { | |
2450 | 'html5Preference': 'HTML5_PREF_WANTS', | |
2451 | } | |
2452 | if sts is not None: | |
2453 | context['signatureTimestamp'] = sts | |
2454 | return { | |
2455 | 'playbackContext': { | |
2456 | 'contentPlaybackContext': context | |
2457 | }, | |
2458 | 'contentCheckOk': True, | |
2459 | 'racyCheckOk': True | |
2460 | } | |
2461 | ||
2462 | @staticmethod | |
2463 | def _is_agegated(player_response): | |
2464 | if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')): | |
2465 | return True | |
2466 | ||
2467 | reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[]) | |
2468 | AGE_GATE_REASONS = ( | |
2469 | 'confirm your age', 'age-restricted', 'inappropriate', # reason | |
2470 | 'age_verification_required', 'age_check_required', # status | |
2471 | ) | |
2472 | return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons) | |
2473 | ||
2474 | @staticmethod | |
2475 | def _is_unplayable(player_response): | |
2476 | return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE' | |
2477 | ||
2478 | def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, identity_token, player_url, initial_pr): | |
2479 | ||
2480 | session_index = self._extract_session_index(player_ytcfg, master_ytcfg) | |
2481 | syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr) | |
2482 | sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None | |
2483 | headers = self.generate_api_headers( | |
2484 | player_ytcfg, identity_token, syncid, | |
2485 | default_client=client, session_index=session_index) | |
2486 | ||
2487 | yt_query = {'videoId': video_id} | |
2488 | yt_query.update(self._generate_player_context(sts)) | |
2489 | return self._extract_response( | |
2490 | item_id=video_id, ep='player', query=yt_query, | |
2491 | ytcfg=player_ytcfg, headers=headers, fatal=True, | |
2492 | default_client=client, | |
2493 | note='Downloading %s player API JSON' % client.replace('_', ' ').strip() | |
2494 | ) or None | |
2495 | ||
2496 | def _get_requested_clients(self, url, smuggled_data): | |
2497 | requested_clients = [] | |
2498 | allowed_clients = sorted( | |
2499 | [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'], | |
2500 | key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True) | |
2501 | for client in self._configuration_arg('player_client'): | |
2502 | if client in allowed_clients: | |
2503 | requested_clients.append(client) | |
2504 | elif client == 'all': | |
2505 | requested_clients.extend(allowed_clients) | |
2506 | else: | |
2507 | self.report_warning(f'Skipping unsupported client {client}') | |
2508 | if not requested_clients: | |
2509 | requested_clients = ['android', 'web'] | |
2510 | ||
2511 | if smuggled_data.get('is_music_url') or self.is_music_url(url): | |
2512 | requested_clients.extend( | |
2513 | f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS) | |
2514 | ||
2515 | return orderedSet(requested_clients) | |
2516 | ||
2517 | def _extract_player_ytcfg(self, client, video_id): | |
2518 | url = { | |
2519 | 'web_music': 'https://music.youtube.com', | |
2520 | 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1' | |
2521 | }.get(client) | |
2522 | if not url: | |
2523 | return {} | |
2524 | webpage = self._download_webpage(url, video_id, fatal=False, note=f'Downloading {client} config') | |
2525 | return self.extract_ytcfg(video_id, webpage) or {} | |
2526 | ||
2527 | def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, identity_token): | |
2528 | initial_pr = None | |
2529 | if webpage: | |
2530 | initial_pr = self._extract_yt_initial_variable( | |
2531 | webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE, | |
2532 | video_id, 'initial player response') | |
2533 | ||
2534 | original_clients = clients | |
2535 | clients = clients[::-1] | |
2536 | prs = [] | |
2537 | ||
2538 | def append_client(client_name): | |
2539 | if client_name in INNERTUBE_CLIENTS and client_name not in original_clients: | |
2540 | clients.append(client_name) | |
2541 | ||
2542 | # Android player_response does not have microFormats which are needed for | |
2543 | # extraction of some data. So we return the initial_pr with formats | |
2544 | # stripped out even if not requested by the user | |
2545 | # See: https://github.com/yt-dlp/yt-dlp/issues/501 | |
2546 | if initial_pr: | |
2547 | pr = dict(initial_pr) | |
2548 | pr['streamingData'] = None | |
2549 | prs.append(pr) | |
2550 | ||
2551 | last_error = None | |
2552 | tried_iframe_fallback = False | |
2553 | player_url = None | |
2554 | while clients: | |
2555 | client = clients.pop() | |
2556 | player_ytcfg = master_ytcfg if client == 'web' else {} | |
2557 | if 'configs' not in self._configuration_arg('player_skip'): | |
2558 | player_ytcfg = self._extract_player_ytcfg(client, video_id) or player_ytcfg | |
2559 | ||
2560 | player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage) | |
2561 | require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER') | |
2562 | if 'js' in self._configuration_arg('player_skip'): | |
2563 | require_js_player = False | |
2564 | player_url = None | |
2565 | ||
2566 | if not player_url and not tried_iframe_fallback and require_js_player: | |
2567 | player_url = self._download_player_url(video_id) | |
2568 | tried_iframe_fallback = True | |
2569 | ||
2570 | try: | |
2571 | pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response( | |
2572 | client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, identity_token, player_url if require_js_player else None, initial_pr) | |
2573 | except ExtractorError as e: | |
2574 | if last_error: | |
2575 | self.report_warning(last_error) | |
2576 | last_error = e | |
2577 | continue | |
2578 | ||
2579 | if pr: | |
2580 | prs.append(pr) | |
2581 | ||
2582 | # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in | |
2583 | if client.endswith('_agegate') and self._is_unplayable(pr) and self._generate_sapisidhash_header(): | |
2584 | append_client(client.replace('_agegate', '_creator')) | |
2585 | elif self._is_agegated(pr): | |
2586 | append_client(f'{client}_agegate') | |
2587 | ||
2588 | if last_error: | |
2589 | if not len(prs): | |
2590 | raise last_error | |
2591 | self.report_warning(last_error) | |
2592 | return prs, player_url | |
2593 | ||
2594 | def _extract_formats(self, streaming_data, video_id, player_url, is_live): | |
2595 | itags, stream_ids = [], [] | |
2596 | itag_qualities, res_qualities = {}, {} | |
2597 | q = qualities([ | |
2598 | # Normally tiny is the smallest video-only formats. But | |
2599 | # audio-only formats with unknown quality may get tagged as tiny | |
2600 | 'tiny', | |
2601 | 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats | |
2602 | 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres' | |
2603 | ]) | |
2604 | streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[]) | |
2605 | ||
2606 | for fmt in streaming_formats: | |
2607 | if fmt.get('targetDurationSec') or fmt.get('drmFamilies'): | |
2608 | continue | |
2609 | ||
2610 | itag = str_or_none(fmt.get('itag')) | |
2611 | audio_track = fmt.get('audioTrack') or {} | |
2612 | stream_id = '%s.%s' % (itag or '', audio_track.get('id', '')) | |
2613 | if stream_id in stream_ids: | |
2614 | continue | |
2615 | ||
2616 | quality = fmt.get('quality') | |
2617 | height = int_or_none(fmt.get('height')) | |
2618 | if quality == 'tiny' or not quality: | |
2619 | quality = fmt.get('audioQuality', '').lower() or quality | |
2620 | # The 3gp format (17) in android client has a quality of "small", | |
2621 | # but is actually worse than other formats | |
2622 | if itag == '17': | |
2623 | quality = 'tiny' | |
2624 | if quality: | |
2625 | if itag: | |
2626 | itag_qualities[itag] = quality | |
2627 | if height: | |
2628 | res_qualities[height] = quality | |
2629 | # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment | |
2630 | # (adding `&sq=0` to the URL) and parsing emsg box to determine the | |
2631 | # number of fragment that would subsequently requested with (`&sq=N`) | |
2632 | if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF': | |
2633 | continue | |
2634 | ||
2635 | fmt_url = fmt.get('url') | |
2636 | if not fmt_url: | |
2637 | sc = compat_parse_qs(fmt.get('signatureCipher')) | |
2638 | fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0])) | |
2639 | encrypted_sig = try_get(sc, lambda x: x['s'][0]) | |
2640 | if not (sc and fmt_url and encrypted_sig): | |
2641 | continue | |
2642 | if not player_url: | |
2643 | continue | |
2644 | signature = self._decrypt_signature(sc['s'][0], video_id, player_url) | |
2645 | sp = try_get(sc, lambda x: x['sp'][0]) or 'signature' | |
2646 | fmt_url += '&' + sp + '=' + signature | |
2647 | ||
2648 | if itag: | |
2649 | itags.append(itag) | |
2650 | stream_ids.append(stream_id) | |
2651 | ||
2652 | tbr = float_or_none( | |
2653 | fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) | |
2654 | dct = { | |
2655 | 'asr': int_or_none(fmt.get('audioSampleRate')), | |
2656 | 'filesize': int_or_none(fmt.get('contentLength')), | |
2657 | 'format_id': itag, | |
2658 | 'format_note': ', '.join(filter(None, ( | |
2659 | '%s%s' % (audio_track.get('displayName') or '', | |
2660 | ' (default)' if audio_track.get('audioIsDefault') else ''), | |
2661 | fmt.get('qualityLabel') or quality.replace('audio_quality_', '')))), | |
2662 | 'fps': int_or_none(fmt.get('fps')), | |
2663 | 'height': height, | |
2664 | 'quality': q(quality), | |
2665 | 'tbr': tbr, | |
2666 | 'url': fmt_url, | |
2667 | 'width': int_or_none(fmt.get('width')), | |
2668 | 'language': audio_track.get('id', '').split('.')[0], | |
2669 | 'language_preference': 1 if audio_track.get('audioIsDefault') else -1, | |
2670 | } | |
2671 | mime_mobj = re.match( | |
2672 | r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '') | |
2673 | if mime_mobj: | |
2674 | dct['ext'] = mimetype2ext(mime_mobj.group(1)) | |
2675 | dct.update(parse_codecs(mime_mobj.group(2))) | |
2676 | no_audio = dct.get('acodec') == 'none' | |
2677 | no_video = dct.get('vcodec') == 'none' | |
2678 | if no_audio: | |
2679 | dct['vbr'] = tbr | |
2680 | if no_video: | |
2681 | dct['abr'] = tbr | |
2682 | if no_audio or no_video: | |
2683 | dct['downloader_options'] = { | |
2684 | # Youtube throttles chunks >~10M | |
2685 | 'http_chunk_size': 10485760, | |
2686 | } | |
2687 | if dct.get('ext'): | |
2688 | dct['container'] = dct['ext'] + '_dash' | |
2689 | yield dct | |
2690 | ||
2691 | skip_manifests = self._configuration_arg('skip') | |
2692 | get_dash = ( | |
2693 | (not is_live or self._configuration_arg('include_live_dash')) | |
2694 | and 'dash' not in skip_manifests and self.get_param('youtube_include_dash_manifest', True)) | |
2695 | get_hls = 'hls' not in skip_manifests and self.get_param('youtube_include_hls_manifest', True) | |
2696 | ||
2697 | def guess_quality(f): | |
2698 | for val, qdict in ((f.get('format_id'), itag_qualities), (f.get('height'), res_qualities)): | |
2699 | if val in qdict: | |
2700 | return q(qdict[val]) | |
2701 | return -1 | |
2702 | ||
2703 | for sd in streaming_data: | |
2704 | hls_manifest_url = get_hls and sd.get('hlsManifestUrl') | |
2705 | if hls_manifest_url: | |
2706 | for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False): | |
2707 | itag = self._search_regex( | |
2708 | r'/itag/(\d+)', f['url'], 'itag', default=None) | |
2709 | if itag in itags: | |
2710 | continue | |
2711 | if itag: | |
2712 | f['format_id'] = itag | |
2713 | itags.append(itag) | |
2714 | f['quality'] = guess_quality(f) | |
2715 | yield f | |
2716 | ||
2717 | dash_manifest_url = get_dash and sd.get('dashManifestUrl') | |
2718 | if dash_manifest_url: | |
2719 | for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False): | |
2720 | itag = f['format_id'] | |
2721 | if itag in itags: | |
2722 | continue | |
2723 | if itag: | |
2724 | itags.append(itag) | |
2725 | f['quality'] = guess_quality(f) | |
2726 | filesize = int_or_none(self._search_regex( | |
2727 | r'/clen/(\d+)', f.get('fragment_base_url') | |
2728 | or f['url'], 'file size', default=None)) | |
2729 | if filesize: | |
2730 | f['filesize'] = filesize | |
2731 | yield f | |
2732 | ||
2733 | def _real_extract(self, url): | |
2734 | url, smuggled_data = unsmuggle_url(url, {}) | |
2735 | video_id = self._match_id(url) | |
2736 | ||
2737 | base_url = self.http_scheme() + '//www.youtube.com/' | |
2738 | webpage_url = base_url + 'watch?v=' + video_id | |
2739 | webpage = None | |
2740 | if 'webpage' not in self._configuration_arg('player_skip'): | |
2741 | webpage = self._download_webpage( | |
2742 | webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False) | |
2743 | ||
2744 | master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg() | |
2745 | identity_token = self._extract_identity_token(webpage, video_id) | |
2746 | ||
2747 | player_responses, player_url = self._extract_player_responses( | |
2748 | self._get_requested_clients(url, smuggled_data), | |
2749 | video_id, webpage, master_ytcfg, identity_token) | |
2750 | ||
2751 | get_first = lambda obj, keys, **kwargs: traverse_obj(obj, (..., *variadic(keys)), **kwargs, get_all=False) | |
2752 | ||
2753 | playability_statuses = traverse_obj( | |
2754 | player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[]) | |
2755 | ||
2756 | trailer_video_id = get_first( | |
2757 | playability_statuses, | |
2758 | ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'), | |
2759 | expected_type=str) | |
2760 | if trailer_video_id: | |
2761 | return self.url_result( | |
2762 | trailer_video_id, self.ie_key(), trailer_video_id) | |
2763 | ||
2764 | search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None)) | |
2765 | if webpage else (lambda x: None)) | |
2766 | ||
2767 | video_details = traverse_obj( | |
2768 | player_responses, (..., 'videoDetails'), expected_type=dict, default=[]) | |
2769 | microformats = traverse_obj( | |
2770 | player_responses, (..., 'microformat', 'playerMicroformatRenderer'), | |
2771 | expected_type=dict, default=[]) | |
2772 | video_title = ( | |
2773 | get_first(video_details, 'title') | |
2774 | or self._get_text(microformats, (..., 'title')) | |
2775 | or search_meta(['og:title', 'twitter:title', 'title'])) | |
2776 | video_description = get_first(video_details, 'shortDescription') | |
2777 | ||
2778 | if not smuggled_data.get('force_singlefeed', False): | |
2779 | if not self.get_param('noplaylist'): | |
2780 | multifeed_metadata_list = get_first( | |
2781 | player_responses, | |
2782 | ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'), | |
2783 | expected_type=str) | |
2784 | if multifeed_metadata_list: | |
2785 | entries = [] | |
2786 | feed_ids = [] | |
2787 | for feed in multifeed_metadata_list.split(','): | |
2788 | # Unquote should take place before split on comma (,) since textual | |
2789 | # fields may contain comma as well (see | |
2790 | # https://github.com/ytdl-org/youtube-dl/issues/8536) | |
2791 | feed_data = compat_parse_qs( | |
2792 | compat_urllib_parse_unquote_plus(feed)) | |
2793 | ||
2794 | def feed_entry(name): | |
2795 | return try_get( | |
2796 | feed_data, lambda x: x[name][0], compat_str) | |
2797 | ||
2798 | feed_id = feed_entry('id') | |
2799 | if not feed_id: | |
2800 | continue | |
2801 | feed_title = feed_entry('title') | |
2802 | title = video_title | |
2803 | if feed_title: | |
2804 | title += ' (%s)' % feed_title | |
2805 | entries.append({ | |
2806 | '_type': 'url_transparent', | |
2807 | 'ie_key': 'Youtube', | |
2808 | 'url': smuggle_url( | |
2809 | '%swatch?v=%s' % (base_url, feed_data['id'][0]), | |
2810 | {'force_singlefeed': True}), | |
2811 | 'title': title, | |
2812 | }) | |
2813 | feed_ids.append(feed_id) | |
2814 | self.to_screen( | |
2815 | 'Downloading multifeed video (%s) - add --no-playlist to just download video %s' | |
2816 | % (', '.join(feed_ids), video_id)) | |
2817 | return self.playlist_result( | |
2818 | entries, video_id, video_title, video_description) | |
2819 | else: | |
2820 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
2821 | ||
2822 | live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails')) | |
2823 | is_live = get_first(video_details, 'isLive') | |
2824 | if is_live is None: | |
2825 | is_live = get_first(live_broadcast_details, 'isLiveNow') | |
2826 | ||
2827 | streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[]) | |
2828 | formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live)) | |
2829 | ||
2830 | if not formats: | |
2831 | if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')): | |
2832 | self.report_drm(video_id) | |
2833 | pemr = get_first( | |
2834 | playability_statuses, | |
2835 | ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {} | |
2836 | reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason') | |
2837 | subreason = clean_html(self._get_text(pemr, 'subreason') or '') | |
2838 | if subreason: | |
2839 | if subreason == 'The uploader has not made this video available in your country.': | |
2840 | countries = get_first(microformats, 'availableCountries') | |
2841 | if not countries: | |
2842 | regions_allowed = search_meta('regionsAllowed') | |
2843 | countries = regions_allowed.split(',') if regions_allowed else None | |
2844 | self.raise_geo_restricted(subreason, countries, metadata_available=True) | |
2845 | reason += f'. {subreason}' | |
2846 | if reason: | |
2847 | self.raise_no_formats(reason, expected=True) | |
2848 | ||
2849 | for f in formats: | |
2850 | if '&c=WEB&' in f['url'] and '&ratebypass=yes&' not in f['url']: # throttled | |
2851 | f['source_preference'] = -10 | |
2852 | # TODO: this method is not reliable | |
2853 | f['format_note'] = format_field(f, 'format_note', '%s ') + '(maybe throttled)' | |
2854 | ||
2855 | # Source is given priority since formats that throttle are given lower source_preference | |
2856 | # When throttling issue is fully fixed, remove this | |
2857 | self._sort_formats(formats, ('quality', 'res', 'fps', 'source', 'codec:vp9.2', 'lang')) | |
2858 | ||
2859 | keywords = get_first(video_details, 'keywords', expected_type=list) or [] | |
2860 | if not keywords and webpage: | |
2861 | keywords = [ | |
2862 | unescapeHTML(m.group('content')) | |
2863 | for m in re.finditer(self._meta_regex('og:video:tag'), webpage)] | |
2864 | for keyword in keywords: | |
2865 | if keyword.startswith('yt:stretch='): | |
2866 | mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword) | |
2867 | if mobj: | |
2868 | # NB: float is intentional for forcing float division | |
2869 | w, h = (float(v) for v in mobj.groups()) | |
2870 | if w > 0 and h > 0: | |
2871 | ratio = w / h | |
2872 | for f in formats: | |
2873 | if f.get('vcodec') != 'none': | |
2874 | f['stretched_ratio'] = ratio | |
2875 | break | |
2876 | ||
2877 | thumbnails = [] | |
2878 | thumbnail_dicts = traverse_obj( | |
2879 | (video_details, microformats), (..., ..., 'thumbnail', 'thumbnails', ...), | |
2880 | expected_type=dict, default=[]) | |
2881 | for thumbnail in thumbnail_dicts: | |
2882 | thumbnail_url = thumbnail.get('url') | |
2883 | if not thumbnail_url: | |
2884 | continue | |
2885 | # Sometimes youtube gives a wrong thumbnail URL. See: | |
2886 | # https://github.com/yt-dlp/yt-dlp/issues/233 | |
2887 | # https://github.com/ytdl-org/youtube-dl/issues/28023 | |
2888 | if 'maxresdefault' in thumbnail_url: | |
2889 | thumbnail_url = thumbnail_url.split('?')[0] | |
2890 | thumbnails.append({ | |
2891 | 'url': thumbnail_url, | |
2892 | 'height': int_or_none(thumbnail.get('height')), | |
2893 | 'width': int_or_none(thumbnail.get('width')), | |
2894 | }) | |
2895 | thumbnail_url = search_meta(['og:image', 'twitter:image']) | |
2896 | if thumbnail_url: | |
2897 | thumbnails.append({ | |
2898 | 'url': thumbnail_url, | |
2899 | }) | |
2900 | # The best resolution thumbnails sometimes does not appear in the webpage | |
2901 | # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340 | |
2902 | # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029> | |
2903 | hq_thumbnail_names = ['maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3'] | |
2904 | # TODO: Test them also? - For some videos, even these don't exist | |
2905 | guaranteed_thumbnail_names = [ | |
2906 | 'hqdefault', 'hq1', 'hq2', 'hq3', '0', | |
2907 | 'mqdefault', 'mq1', 'mq2', 'mq3', | |
2908 | 'default', '1', '2', '3' | |
2909 | ] | |
2910 | thumbnail_names = hq_thumbnail_names + guaranteed_thumbnail_names | |
2911 | n_thumbnail_names = len(thumbnail_names) | |
2912 | ||
2913 | thumbnails.extend({ | |
2914 | 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format( | |
2915 | video_id=video_id, name=name, ext=ext, | |
2916 | webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''), | |
2917 | '_test_url': name in hq_thumbnail_names, | |
2918 | } for name in thumbnail_names for ext in ('webp', 'jpg')) | |
2919 | for thumb in thumbnails: | |
2920 | i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names) | |
2921 | thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i) | |
2922 | self._remove_duplicate_formats(thumbnails) | |
2923 | ||
2924 | category = get_first(microformats, 'category') or search_meta('genre') | |
2925 | channel_id = str_or_none( | |
2926 | get_first(video_details, 'channelId') | |
2927 | or get_first(microformats, 'externalChannelId') | |
2928 | or search_meta('channelId')) | |
2929 | duration = int_or_none( | |
2930 | get_first(video_details, 'lengthSeconds') | |
2931 | or get_first(microformats, 'lengthSeconds') | |
2932 | or parse_duration(search_meta('duration'))) or None | |
2933 | owner_profile_url = get_first(microformats, 'ownerProfileUrl') | |
2934 | ||
2935 | live_content = get_first(video_details, 'isLiveContent') | |
2936 | is_upcoming = get_first(video_details, 'isUpcoming') | |
2937 | if is_live is None: | |
2938 | if is_upcoming or live_content is False: | |
2939 | is_live = False | |
2940 | if is_upcoming is None and (live_content or is_live): | |
2941 | is_upcoming = False | |
2942 | live_starttime = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp')) | |
2943 | live_endtime = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp')) | |
2944 | if not duration and live_endtime and live_starttime: | |
2945 | duration = live_endtime - live_starttime | |
2946 | ||
2947 | info = { | |
2948 | 'id': video_id, | |
2949 | 'title': self._live_title(video_title) if is_live else video_title, | |
2950 | 'formats': formats, | |
2951 | 'thumbnails': thumbnails, | |
2952 | 'description': video_description, | |
2953 | 'upload_date': unified_strdate( | |
2954 | get_first(microformats, 'uploadDate') | |
2955 | or search_meta('uploadDate')), | |
2956 | 'uploader': get_first(video_details, 'author'), | |
2957 | 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None, | |
2958 | 'uploader_url': owner_profile_url, | |
2959 | 'channel_id': channel_id, | |
2960 | 'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None, | |
2961 | 'duration': duration, | |
2962 | 'view_count': int_or_none( | |
2963 | get_first((video_details, microformats), (..., 'viewCount')) | |
2964 | or search_meta('interactionCount')), | |
2965 | 'average_rating': float_or_none(get_first(video_details, 'averageRating')), | |
2966 | 'age_limit': 18 if ( | |
2967 | get_first(microformats, 'isFamilySafe') is False | |
2968 | or search_meta('isFamilyFriendly') == 'false' | |
2969 | or search_meta('og:restrictions:age') == '18+') else 0, | |
2970 | 'webpage_url': webpage_url, | |
2971 | 'categories': [category] if category else None, | |
2972 | 'tags': keywords, | |
2973 | 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'), | |
2974 | 'is_live': is_live, | |
2975 | 'was_live': (False if is_live or is_upcoming or live_content is False | |
2976 | else None if is_live is None or is_upcoming is None | |
2977 | else live_content), | |
2978 | 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL | |
2979 | 'release_timestamp': live_starttime, | |
2980 | } | |
2981 | ||
2982 | pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict) | |
2983 | # Converted into dicts to remove duplicates | |
2984 | captions = { | |
2985 | sub.get('baseUrl'): sub | |
2986 | for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])} | |
2987 | translation_languages = { | |
2988 | lang.get('languageCode'): lang.get('languageName') | |
2989 | for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])} | |
2990 | subtitles = {} | |
2991 | if pctr: | |
2992 | def process_language(container, base_url, lang_code, sub_name, query): | |
2993 | lang_subs = container.setdefault(lang_code, []) | |
2994 | for fmt in self._SUBTITLE_FORMATS: | |
2995 | query.update({ | |
2996 | 'fmt': fmt, | |
2997 | }) | |
2998 | lang_subs.append({ | |
2999 | 'ext': fmt, | |
3000 | 'url': update_url_query(base_url, query), | |
3001 | 'name': sub_name, | |
3002 | }) | |
3003 | ||
3004 | for base_url, caption_track in captions.items(): | |
3005 | if not base_url: | |
3006 | continue | |
3007 | if caption_track.get('kind') != 'asr': | |
3008 | lang_code = ( | |
3009 | remove_start(caption_track.get('vssId') or '', '.').replace('.', '-') | |
3010 | or caption_track.get('languageCode')) | |
3011 | if not lang_code: | |
3012 | continue | |
3013 | process_language( | |
3014 | subtitles, base_url, lang_code, | |
3015 | traverse_obj(caption_track, ('name', 'simpleText'), ('name', 'runs', ..., 'text'), get_all=False), | |
3016 | {}) | |
3017 | continue | |
3018 | automatic_captions = {} | |
3019 | for trans_code, trans_name in translation_languages.items(): | |
3020 | if not trans_code: | |
3021 | continue | |
3022 | process_language( | |
3023 | automatic_captions, base_url, trans_code, | |
3024 | self._get_text(trans_name, max_runs=1), | |
3025 | {'tlang': trans_code}) | |
3026 | info['automatic_captions'] = automatic_captions | |
3027 | info['subtitles'] = subtitles | |
3028 | ||
3029 | parsed_url = compat_urllib_parse_urlparse(url) | |
3030 | for component in [parsed_url.fragment, parsed_url.query]: | |
3031 | query = compat_parse_qs(component) | |
3032 | for k, v in query.items(): | |
3033 | for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]: | |
3034 | d_k += '_time' | |
3035 | if d_k not in info and k in s_ks: | |
3036 | info[d_k] = parse_duration(query[k][0]) | |
3037 | ||
3038 | # Youtube Music Auto-generated description | |
3039 | if video_description: | |
3040 | 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) | |
3041 | if mobj: | |
3042 | release_year = mobj.group('release_year') | |
3043 | release_date = mobj.group('release_date') | |
3044 | if release_date: | |
3045 | release_date = release_date.replace('-', '') | |
3046 | if not release_year: | |
3047 | release_year = release_date[:4] | |
3048 | info.update({ | |
3049 | 'album': mobj.group('album'.strip()), | |
3050 | 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')), | |
3051 | 'track': mobj.group('track').strip(), | |
3052 | 'release_date': release_date, | |
3053 | 'release_year': int_or_none(release_year), | |
3054 | }) | |
3055 | ||
3056 | initial_data = None | |
3057 | if webpage: | |
3058 | initial_data = self._extract_yt_initial_variable( | |
3059 | webpage, self._YT_INITIAL_DATA_RE, video_id, | |
3060 | 'yt initial data') | |
3061 | if not initial_data: | |
3062 | headers = self.generate_api_headers( | |
3063 | master_ytcfg, identity_token, self._extract_account_syncid(master_ytcfg), | |
3064 | session_index=self._extract_session_index(master_ytcfg)) | |
3065 | ||
3066 | initial_data = self._extract_response( | |
3067 | item_id=video_id, ep='next', fatal=False, | |
3068 | ytcfg=master_ytcfg, headers=headers, query={'videoId': video_id}, | |
3069 | note='Downloading initial data API JSON') | |
3070 | ||
3071 | try: | |
3072 | # This will error if there is no livechat | |
3073 | initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation'] | |
3074 | info['subtitles']['live_chat'] = [{ | |
3075 | 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies | |
3076 | 'video_id': video_id, | |
3077 | 'ext': 'json', | |
3078 | 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay', | |
3079 | }] | |
3080 | except (KeyError, IndexError, TypeError): | |
3081 | pass | |
3082 | ||
3083 | if initial_data: | |
3084 | info['chapters'] = ( | |
3085 | self._extract_chapters_from_json(initial_data, duration) | |
3086 | or self._extract_chapters_from_engagement_panel(initial_data, duration) | |
3087 | or None) | |
3088 | ||
3089 | contents = try_get( | |
3090 | initial_data, | |
3091 | lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], | |
3092 | list) or [] | |
3093 | for content in contents: | |
3094 | vpir = content.get('videoPrimaryInfoRenderer') | |
3095 | if vpir: | |
3096 | stl = vpir.get('superTitleLink') | |
3097 | if stl: | |
3098 | stl = self._get_text(stl) | |
3099 | if try_get( | |
3100 | vpir, | |
3101 | lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN': | |
3102 | info['location'] = stl | |
3103 | else: | |
3104 | mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl) | |
3105 | if mobj: | |
3106 | info.update({ | |
3107 | 'series': mobj.group(1), | |
3108 | 'season_number': int(mobj.group(2)), | |
3109 | 'episode_number': int(mobj.group(3)), | |
3110 | }) | |
3111 | for tlb in (try_get( | |
3112 | vpir, | |
3113 | lambda x: x['videoActions']['menuRenderer']['topLevelButtons'], | |
3114 | list) or []): | |
3115 | tbr = tlb.get('toggleButtonRenderer') or {} | |
3116 | for getter, regex in [( | |
3117 | lambda x: x['defaultText']['accessibility']['accessibilityData'], | |
3118 | r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([ | |
3119 | lambda x: x['accessibility'], | |
3120 | lambda x: x['accessibilityData']['accessibilityData'], | |
3121 | ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]: | |
3122 | label = (try_get(tbr, getter, dict) or {}).get('label') | |
3123 | if label: | |
3124 | mobj = re.match(regex, label) | |
3125 | if mobj: | |
3126 | info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count')) | |
3127 | break | |
3128 | sbr_tooltip = try_get( | |
3129 | vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip']) | |
3130 | if sbr_tooltip: | |
3131 | like_count, dislike_count = sbr_tooltip.split(' / ') | |
3132 | info.update({ | |
3133 | 'like_count': str_to_int(like_count), | |
3134 | 'dislike_count': str_to_int(dislike_count), | |
3135 | }) | |
3136 | vsir = content.get('videoSecondaryInfoRenderer') | |
3137 | if vsir: | |
3138 | info['channel'] = self._get_text(vsir, ('owner', 'videoOwnerRenderer', 'title')) | |
3139 | rows = try_get( | |
3140 | vsir, | |
3141 | lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'], | |
3142 | list) or [] | |
3143 | multiple_songs = False | |
3144 | for row in rows: | |
3145 | if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True: | |
3146 | multiple_songs = True | |
3147 | break | |
3148 | for row in rows: | |
3149 | mrr = row.get('metadataRowRenderer') or {} | |
3150 | mrr_title = mrr.get('title') | |
3151 | if not mrr_title: | |
3152 | continue | |
3153 | mrr_title = self._get_text(mrr, 'title') | |
3154 | mrr_contents_text = self._get_text(mrr, ('contents', 0)) | |
3155 | if mrr_title == 'License': | |
3156 | info['license'] = mrr_contents_text | |
3157 | elif not multiple_songs: | |
3158 | if mrr_title == 'Album': | |
3159 | info['album'] = mrr_contents_text | |
3160 | elif mrr_title == 'Artist': | |
3161 | info['artist'] = mrr_contents_text | |
3162 | elif mrr_title == 'Song': | |
3163 | info['track'] = mrr_contents_text | |
3164 | ||
3165 | fallbacks = { | |
3166 | 'channel': 'uploader', | |
3167 | 'channel_id': 'uploader_id', | |
3168 | 'channel_url': 'uploader_url', | |
3169 | } | |
3170 | for to, frm in fallbacks.items(): | |
3171 | if not info.get(to): | |
3172 | info[to] = info.get(frm) | |
3173 | ||
3174 | for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]: | |
3175 | v = info.get(s_k) | |
3176 | if v: | |
3177 | info[d_k] = v | |
3178 | ||
3179 | is_private = get_first(video_details, 'isPrivate', expected_type=bool) | |
3180 | is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool) | |
3181 | is_membersonly = None | |
3182 | is_premium = None | |
3183 | if initial_data and is_private is not None: | |
3184 | is_membersonly = False | |
3185 | is_premium = False | |
3186 | contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or [] | |
3187 | badge_labels = set() | |
3188 | for content in contents: | |
3189 | if not isinstance(content, dict): | |
3190 | continue | |
3191 | badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer'))) | |
3192 | for badge_label in badge_labels: | |
3193 | if badge_label.lower() == 'members only': | |
3194 | is_membersonly = True | |
3195 | elif badge_label.lower() == 'premium': | |
3196 | is_premium = True | |
3197 | elif badge_label.lower() == 'unlisted': | |
3198 | is_unlisted = True | |
3199 | ||
3200 | info['availability'] = self._availability( | |
3201 | is_private=is_private, | |
3202 | needs_premium=is_premium, | |
3203 | needs_subscription=is_membersonly, | |
3204 | needs_auth=info['age_limit'] >= 18, | |
3205 | is_unlisted=None if is_private is None else is_unlisted) | |
3206 | ||
3207 | if self.get_param('getcomments', False): | |
3208 | info['__post_extractor'] = lambda: self._extract_comments(master_ytcfg, video_id, contents, webpage) | |
3209 | ||
3210 | self.mark_watched(video_id, player_responses) | |
3211 | ||
3212 | return info | |
3213 | ||
3214 | ||
3215 | class YoutubeTabIE(YoutubeBaseInfoExtractor): | |
3216 | IE_DESC = 'YouTube.com tab' | |
3217 | _VALID_URL = r'''(?x) | |
3218 | https?:// | |
3219 | (?:\w+\.)? | |
3220 | (?: | |
3221 | youtube(?:kids)?\.com| | |
3222 | invidio\.us | |
3223 | )/ | |
3224 | (?: | |
3225 | (?P<channel_type>channel|c|user|browse)/| | |
3226 | (?P<not_channel> | |
3227 | feed/|hashtag/| | |
3228 | (?:playlist|watch)\?.*?\blist= | |
3229 | )| | |
3230 | (?!(?:%s)\b) # Direct URLs | |
3231 | ) | |
3232 | (?P<id>[^/?\#&]+) | |
3233 | ''' % YoutubeBaseInfoExtractor._RESERVED_NAMES | |
3234 | IE_NAME = 'youtube:tab' | |
3235 | ||
3236 | _TESTS = [{ | |
3237 | 'note': 'playlists, multipage', | |
3238 | 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid', | |
3239 | 'playlist_mincount': 94, | |
3240 | 'info_dict': { | |
3241 | 'id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
3242 | 'title': 'Игорь Клейнер - Playlists', | |
3243 | 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2', | |
3244 | 'uploader': 'Игорь Клейнер', | |
3245 | 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
3246 | }, | |
3247 | }, { | |
3248 | 'note': 'playlists, multipage, different order', | |
3249 | 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd', | |
3250 | 'playlist_mincount': 94, | |
3251 | 'info_dict': { | |
3252 | 'id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
3253 | 'title': 'Игорь Клейнер - Playlists', | |
3254 | 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2', | |
3255 | 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
3256 | 'uploader': 'Игорь Клейнер', | |
3257 | }, | |
3258 | }, { | |
3259 | 'note': 'playlists, series', | |
3260 | 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3', | |
3261 | 'playlist_mincount': 5, | |
3262 | 'info_dict': { | |
3263 | 'id': 'UCYO_jab_esuFRV4b17AJtAw', | |
3264 | 'title': '3Blue1Brown - Playlists', | |
3265 | 'description': 'md5:e1384e8a133307dd10edee76e875d62f', | |
3266 | 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw', | |
3267 | 'uploader': '3Blue1Brown', | |
3268 | }, | |
3269 | }, { | |
3270 | 'note': 'playlists, singlepage', | |
3271 | 'url': 'https://www.youtube.com/user/ThirstForScience/playlists', | |
3272 | 'playlist_mincount': 4, | |
3273 | 'info_dict': { | |
3274 | 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ', | |
3275 | 'title': 'ThirstForScience - Playlists', | |
3276 | 'description': 'md5:609399d937ea957b0f53cbffb747a14c', | |
3277 | 'uploader': 'ThirstForScience', | |
3278 | 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ', | |
3279 | } | |
3280 | }, { | |
3281 | 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists', | |
3282 | 'only_matching': True, | |
3283 | }, { | |
3284 | 'note': 'basic, single video playlist', | |
3285 | 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', | |
3286 | 'info_dict': { | |
3287 | 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', | |
3288 | 'uploader': 'Sergey M.', | |
3289 | 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', | |
3290 | 'title': 'youtube-dl public playlist', | |
3291 | }, | |
3292 | 'playlist_count': 1, | |
3293 | }, { | |
3294 | 'note': 'empty playlist', | |
3295 | 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', | |
3296 | 'info_dict': { | |
3297 | 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', | |
3298 | 'uploader': 'Sergey M.', | |
3299 | 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', | |
3300 | 'title': 'youtube-dl empty playlist', | |
3301 | }, | |
3302 | 'playlist_count': 0, | |
3303 | }, { | |
3304 | 'note': 'Home tab', | |
3305 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured', | |
3306 | 'info_dict': { | |
3307 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
3308 | 'title': 'lex will - Home', | |
3309 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
3310 | 'uploader': 'lex will', | |
3311 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
3312 | }, | |
3313 | 'playlist_mincount': 2, | |
3314 | }, { | |
3315 | 'note': 'Videos tab', | |
3316 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos', | |
3317 | 'info_dict': { | |
3318 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
3319 | 'title': 'lex will - Videos', | |
3320 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
3321 | 'uploader': 'lex will', | |
3322 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
3323 | }, | |
3324 | 'playlist_mincount': 975, | |
3325 | }, { | |
3326 | 'note': 'Videos tab, sorted by popular', | |
3327 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid', | |
3328 | 'info_dict': { | |
3329 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
3330 | 'title': 'lex will - Videos', | |
3331 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
3332 | 'uploader': 'lex will', | |
3333 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
3334 | }, | |
3335 | 'playlist_mincount': 199, | |
3336 | }, { | |
3337 | 'note': 'Playlists tab', | |
3338 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists', | |
3339 | 'info_dict': { | |
3340 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
3341 | 'title': 'lex will - Playlists', | |
3342 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
3343 | 'uploader': 'lex will', | |
3344 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
3345 | }, | |
3346 | 'playlist_mincount': 17, | |
3347 | }, { | |
3348 | 'note': 'Community tab', | |
3349 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community', | |
3350 | 'info_dict': { | |
3351 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
3352 | 'title': 'lex will - Community', | |
3353 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
3354 | 'uploader': 'lex will', | |
3355 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
3356 | }, | |
3357 | 'playlist_mincount': 18, | |
3358 | }, { | |
3359 | 'note': 'Channels tab', | |
3360 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels', | |
3361 | 'info_dict': { | |
3362 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
3363 | 'title': 'lex will - Channels', | |
3364 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
3365 | 'uploader': 'lex will', | |
3366 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
3367 | }, | |
3368 | 'playlist_mincount': 12, | |
3369 | }, { | |
3370 | 'note': 'Search tab', | |
3371 | 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra', | |
3372 | 'playlist_mincount': 40, | |
3373 | 'info_dict': { | |
3374 | 'id': 'UCYO_jab_esuFRV4b17AJtAw', | |
3375 | 'title': '3Blue1Brown - Search - linear algebra', | |
3376 | 'description': 'md5:e1384e8a133307dd10edee76e875d62f', | |
3377 | 'uploader': '3Blue1Brown', | |
3378 | 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw', | |
3379 | }, | |
3380 | }, { | |
3381 | 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
3382 | 'only_matching': True, | |
3383 | }, { | |
3384 | 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
3385 | 'only_matching': True, | |
3386 | }, { | |
3387 | 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
3388 | 'only_matching': True, | |
3389 | }, { | |
3390 | 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', | |
3391 | 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
3392 | 'info_dict': { | |
3393 | 'title': '29C3: Not my department', | |
3394 | 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
3395 | 'uploader': 'Christiaan008', | |
3396 | 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg', | |
3397 | 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268', | |
3398 | }, | |
3399 | 'playlist_count': 96, | |
3400 | }, { | |
3401 | 'note': 'Large playlist', | |
3402 | 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', | |
3403 | 'info_dict': { | |
3404 | 'title': 'Uploads from Cauchemar', | |
3405 | 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', | |
3406 | 'uploader': 'Cauchemar', | |
3407 | 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q', | |
3408 | }, | |
3409 | 'playlist_mincount': 1123, | |
3410 | }, { | |
3411 | 'note': 'even larger playlist, 8832 videos', | |
3412 | 'url': 'http://www.youtube.com/user/NASAgovVideo/videos', | |
3413 | 'only_matching': True, | |
3414 | }, { | |
3415 | 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', | |
3416 | 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', | |
3417 | 'info_dict': { | |
3418 | 'title': 'Uploads from Interstellar Movie', | |
3419 | 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', | |
3420 | 'uploader': 'Interstellar Movie', | |
3421 | 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA', | |
3422 | }, | |
3423 | 'playlist_mincount': 21, | |
3424 | }, { | |
3425 | 'note': 'Playlist with "show unavailable videos" button', | |
3426 | 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q', | |
3427 | 'info_dict': { | |
3428 | 'title': 'Uploads from Phim Siêu Nhân Nhật Bản', | |
3429 | 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q', | |
3430 | 'uploader': 'Phim Siêu Nhân Nhật Bản', | |
3431 | 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q', | |
3432 | }, | |
3433 | 'playlist_mincount': 200, | |
3434 | }, { | |
3435 | 'note': 'Playlist with unavailable videos in page 7', | |
3436 | 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w', | |
3437 | 'info_dict': { | |
3438 | 'title': 'Uploads from BlankTV', | |
3439 | 'id': 'UU8l9frL61Yl5KFOl87nIm2w', | |
3440 | 'uploader': 'BlankTV', | |
3441 | 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w', | |
3442 | }, | |
3443 | 'playlist_mincount': 1000, | |
3444 | }, { | |
3445 | 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844', | |
3446 | 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', | |
3447 | 'info_dict': { | |
3448 | 'title': 'Data Analysis with Dr Mike Pound', | |
3449 | 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', | |
3450 | 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA', | |
3451 | 'uploader': 'Computerphile', | |
3452 | 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487', | |
3453 | }, | |
3454 | 'playlist_mincount': 11, | |
3455 | }, { | |
3456 | 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', | |
3457 | 'only_matching': True, | |
3458 | }, { | |
3459 | 'note': 'Playlist URL that does not actually serve a playlist', | |
3460 | 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4', | |
3461 | 'info_dict': { | |
3462 | 'id': 'FqZTN594JQw', | |
3463 | 'ext': 'webm', | |
3464 | 'title': "Smiley's People 01 detective, Adventure Series, Action", | |
3465 | 'uploader': 'STREEM', | |
3466 | 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng', | |
3467 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng', | |
3468 | 'upload_date': '20150526', | |
3469 | 'license': 'Standard YouTube License', | |
3470 | 'description': 'md5:507cdcb5a49ac0da37a920ece610be80', | |
3471 | 'categories': ['People & Blogs'], | |
3472 | 'tags': list, | |
3473 | 'view_count': int, | |
3474 | 'like_count': int, | |
3475 | 'dislike_count': int, | |
3476 | }, | |
3477 | 'params': { | |
3478 | 'skip_download': True, | |
3479 | }, | |
3480 | 'skip': 'This video is not available.', | |
3481 | 'add_ie': [YoutubeIE.ie_key()], | |
3482 | }, { | |
3483 | 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g', | |
3484 | 'only_matching': True, | |
3485 | }, { | |
3486 | 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM', | |
3487 | 'only_matching': True, | |
3488 | }, { | |
3489 | 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live', | |
3490 | 'info_dict': { | |
3491 | 'id': '3yImotZU3tw', # This will keep changing | |
3492 | 'ext': 'mp4', | |
3493 | 'title': compat_str, | |
3494 | 'uploader': 'Sky News', | |
3495 | 'uploader_id': 'skynews', | |
3496 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews', | |
3497 | 'upload_date': r're:\d{8}', | |
3498 | 'description': compat_str, | |
3499 | 'categories': ['News & Politics'], | |
3500 | 'tags': list, | |
3501 | 'like_count': int, | |
3502 | 'dislike_count': int, | |
3503 | }, | |
3504 | 'params': { | |
3505 | 'skip_download': True, | |
3506 | }, | |
3507 | 'expected_warnings': ['Downloading just video ', 'Ignoring subtitle tracks found in '], | |
3508 | }, { | |
3509 | 'url': 'https://www.youtube.com/user/TheYoungTurks/live', | |
3510 | 'info_dict': { | |
3511 | 'id': 'a48o2S1cPoo', | |
3512 | 'ext': 'mp4', | |
3513 | 'title': 'The Young Turks - Live Main Show', | |
3514 | 'uploader': 'The Young Turks', | |
3515 | 'uploader_id': 'TheYoungTurks', | |
3516 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks', | |
3517 | 'upload_date': '20150715', | |
3518 | 'license': 'Standard YouTube License', | |
3519 | 'description': 'md5:438179573adcdff3c97ebb1ee632b891', | |
3520 | 'categories': ['News & Politics'], | |
3521 | 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'], | |
3522 | 'like_count': int, | |
3523 | 'dislike_count': int, | |
3524 | }, | |
3525 | 'params': { | |
3526 | 'skip_download': True, | |
3527 | }, | |
3528 | 'only_matching': True, | |
3529 | }, { | |
3530 | 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live', | |
3531 | 'only_matching': True, | |
3532 | }, { | |
3533 | 'url': 'https://www.youtube.com/c/CommanderVideoHq/live', | |
3534 | 'only_matching': True, | |
3535 | }, { | |
3536 | 'note': 'A channel that is not live. Should raise error', | |
3537 | 'url': 'https://www.youtube.com/user/numberphile/live', | |
3538 | 'only_matching': True, | |
3539 | }, { | |
3540 | 'url': 'https://www.youtube.com/feed/trending', | |
3541 | 'only_matching': True, | |
3542 | }, { | |
3543 | 'url': 'https://www.youtube.com/feed/library', | |
3544 | 'only_matching': True, | |
3545 | }, { | |
3546 | 'url': 'https://www.youtube.com/feed/history', | |
3547 | 'only_matching': True, | |
3548 | }, { | |
3549 | 'url': 'https://www.youtube.com/feed/subscriptions', | |
3550 | 'only_matching': True, | |
3551 | }, { | |
3552 | 'url': 'https://www.youtube.com/feed/watch_later', | |
3553 | 'only_matching': True, | |
3554 | }, { | |
3555 | 'note': 'Recommended - redirects to home page', | |
3556 | 'url': 'https://www.youtube.com/feed/recommended', | |
3557 | 'only_matching': True, | |
3558 | }, { | |
3559 | 'note': 'inline playlist with not always working continuations', | |
3560 | 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C', | |
3561 | 'only_matching': True, | |
3562 | }, { | |
3563 | 'url': 'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8', | |
3564 | 'only_matching': True, | |
3565 | }, { | |
3566 | 'url': 'https://www.youtube.com/course', | |
3567 | 'only_matching': True, | |
3568 | }, { | |
3569 | 'url': 'https://www.youtube.com/zsecurity', | |
3570 | 'only_matching': True, | |
3571 | }, { | |
3572 | 'url': 'http://www.youtube.com/NASAgovVideo/videos', | |
3573 | 'only_matching': True, | |
3574 | }, { | |
3575 | 'url': 'https://www.youtube.com/TheYoungTurks/live', | |
3576 | 'only_matching': True, | |
3577 | }, { | |
3578 | 'url': 'https://www.youtube.com/hashtag/cctv9', | |
3579 | 'info_dict': { | |
3580 | 'id': 'cctv9', | |
3581 | 'title': '#cctv9', | |
3582 | }, | |
3583 | 'playlist_mincount': 350, | |
3584 | }, { | |
3585 | 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU', | |
3586 | 'only_matching': True, | |
3587 | }, { | |
3588 | 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist', | |
3589 | 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', | |
3590 | 'only_matching': True | |
3591 | }, { | |
3592 | 'note': '/browse/ should redirect to /channel/', | |
3593 | 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng', | |
3594 | 'only_matching': True | |
3595 | }, { | |
3596 | 'note': 'VLPL, should redirect to playlist?list=PL...', | |
3597 | 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', | |
3598 | 'info_dict': { | |
3599 | 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', | |
3600 | 'uploader': 'NoCopyrightSounds', | |
3601 | 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!', | |
3602 | 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg', | |
3603 | 'title': 'NCS Releases', | |
3604 | }, | |
3605 | 'playlist_mincount': 166, | |
3606 | }, { | |
3607 | 'note': 'Topic, should redirect to playlist?list=UU...', | |
3608 | 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw', | |
3609 | 'info_dict': { | |
3610 | 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw', | |
3611 | 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', | |
3612 | 'title': 'Uploads from Royalty Free Music - Topic', | |
3613 | 'uploader': 'Royalty Free Music - Topic', | |
3614 | }, | |
3615 | 'expected_warnings': [ | |
3616 | 'A channel/user page was given', | |
3617 | 'The URL does not have a videos tab', | |
3618 | ], | |
3619 | 'playlist_mincount': 101, | |
3620 | }, { | |
3621 | 'note': 'Topic without a UU playlist', | |
3622 | 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg', | |
3623 | 'info_dict': { | |
3624 | 'id': 'UCtFRv9O2AHqOZjjynzrv-xg', | |
3625 | 'title': 'UCtFRv9O2AHqOZjjynzrv-xg', | |
3626 | }, | |
3627 | 'expected_warnings': [ | |
3628 | 'A channel/user page was given', | |
3629 | 'The URL does not have a videos tab', | |
3630 | 'Falling back to channel URL', | |
3631 | ], | |
3632 | 'playlist_mincount': 9, | |
3633 | }, { | |
3634 | 'note': 'Youtube music Album', | |
3635 | 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE', | |
3636 | 'info_dict': { | |
3637 | 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0', | |
3638 | 'title': 'Album - Royalty Free Music Library V2 (50 Songs)', | |
3639 | }, | |
3640 | 'playlist_count': 50, | |
3641 | }, { | |
3642 | 'note': 'unlisted single video playlist', | |
3643 | 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf', | |
3644 | 'info_dict': { | |
3645 | 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q', | |
3646 | 'uploader': 'colethedj', | |
3647 | 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf', | |
3648 | 'title': 'yt-dlp unlisted playlist test', | |
3649 | 'availability': 'unlisted' | |
3650 | }, | |
3651 | 'playlist_count': 1, | |
3652 | }] | |
3653 | ||
3654 | @classmethod | |
3655 | def suitable(cls, url): | |
3656 | return False if YoutubeIE.suitable(url) else super( | |
3657 | YoutubeTabIE, cls).suitable(url) | |
3658 | ||
3659 | def _extract_channel_id(self, webpage): | |
3660 | channel_id = self._html_search_meta( | |
3661 | 'channelId', webpage, 'channel id', default=None) | |
3662 | if channel_id: | |
3663 | return channel_id | |
3664 | channel_url = self._html_search_meta( | |
3665 | ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url', | |
3666 | 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad', | |
3667 | 'twitter:app:url:googleplay'), webpage, 'channel url') | |
3668 | return self._search_regex( | |
3669 | r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+', | |
3670 | channel_url, 'channel id') | |
3671 | ||
3672 | @staticmethod | |
3673 | def _extract_basic_item_renderer(item): | |
3674 | # Modified from _extract_grid_item_renderer | |
3675 | known_basic_renderers = ( | |
3676 | 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer' | |
3677 | ) | |
3678 | for key, renderer in item.items(): | |
3679 | if not isinstance(renderer, dict): | |
3680 | continue | |
3681 | elif key in known_basic_renderers: | |
3682 | return renderer | |
3683 | elif key.startswith('grid') and key.endswith('Renderer'): | |
3684 | return renderer | |
3685 | ||
3686 | def _grid_entries(self, grid_renderer): | |
3687 | for item in grid_renderer['items']: | |
3688 | if not isinstance(item, dict): | |
3689 | continue | |
3690 | renderer = self._extract_basic_item_renderer(item) | |
3691 | if not isinstance(renderer, dict): | |
3692 | continue | |
3693 | title = self._get_text(renderer, 'title') | |
3694 | ||
3695 | # playlist | |
3696 | playlist_id = renderer.get('playlistId') | |
3697 | if playlist_id: | |
3698 | yield self.url_result( | |
3699 | 'https://www.youtube.com/playlist?list=%s' % playlist_id, | |
3700 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id, | |
3701 | video_title=title) | |
3702 | continue | |
3703 | # video | |
3704 | video_id = renderer.get('videoId') | |
3705 | if video_id: | |
3706 | yield self._extract_video(renderer) | |
3707 | continue | |
3708 | # channel | |
3709 | channel_id = renderer.get('channelId') | |
3710 | if channel_id: | |
3711 | yield self.url_result( | |
3712 | 'https://www.youtube.com/channel/%s' % channel_id, | |
3713 | ie=YoutubeTabIE.ie_key(), video_title=title) | |
3714 | continue | |
3715 | # generic endpoint URL support | |
3716 | ep_url = urljoin('https://www.youtube.com/', try_get( | |
3717 | renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'], | |
3718 | compat_str)) | |
3719 | if ep_url: | |
3720 | for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE): | |
3721 | if ie.suitable(ep_url): | |
3722 | yield self.url_result( | |
3723 | ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title) | |
3724 | break | |
3725 | ||
3726 | def _shelf_entries_from_content(self, shelf_renderer): | |
3727 | content = shelf_renderer.get('content') | |
3728 | if not isinstance(content, dict): | |
3729 | return | |
3730 | renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer') | |
3731 | if renderer: | |
3732 | # TODO: add support for nested playlists so each shelf is processed | |
3733 | # as separate playlist | |
3734 | # TODO: this includes only first N items | |
3735 | for entry in self._grid_entries(renderer): | |
3736 | yield entry | |
3737 | renderer = content.get('horizontalListRenderer') | |
3738 | if renderer: | |
3739 | # TODO | |
3740 | pass | |
3741 | ||
3742 | def _shelf_entries(self, shelf_renderer, skip_channels=False): | |
3743 | ep = try_get( | |
3744 | shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'], | |
3745 | compat_str) | |
3746 | shelf_url = urljoin('https://www.youtube.com', ep) | |
3747 | if shelf_url: | |
3748 | # Skipping links to another channels, note that checking for | |
3749 | # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL | |
3750 | # will not work | |
3751 | if skip_channels and '/channels?' in shelf_url: | |
3752 | return | |
3753 | title = self._get_text(shelf_renderer, 'title') | |
3754 | yield self.url_result(shelf_url, video_title=title) | |
3755 | # Shelf may not contain shelf URL, fallback to extraction from content | |
3756 | for entry in self._shelf_entries_from_content(shelf_renderer): | |
3757 | yield entry | |
3758 | ||
3759 | def _playlist_entries(self, video_list_renderer): | |
3760 | for content in video_list_renderer['contents']: | |
3761 | if not isinstance(content, dict): | |
3762 | continue | |
3763 | renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer') | |
3764 | if not isinstance(renderer, dict): | |
3765 | continue | |
3766 | video_id = renderer.get('videoId') | |
3767 | if not video_id: | |
3768 | continue | |
3769 | yield self._extract_video(renderer) | |
3770 | ||
3771 | def _rich_entries(self, rich_grid_renderer): | |
3772 | renderer = try_get( | |
3773 | rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {} | |
3774 | video_id = renderer.get('videoId') | |
3775 | if not video_id: | |
3776 | return | |
3777 | yield self._extract_video(renderer) | |
3778 | ||
3779 | def _video_entry(self, video_renderer): | |
3780 | video_id = video_renderer.get('videoId') | |
3781 | if video_id: | |
3782 | return self._extract_video(video_renderer) | |
3783 | ||
3784 | def _post_thread_entries(self, post_thread_renderer): | |
3785 | post_renderer = try_get( | |
3786 | post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict) | |
3787 | if not post_renderer: | |
3788 | return | |
3789 | # video attachment | |
3790 | video_renderer = try_get( | |
3791 | post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {} | |
3792 | video_id = video_renderer.get('videoId') | |
3793 | if video_id: | |
3794 | entry = self._extract_video(video_renderer) | |
3795 | if entry: | |
3796 | yield entry | |
3797 | # playlist attachment | |
3798 | playlist_id = try_get( | |
3799 | post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str) | |
3800 | if playlist_id: | |
3801 | yield self.url_result( | |
3802 | 'https://www.youtube.com/playlist?list=%s' % playlist_id, | |
3803 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
3804 | # inline video links | |
3805 | runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or [] | |
3806 | for run in runs: | |
3807 | if not isinstance(run, dict): | |
3808 | continue | |
3809 | ep_url = try_get( | |
3810 | run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str) | |
3811 | if not ep_url: | |
3812 | continue | |
3813 | if not YoutubeIE.suitable(ep_url): | |
3814 | continue | |
3815 | ep_video_id = YoutubeIE._match_id(ep_url) | |
3816 | if video_id == ep_video_id: | |
3817 | continue | |
3818 | yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id) | |
3819 | ||
3820 | def _post_thread_continuation_entries(self, post_thread_continuation): | |
3821 | contents = post_thread_continuation.get('contents') | |
3822 | if not isinstance(contents, list): | |
3823 | return | |
3824 | for content in contents: | |
3825 | renderer = content.get('backstagePostThreadRenderer') | |
3826 | if not isinstance(renderer, dict): | |
3827 | continue | |
3828 | for entry in self._post_thread_entries(renderer): | |
3829 | yield entry | |
3830 | ||
3831 | r''' # unused | |
3832 | def _rich_grid_entries(self, contents): | |
3833 | for content in contents: | |
3834 | video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict) | |
3835 | if video_renderer: | |
3836 | entry = self._video_entry(video_renderer) | |
3837 | if entry: | |
3838 | yield entry | |
3839 | ''' | |
3840 | def _entries(self, tab, item_id, identity_token, account_syncid, ytcfg): | |
3841 | ||
3842 | def extract_entries(parent_renderer): # this needs to called again for continuation to work with feeds | |
3843 | contents = try_get(parent_renderer, lambda x: x['contents'], list) or [] | |
3844 | for content in contents: | |
3845 | if not isinstance(content, dict): | |
3846 | continue | |
3847 | is_renderer = try_get(content, lambda x: x['itemSectionRenderer'], dict) | |
3848 | if not is_renderer: | |
3849 | renderer = content.get('richItemRenderer') | |
3850 | if renderer: | |
3851 | for entry in self._rich_entries(renderer): | |
3852 | yield entry | |
3853 | continuation_list[0] = self._extract_continuation(parent_renderer) | |
3854 | continue | |
3855 | isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or [] | |
3856 | for isr_content in isr_contents: | |
3857 | if not isinstance(isr_content, dict): | |
3858 | continue | |
3859 | ||
3860 | known_renderers = { | |
3861 | 'playlistVideoListRenderer': self._playlist_entries, | |
3862 | 'gridRenderer': self._grid_entries, | |
3863 | 'shelfRenderer': lambda x: self._shelf_entries(x, tab.get('title') != 'Channels'), | |
3864 | 'backstagePostThreadRenderer': self._post_thread_entries, | |
3865 | 'videoRenderer': lambda x: [self._video_entry(x)], | |
3866 | } | |
3867 | for key, renderer in isr_content.items(): | |
3868 | if key not in known_renderers: | |
3869 | continue | |
3870 | for entry in known_renderers[key](renderer): | |
3871 | if entry: | |
3872 | yield entry | |
3873 | continuation_list[0] = self._extract_continuation(renderer) | |
3874 | break | |
3875 | ||
3876 | if not continuation_list[0]: | |
3877 | continuation_list[0] = self._extract_continuation(is_renderer) | |
3878 | ||
3879 | if not continuation_list[0]: | |
3880 | continuation_list[0] = self._extract_continuation(parent_renderer) | |
3881 | ||
3882 | continuation_list = [None] # Python 2 doesnot support nonlocal | |
3883 | tab_content = try_get(tab, lambda x: x['content'], dict) | |
3884 | if not tab_content: | |
3885 | return | |
3886 | parent_renderer = ( | |
3887 | try_get(tab_content, lambda x: x['sectionListRenderer'], dict) | |
3888 | or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {}) | |
3889 | for entry in extract_entries(parent_renderer): | |
3890 | yield entry | |
3891 | continuation = continuation_list[0] | |
3892 | visitor_data = None | |
3893 | ||
3894 | for page_num in itertools.count(1): | |
3895 | if not continuation: | |
3896 | break | |
3897 | headers = self.generate_api_headers(ytcfg, identity_token, account_syncid, visitor_data) | |
3898 | response = self._extract_response( | |
3899 | item_id='%s page %s' % (item_id, page_num), | |
3900 | query=continuation, headers=headers, ytcfg=ytcfg, | |
3901 | check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints')) | |
3902 | ||
3903 | if not response: | |
3904 | break | |
3905 | visitor_data = try_get( | |
3906 | response, lambda x: x['responseContext']['visitorData'], compat_str) or visitor_data | |
3907 | ||
3908 | known_continuation_renderers = { | |
3909 | 'playlistVideoListContinuation': self._playlist_entries, | |
3910 | 'gridContinuation': self._grid_entries, | |
3911 | 'itemSectionContinuation': self._post_thread_continuation_entries, | |
3912 | 'sectionListContinuation': extract_entries, # for feeds | |
3913 | } | |
3914 | continuation_contents = try_get( | |
3915 | response, lambda x: x['continuationContents'], dict) or {} | |
3916 | continuation_renderer = None | |
3917 | for key, value in continuation_contents.items(): | |
3918 | if key not in known_continuation_renderers: | |
3919 | continue | |
3920 | continuation_renderer = value | |
3921 | continuation_list = [None] | |
3922 | for entry in known_continuation_renderers[key](continuation_renderer): | |
3923 | yield entry | |
3924 | continuation = continuation_list[0] or self._extract_continuation(continuation_renderer) | |
3925 | break | |
3926 | if continuation_renderer: | |
3927 | continue | |
3928 | ||
3929 | known_renderers = { | |
3930 | 'gridPlaylistRenderer': (self._grid_entries, 'items'), | |
3931 | 'gridVideoRenderer': (self._grid_entries, 'items'), | |
3932 | 'gridChannelRenderer': (self._grid_entries, 'items'), | |
3933 | 'playlistVideoRenderer': (self._playlist_entries, 'contents'), | |
3934 | 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds | |
3935 | 'richItemRenderer': (extract_entries, 'contents'), # for hashtag | |
3936 | 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents') | |
3937 | } | |
3938 | on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints')) | |
3939 | continuation_items = try_get( | |
3940 | on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list) | |
3941 | continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {} | |
3942 | video_items_renderer = None | |
3943 | for key, value in continuation_item.items(): | |
3944 | if key not in known_renderers: | |
3945 | continue | |
3946 | video_items_renderer = {known_renderers[key][1]: continuation_items} | |
3947 | continuation_list = [None] | |
3948 | for entry in known_renderers[key][0](video_items_renderer): | |
3949 | yield entry | |
3950 | continuation = continuation_list[0] or self._extract_continuation(video_items_renderer) | |
3951 | break | |
3952 | if video_items_renderer: | |
3953 | continue | |
3954 | break | |
3955 | ||
3956 | @staticmethod | |
3957 | def _extract_selected_tab(tabs): | |
3958 | for tab in tabs: | |
3959 | renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {} | |
3960 | if renderer.get('selected') is True: | |
3961 | return renderer | |
3962 | else: | |
3963 | raise ExtractorError('Unable to find selected tab') | |
3964 | ||
3965 | @classmethod | |
3966 | def _extract_uploader(cls, data): | |
3967 | uploader = {} | |
3968 | renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {} | |
3969 | owner = try_get( | |
3970 | renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict) | |
3971 | if owner: | |
3972 | uploader['uploader'] = owner.get('text') | |
3973 | uploader['uploader_id'] = try_get( | |
3974 | owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str) | |
3975 | uploader['uploader_url'] = urljoin( | |
3976 | 'https://www.youtube.com/', | |
3977 | try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str)) | |
3978 | return {k: v for k, v in uploader.items() if v is not None} | |
3979 | ||
3980 | def _extract_from_tabs(self, item_id, webpage, data, tabs): | |
3981 | playlist_id = title = description = channel_url = channel_name = channel_id = None | |
3982 | thumbnails_list = tags = [] | |
3983 | ||
3984 | selected_tab = self._extract_selected_tab(tabs) | |
3985 | renderer = try_get( | |
3986 | data, lambda x: x['metadata']['channelMetadataRenderer'], dict) | |
3987 | if renderer: | |
3988 | channel_name = renderer.get('title') | |
3989 | channel_url = renderer.get('channelUrl') | |
3990 | channel_id = renderer.get('externalId') | |
3991 | else: | |
3992 | renderer = try_get( | |
3993 | data, lambda x: x['metadata']['playlistMetadataRenderer'], dict) | |
3994 | ||
3995 | if renderer: | |
3996 | title = renderer.get('title') | |
3997 | description = renderer.get('description', '') | |
3998 | playlist_id = channel_id | |
3999 | tags = renderer.get('keywords', '').split() | |
4000 | thumbnails_list = ( | |
4001 | try_get(renderer, lambda x: x['avatar']['thumbnails'], list) | |
4002 | or try_get( | |
4003 | self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer'), | |
4004 | lambda x: x['thumbnailRenderer']['playlistVideoThumbnailRenderer']['thumbnail']['thumbnails'], | |
4005 | list) | |
4006 | or []) | |
4007 | ||
4008 | thumbnails = [] | |
4009 | for t in thumbnails_list: | |
4010 | if not isinstance(t, dict): | |
4011 | continue | |
4012 | thumbnail_url = url_or_none(t.get('url')) | |
4013 | if not thumbnail_url: | |
4014 | continue | |
4015 | thumbnails.append({ | |
4016 | 'url': thumbnail_url, | |
4017 | 'width': int_or_none(t.get('width')), | |
4018 | 'height': int_or_none(t.get('height')), | |
4019 | }) | |
4020 | if playlist_id is None: | |
4021 | playlist_id = item_id | |
4022 | if title is None: | |
4023 | title = ( | |
4024 | try_get(data, lambda x: x['header']['hashtagHeaderRenderer']['hashtag']['simpleText']) | |
4025 | or playlist_id) | |
4026 | title += format_field(selected_tab, 'title', ' - %s') | |
4027 | title += format_field(selected_tab, 'expandedText', ' - %s') | |
4028 | metadata = { | |
4029 | 'playlist_id': playlist_id, | |
4030 | 'playlist_title': title, | |
4031 | 'playlist_description': description, | |
4032 | 'uploader': channel_name, | |
4033 | 'uploader_id': channel_id, | |
4034 | 'uploader_url': channel_url, | |
4035 | 'thumbnails': thumbnails, | |
4036 | 'tags': tags, | |
4037 | } | |
4038 | availability = self._extract_availability(data) | |
4039 | if availability: | |
4040 | metadata['availability'] = availability | |
4041 | if not channel_id: | |
4042 | metadata.update(self._extract_uploader(data)) | |
4043 | metadata.update({ | |
4044 | 'channel': metadata['uploader'], | |
4045 | 'channel_id': metadata['uploader_id'], | |
4046 | 'channel_url': metadata['uploader_url']}) | |
4047 | ytcfg = self.extract_ytcfg(item_id, webpage) | |
4048 | return self.playlist_result( | |
4049 | self._entries( | |
4050 | selected_tab, playlist_id, | |
4051 | self._extract_identity_token(webpage, item_id), | |
4052 | self._extract_account_syncid(ytcfg, data), ytcfg), | |
4053 | **metadata) | |
4054 | ||
4055 | def _extract_mix_playlist(self, playlist, playlist_id, data, webpage): | |
4056 | first_id = last_id = None | |
4057 | ytcfg = self.extract_ytcfg(playlist_id, webpage) | |
4058 | headers = self.generate_api_headers( | |
4059 | ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data), | |
4060 | identity_token=self._extract_identity_token(webpage, item_id=playlist_id)) | |
4061 | for page_num in itertools.count(1): | |
4062 | videos = list(self._playlist_entries(playlist)) | |
4063 | if not videos: | |
4064 | return | |
4065 | start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1 | |
4066 | if start >= len(videos): | |
4067 | return | |
4068 | for video in videos[start:]: | |
4069 | if video['id'] == first_id: | |
4070 | self.to_screen('First video %s found again; Assuming end of Mix' % first_id) | |
4071 | return | |
4072 | yield video | |
4073 | first_id = first_id or videos[0]['id'] | |
4074 | last_id = videos[-1]['id'] | |
4075 | watch_endpoint = try_get( | |
4076 | playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint']) | |
4077 | query = { | |
4078 | 'playlistId': playlist_id, | |
4079 | 'videoId': watch_endpoint.get('videoId') or last_id, | |
4080 | 'index': watch_endpoint.get('index') or len(videos), | |
4081 | 'params': watch_endpoint.get('params') or 'OAE%3D' | |
4082 | } | |
4083 | response = self._extract_response( | |
4084 | item_id='%s page %d' % (playlist_id, page_num), | |
4085 | query=query, ep='next', headers=headers, ytcfg=ytcfg, | |
4086 | check_get_keys='contents' | |
4087 | ) | |
4088 | playlist = try_get( | |
4089 | response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict) | |
4090 | ||
4091 | def _extract_from_playlist(self, item_id, url, data, playlist, webpage): | |
4092 | title = playlist.get('title') or try_get( | |
4093 | data, lambda x: x['titleText']['simpleText'], compat_str) | |
4094 | playlist_id = playlist.get('playlistId') or item_id | |
4095 | ||
4096 | # Delegating everything except mix playlists to regular tab-based playlist URL | |
4097 | playlist_url = urljoin(url, try_get( | |
4098 | playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'], | |
4099 | compat_str)) | |
4100 | if playlist_url and playlist_url != url: | |
4101 | return self.url_result( | |
4102 | playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id, | |
4103 | video_title=title) | |
4104 | ||
4105 | return self.playlist_result( | |
4106 | self._extract_mix_playlist(playlist, playlist_id, data, webpage), | |
4107 | playlist_id=playlist_id, playlist_title=title) | |
4108 | ||
4109 | def _extract_availability(self, data): | |
4110 | """ | |
4111 | Gets the availability of a given playlist/tab. | |
4112 | Note: Unless YouTube tells us explicitly, we do not assume it is public | |
4113 | @param data: response | |
4114 | """ | |
4115 | is_private = is_unlisted = None | |
4116 | renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {} | |
4117 | badge_labels = self._extract_badges(renderer) | |
4118 | ||
4119 | # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge | |
4120 | privacy_dropdown_entries = try_get( | |
4121 | renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or [] | |
4122 | for renderer_dict in privacy_dropdown_entries: | |
4123 | is_selected = try_get( | |
4124 | renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False | |
4125 | if not is_selected: | |
4126 | continue | |
4127 | label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label')) | |
4128 | if label: | |
4129 | badge_labels.add(label.lower()) | |
4130 | break | |
4131 | ||
4132 | for badge_label in badge_labels: | |
4133 | if badge_label == 'unlisted': | |
4134 | is_unlisted = True | |
4135 | elif badge_label == 'private': | |
4136 | is_private = True | |
4137 | elif badge_label == 'public': | |
4138 | is_unlisted = is_private = False | |
4139 | return self._availability(is_private, False, False, False, is_unlisted) | |
4140 | ||
4141 | @staticmethod | |
4142 | def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict): | |
4143 | sidebar_renderer = try_get( | |
4144 | data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or [] | |
4145 | for item in sidebar_renderer: | |
4146 | renderer = try_get(item, lambda x: x[info_renderer], expected_type) | |
4147 | if renderer: | |
4148 | return renderer | |
4149 | ||
4150 | def _reload_with_unavailable_videos(self, item_id, data, webpage): | |
4151 | """ | |
4152 | Get playlist with unavailable videos if the 'show unavailable videos' button exists. | |
4153 | """ | |
4154 | browse_id = params = None | |
4155 | renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') | |
4156 | if not renderer: | |
4157 | return | |
4158 | menu_renderer = try_get( | |
4159 | renderer, lambda x: x['menu']['menuRenderer']['items'], list) or [] | |
4160 | for menu_item in menu_renderer: | |
4161 | if not isinstance(menu_item, dict): | |
4162 | continue | |
4163 | nav_item_renderer = menu_item.get('menuNavigationItemRenderer') | |
4164 | text = try_get( | |
4165 | nav_item_renderer, lambda x: x['text']['simpleText'], compat_str) | |
4166 | if not text or text.lower() != 'show unavailable videos': | |
4167 | continue | |
4168 | browse_endpoint = try_get( | |
4169 | nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {} | |
4170 | browse_id = browse_endpoint.get('browseId') | |
4171 | params = browse_endpoint.get('params') | |
4172 | break | |
4173 | ||
4174 | ytcfg = self.extract_ytcfg(item_id, webpage) | |
4175 | headers = self.generate_api_headers( | |
4176 | ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data), | |
4177 | identity_token=self._extract_identity_token(webpage, item_id=item_id), | |
4178 | visitor_data=try_get( | |
4179 | self._extract_context(ytcfg), lambda x: x['client']['visitorData'], compat_str)) | |
4180 | query = { | |
4181 | 'params': params or 'wgYCCAA=', | |
4182 | 'browseId': browse_id or 'VL%s' % item_id | |
4183 | } | |
4184 | return self._extract_response( | |
4185 | item_id=item_id, headers=headers, query=query, | |
4186 | check_get_keys='contents', fatal=False, ytcfg=ytcfg, | |
4187 | note='Downloading API JSON with unavailable videos') | |
4188 | ||
4189 | def _extract_webpage(self, url, item_id): | |
4190 | retries = self.get_param('extractor_retries', 3) | |
4191 | count = -1 | |
4192 | last_error = 'Incomplete yt initial data recieved' | |
4193 | while count < retries: | |
4194 | count += 1 | |
4195 | # Sometimes youtube returns a webpage with incomplete ytInitialData | |
4196 | # See: https://github.com/yt-dlp/yt-dlp/issues/116 | |
4197 | if count: | |
4198 | self.report_warning('%s. Retrying ...' % last_error) | |
4199 | webpage = self._download_webpage( | |
4200 | url, item_id, | |
4201 | 'Downloading webpage%s' % (' (retry #%d)' % count if count else '')) | |
4202 | data = self.extract_yt_initial_data(item_id, webpage) | |
4203 | if data.get('contents') or data.get('currentVideoEndpoint'): | |
4204 | break | |
4205 | # Extract alerts here only when there is error | |
4206 | self._extract_and_report_alerts(data) | |
4207 | if count >= retries: | |
4208 | raise ExtractorError(last_error) | |
4209 | return webpage, data | |
4210 | ||
4211 | @staticmethod | |
4212 | def _smuggle_data(entries, data): | |
4213 | for entry in entries: | |
4214 | if data: | |
4215 | entry['url'] = smuggle_url(entry['url'], data) | |
4216 | yield entry | |
4217 | ||
4218 | def _real_extract(self, url): | |
4219 | url, smuggled_data = unsmuggle_url(url, {}) | |
4220 | if self.is_music_url(url): | |
4221 | smuggled_data['is_music_url'] = True | |
4222 | info_dict = self.__real_extract(url, smuggled_data) | |
4223 | if info_dict.get('entries'): | |
4224 | info_dict['entries'] = self._smuggle_data(info_dict['entries'], smuggled_data) | |
4225 | return info_dict | |
4226 | ||
4227 | _url_re = re.compile(r'(?P<pre>%s)(?(channel_type)(?P<tab>/\w+))?(?P<post>.*)$' % _VALID_URL) | |
4228 | ||
4229 | def __real_extract(self, url, smuggled_data): | |
4230 | item_id = self._match_id(url) | |
4231 | url = compat_urlparse.urlunparse( | |
4232 | compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com')) | |
4233 | compat_opts = self.get_param('compat_opts', []) | |
4234 | ||
4235 | def get_mobj(url): | |
4236 | mobj = self._url_re.match(url).groupdict() | |
4237 | mobj.update((k, '') for k, v in mobj.items() if v is None) | |
4238 | return mobj | |
4239 | ||
4240 | mobj = get_mobj(url) | |
4241 | # Youtube returns incomplete data if tabname is not lower case | |
4242 | pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel'] | |
4243 | ||
4244 | if is_channel: | |
4245 | if smuggled_data.get('is_music_url'): | |
4246 | if item_id[:2] == 'VL': | |
4247 | # Youtube music VL channels have an equivalent playlist | |
4248 | item_id = item_id[2:] | |
4249 | pre, tab, post, is_channel = 'https://www.youtube.com/playlist?list=%s' % item_id, '', '', False | |
4250 | elif item_id[:2] == 'MP': | |
4251 | # Youtube music albums (/channel/MP...) have a OLAK playlist that can be extracted from the webpage | |
4252 | item_id = self._search_regex( | |
4253 | r'\\x22audioPlaylistId\\x22:\\x22([0-9A-Za-z_-]+)\\x22', | |
4254 | self._download_webpage('https://music.youtube.com/channel/%s' % item_id, item_id), | |
4255 | 'playlist id') | |
4256 | pre, tab, post, is_channel = 'https://www.youtube.com/playlist?list=%s' % item_id, '', '', False | |
4257 | elif mobj['channel_type'] == 'browse': | |
4258 | # Youtube music /browse/ should be changed to /channel/ | |
4259 | pre = 'https://www.youtube.com/channel/%s' % item_id | |
4260 | if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts: | |
4261 | # Home URLs should redirect to /videos/ | |
4262 | self.report_warning( | |
4263 | 'A channel/user page was given. All the channel\'s videos will be downloaded. ' | |
4264 | 'To download only the videos in the home page, add a "/featured" to the URL') | |
4265 | tab = '/videos' | |
4266 | ||
4267 | url = ''.join((pre, tab, post)) | |
4268 | mobj = get_mobj(url) | |
4269 | ||
4270 | # Handle both video/playlist URLs | |
4271 | qs = parse_qs(url) | |
4272 | video_id = qs.get('v', [None])[0] | |
4273 | playlist_id = qs.get('list', [None])[0] | |
4274 | ||
4275 | if not video_id and mobj['not_channel'].startswith('watch'): | |
4276 | if not playlist_id: | |
4277 | # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable | |
4278 | raise ExtractorError('Unable to recognize tab page') | |
4279 | # Common mistake: https://www.youtube.com/watch?list=playlist_id | |
4280 | self.report_warning('A video URL was given without video ID. Trying to download playlist %s' % playlist_id) | |
4281 | url = 'https://www.youtube.com/playlist?list=%s' % playlist_id | |
4282 | mobj = get_mobj(url) | |
4283 | ||
4284 | if video_id and playlist_id: | |
4285 | if self.get_param('noplaylist'): | |
4286 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
4287 | return self.url_result(f'https://www.youtube.com/watch?v={video_id}', ie=YoutubeIE.ie_key(), video_id=video_id) | |
4288 | self.to_screen('Downloading playlist %s; add --no-playlist to just download video %s' % (playlist_id, video_id)) | |
4289 | ||
4290 | webpage, data = self._extract_webpage(url, item_id) | |
4291 | ||
4292 | tabs = try_get( | |
4293 | data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list) | |
4294 | if tabs: | |
4295 | selected_tab = self._extract_selected_tab(tabs) | |
4296 | tab_name = selected_tab.get('title', '') | |
4297 | if 'no-youtube-channel-redirect' not in compat_opts: | |
4298 | if mobj['tab'] == '/live': | |
4299 | # Live tab should have redirected to the video | |
4300 | raise ExtractorError('The channel is not currently live', expected=True) | |
4301 | if mobj['tab'] == '/videos' and tab_name.lower() != mobj['tab'][1:]: | |
4302 | if not mobj['not_channel'] and item_id[:2] == 'UC': | |
4303 | # Topic channels don't have /videos. Use the equivalent playlist instead | |
4304 | 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:])) | |
4305 | pl_id = 'UU%s' % item_id[2:] | |
4306 | pl_url = 'https://www.youtube.com/playlist?list=%s%s' % (pl_id, mobj['post']) | |
4307 | try: | |
4308 | pl_webpage, pl_data = self._extract_webpage(pl_url, pl_id) | |
4309 | for alert_type, alert_message in self._extract_alerts(pl_data): | |
4310 | if alert_type == 'error': | |
4311 | raise ExtractorError('Youtube said: %s' % alert_message) | |
4312 | item_id, url, webpage, data = pl_id, pl_url, pl_webpage, pl_data | |
4313 | except ExtractorError: | |
4314 | self.report_warning('The playlist gave error. Falling back to channel URL') | |
4315 | else: | |
4316 | self.report_warning('The URL does not have a %s tab. %s is being downloaded instead' % (mobj['tab'][1:], tab_name)) | |
4317 | ||
4318 | self.write_debug('Final URL: %s' % url) | |
4319 | ||
4320 | # YouTube sometimes provides a button to reload playlist with unavailable videos. | |
4321 | if 'no-youtube-unavailable-videos' not in compat_opts: | |
4322 | data = self._reload_with_unavailable_videos(item_id, data, webpage) or data | |
4323 | self._extract_and_report_alerts(data, only_once=True) | |
4324 | tabs = try_get( | |
4325 | data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list) | |
4326 | if tabs: | |
4327 | return self._extract_from_tabs(item_id, webpage, data, tabs) | |
4328 | ||
4329 | playlist = try_get( | |
4330 | data, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict) | |
4331 | if playlist: | |
4332 | return self._extract_from_playlist(item_id, url, data, playlist, webpage) | |
4333 | ||
4334 | video_id = try_get( | |
4335 | data, lambda x: x['currentVideoEndpoint']['watchEndpoint']['videoId'], | |
4336 | compat_str) or video_id | |
4337 | if video_id: | |
4338 | if mobj['tab'] != '/live': # live tab is expected to redirect to video | |
4339 | self.report_warning('Unable to recognize playlist. Downloading just video %s' % video_id) | |
4340 | return self.url_result(f'https://www.youtube.com/watch?v={video_id}', ie=YoutubeIE.ie_key(), video_id=video_id) | |
4341 | ||
4342 | raise ExtractorError('Unable to recognize tab page') | |
4343 | ||
4344 | ||
4345 | class YoutubePlaylistIE(InfoExtractor): | |
4346 | IE_DESC = 'YouTube.com playlists' | |
4347 | _VALID_URL = r'''(?x)(?: | |
4348 | (?:https?://)? | |
4349 | (?:\w+\.)? | |
4350 | (?: | |
4351 | (?: | |
4352 | youtube(?:kids)?\.com| | |
4353 | invidio\.us | |
4354 | ) | |
4355 | /.*?\?.*?\blist= | |
4356 | )? | |
4357 | (?P<id>%(playlist_id)s) | |
4358 | )''' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE} | |
4359 | IE_NAME = 'youtube:playlist' | |
4360 | _TESTS = [{ | |
4361 | 'note': 'issue #673', | |
4362 | 'url': 'PLBB231211A4F62143', | |
4363 | 'info_dict': { | |
4364 | 'title': '[OLD]Team Fortress 2 (Class-based LP)', | |
4365 | 'id': 'PLBB231211A4F62143', | |
4366 | 'uploader': 'Wickydoo', | |
4367 | 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q', | |
4368 | 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2', | |
4369 | }, | |
4370 | 'playlist_mincount': 29, | |
4371 | }, { | |
4372 | 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
4373 | 'info_dict': { | |
4374 | 'title': 'YDL_safe_search', | |
4375 | 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
4376 | }, | |
4377 | 'playlist_count': 2, | |
4378 | 'skip': 'This playlist is private', | |
4379 | }, { | |
4380 | 'note': 'embedded', | |
4381 | 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', | |
4382 | 'playlist_count': 4, | |
4383 | 'info_dict': { | |
4384 | 'title': 'JODA15', | |
4385 | 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', | |
4386 | 'uploader': 'milan', | |
4387 | 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw', | |
4388 | } | |
4389 | }, { | |
4390 | 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', | |
4391 | 'playlist_mincount': 654, | |
4392 | 'info_dict': { | |
4393 | 'title': '2018 Chinese New Singles (11/6 updated)', | |
4394 | 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', | |
4395 | 'uploader': 'LBK', | |
4396 | 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA', | |
4397 | 'description': 'md5:da521864744d60a198e3a88af4db0d9d', | |
4398 | } | |
4399 | }, { | |
4400 | 'url': 'TLGGrESM50VT6acwMjAyMjAxNw', | |
4401 | 'only_matching': True, | |
4402 | }, { | |
4403 | # music album playlist | |
4404 | 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM', | |
4405 | 'only_matching': True, | |
4406 | }] | |
4407 | ||
4408 | @classmethod | |
4409 | def suitable(cls, url): | |
4410 | if YoutubeTabIE.suitable(url): | |
4411 | return False | |
4412 | # Hack for lazy extractors until more generic solution is implemented | |
4413 | # (see #28780) | |
4414 | from .youtube import parse_qs | |
4415 | qs = parse_qs(url) | |
4416 | if qs.get('v', [None])[0]: | |
4417 | return False | |
4418 | return super(YoutubePlaylistIE, cls).suitable(url) | |
4419 | ||
4420 | def _real_extract(self, url): | |
4421 | playlist_id = self._match_id(url) | |
4422 | is_music_url = YoutubeBaseInfoExtractor.is_music_url(url) | |
4423 | url = update_url_query( | |
4424 | 'https://www.youtube.com/playlist', | |
4425 | parse_qs(url) or {'list': playlist_id}) | |
4426 | if is_music_url: | |
4427 | url = smuggle_url(url, {'is_music_url': True}) | |
4428 | return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
4429 | ||
4430 | ||
4431 | class YoutubeYtBeIE(InfoExtractor): | |
4432 | IE_DESC = 'youtu.be' | |
4433 | _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} | |
4434 | _TESTS = [{ | |
4435 | 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5', | |
4436 | 'info_dict': { | |
4437 | 'id': 'yeWKywCrFtk', | |
4438 | 'ext': 'mp4', | |
4439 | 'title': 'Small Scale Baler and Braiding Rugs', | |
4440 | 'uploader': 'Backus-Page House Museum', | |
4441 | 'uploader_id': 'backuspagemuseum', | |
4442 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum', | |
4443 | 'upload_date': '20161008', | |
4444 | 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a', | |
4445 | 'categories': ['Nonprofits & Activism'], | |
4446 | 'tags': list, | |
4447 | 'like_count': int, | |
4448 | 'dislike_count': int, | |
4449 | }, | |
4450 | 'params': { | |
4451 | 'noplaylist': True, | |
4452 | 'skip_download': True, | |
4453 | }, | |
4454 | }, { | |
4455 | 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21', | |
4456 | 'only_matching': True, | |
4457 | }] | |
4458 | ||
4459 | def _real_extract(self, url): | |
4460 | mobj = self._match_valid_url(url) | |
4461 | video_id = mobj.group('id') | |
4462 | playlist_id = mobj.group('playlist_id') | |
4463 | return self.url_result( | |
4464 | update_url_query('https://www.youtube.com/watch', { | |
4465 | 'v': video_id, | |
4466 | 'list': playlist_id, | |
4467 | 'feature': 'youtu.be', | |
4468 | }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
4469 | ||
4470 | ||
4471 | class YoutubeYtUserIE(InfoExtractor): | |
4472 | IE_DESC = 'YouTube.com user videos, URL or "ytuser" keyword' | |
4473 | _VALID_URL = r'ytuser:(?P<id>.+)' | |
4474 | _TESTS = [{ | |
4475 | 'url': 'ytuser:phihag', | |
4476 | 'only_matching': True, | |
4477 | }] | |
4478 | ||
4479 | def _real_extract(self, url): | |
4480 | user_id = self._match_id(url) | |
4481 | return self.url_result( | |
4482 | 'https://www.youtube.com/user/%s' % user_id, | |
4483 | ie=YoutubeTabIE.ie_key(), video_id=user_id) | |
4484 | ||
4485 | ||
4486 | class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): | |
4487 | IE_NAME = 'youtube:favorites' | |
4488 | IE_DESC = 'YouTube.com liked videos, ":ytfav" for short (requires authentication)' | |
4489 | _VALID_URL = r':ytfav(?:ou?rite)?s?' | |
4490 | _LOGIN_REQUIRED = True | |
4491 | _TESTS = [{ | |
4492 | 'url': ':ytfav', | |
4493 | 'only_matching': True, | |
4494 | }, { | |
4495 | 'url': ':ytfavorites', | |
4496 | 'only_matching': True, | |
4497 | }] | |
4498 | ||
4499 | def _real_extract(self, url): | |
4500 | return self.url_result( | |
4501 | 'https://www.youtube.com/playlist?list=LL', | |
4502 | ie=YoutubeTabIE.ie_key()) | |
4503 | ||
4504 | ||
4505 | class YoutubeSearchIE(SearchInfoExtractor, YoutubeTabIE): | |
4506 | IE_DESC = 'YouTube.com searches, "ytsearch" keyword' | |
4507 | # there doesn't appear to be a real limit, for example if you search for | |
4508 | # 'python' you get more than 8.000.000 results | |
4509 | _MAX_RESULTS = float('inf') | |
4510 | IE_NAME = 'youtube:search' | |
4511 | _SEARCH_KEY = 'ytsearch' | |
4512 | _SEARCH_PARAMS = None | |
4513 | _TESTS = [] | |
4514 | ||
4515 | def _entries(self, query, n): | |
4516 | data = {'query': query} | |
4517 | if self._SEARCH_PARAMS: | |
4518 | data['params'] = self._SEARCH_PARAMS | |
4519 | total = 0 | |
4520 | continuation = {} | |
4521 | for page_num in itertools.count(1): | |
4522 | data.update(continuation) | |
4523 | search = self._extract_response( | |
4524 | item_id='query "%s" page %s' % (query, page_num), ep='search', query=data, | |
4525 | check_get_keys=('contents', 'onResponseReceivedCommands') | |
4526 | ) | |
4527 | if not search: | |
4528 | break | |
4529 | slr_contents = try_get( | |
4530 | search, | |
4531 | (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'], | |
4532 | lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']), | |
4533 | list) | |
4534 | if not slr_contents: | |
4535 | break | |
4536 | ||
4537 | # Youtube sometimes adds promoted content to searches, | |
4538 | # changing the index location of videos and token. | |
4539 | # So we search through all entries till we find them. | |
4540 | continuation = None | |
4541 | for slr_content in slr_contents: | |
4542 | if not continuation: | |
4543 | continuation = self._extract_continuation({'contents': [slr_content]}) | |
4544 | ||
4545 | isr_contents = try_get( | |
4546 | slr_content, | |
4547 | lambda x: x['itemSectionRenderer']['contents'], | |
4548 | list) | |
4549 | if not isr_contents: | |
4550 | continue | |
4551 | for content in isr_contents: | |
4552 | if not isinstance(content, dict): | |
4553 | continue | |
4554 | video = content.get('videoRenderer') | |
4555 | if not isinstance(video, dict): | |
4556 | continue | |
4557 | video_id = video.get('videoId') | |
4558 | if not video_id: | |
4559 | continue | |
4560 | ||
4561 | yield self._extract_video(video) | |
4562 | total += 1 | |
4563 | if total == n: | |
4564 | return | |
4565 | ||
4566 | if not continuation: | |
4567 | break | |
4568 | ||
4569 | def _get_n_results(self, query, n): | |
4570 | """Get a specified number of results for a query""" | |
4571 | return self.playlist_result(self._entries(query, n), query, query) | |
4572 | ||
4573 | ||
4574 | class YoutubeSearchDateIE(YoutubeSearchIE): | |
4575 | IE_NAME = YoutubeSearchIE.IE_NAME + ':date' | |
4576 | _SEARCH_KEY = 'ytsearchdate' | |
4577 | IE_DESC = 'YouTube.com searches, newest videos first, "ytsearchdate" keyword' | |
4578 | _SEARCH_PARAMS = 'CAI%3D' | |
4579 | ||
4580 | ||
4581 | class YoutubeSearchURLIE(YoutubeSearchIE): | |
4582 | IE_DESC = 'YouTube.com search URLs' | |
4583 | IE_NAME = YoutubeSearchIE.IE_NAME + '_url' | |
4584 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)' | |
4585 | # _MAX_RESULTS = 100 | |
4586 | _TESTS = [{ | |
4587 | 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', | |
4588 | 'playlist_mincount': 5, | |
4589 | 'info_dict': { | |
4590 | 'id': 'youtube-dl test video', | |
4591 | 'title': 'youtube-dl test video', | |
4592 | } | |
4593 | }, { | |
4594 | 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB', | |
4595 | 'only_matching': True, | |
4596 | }] | |
4597 | ||
4598 | @classmethod | |
4599 | def _make_valid_url(cls): | |
4600 | return cls._VALID_URL | |
4601 | ||
4602 | def _real_extract(self, url): | |
4603 | qs = parse_qs(url) | |
4604 | query = (qs.get('search_query') or qs.get('q'))[0] | |
4605 | self._SEARCH_PARAMS = qs.get('sp', ('',))[0] | |
4606 | return self._get_n_results(query, self._MAX_RESULTS) | |
4607 | ||
4608 | ||
4609 | class YoutubeFeedsInfoExtractor(YoutubeTabIE): | |
4610 | """ | |
4611 | Base class for feed extractors | |
4612 | Subclasses must define the _FEED_NAME property. | |
4613 | """ | |
4614 | _LOGIN_REQUIRED = True | |
4615 | _TESTS = [] | |
4616 | ||
4617 | @property | |
4618 | def IE_NAME(self): | |
4619 | return 'youtube:%s' % self._FEED_NAME | |
4620 | ||
4621 | def _real_extract(self, url): | |
4622 | return self.url_result( | |
4623 | 'https://www.youtube.com/feed/%s' % self._FEED_NAME, | |
4624 | ie=YoutubeTabIE.ie_key()) | |
4625 | ||
4626 | ||
4627 | class YoutubeWatchLaterIE(InfoExtractor): | |
4628 | IE_NAME = 'youtube:watchlater' | |
4629 | IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)' | |
4630 | _VALID_URL = r':ytwatchlater' | |
4631 | _TESTS = [{ | |
4632 | 'url': ':ytwatchlater', | |
4633 | 'only_matching': True, | |
4634 | }] | |
4635 | ||
4636 | def _real_extract(self, url): | |
4637 | return self.url_result( | |
4638 | 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key()) | |
4639 | ||
4640 | ||
4641 | class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): | |
4642 | IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)' | |
4643 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?' | |
4644 | _FEED_NAME = 'recommended' | |
4645 | _LOGIN_REQUIRED = False | |
4646 | _TESTS = [{ | |
4647 | 'url': ':ytrec', | |
4648 | 'only_matching': True, | |
4649 | }, { | |
4650 | 'url': ':ytrecommended', | |
4651 | 'only_matching': True, | |
4652 | }, { | |
4653 | 'url': 'https://youtube.com', | |
4654 | 'only_matching': True, | |
4655 | }] | |
4656 | ||
4657 | ||
4658 | class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): | |
4659 | IE_DESC = 'YouTube.com subscriptions feed, ":ytsubs" for short (requires authentication)' | |
4660 | _VALID_URL = r':ytsub(?:scription)?s?' | |
4661 | _FEED_NAME = 'subscriptions' | |
4662 | _TESTS = [{ | |
4663 | 'url': ':ytsubs', | |
4664 | 'only_matching': True, | |
4665 | }, { | |
4666 | 'url': ':ytsubscriptions', | |
4667 | 'only_matching': True, | |
4668 | }] | |
4669 | ||
4670 | ||
4671 | class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): | |
4672 | IE_DESC = 'Youtube watch history, ":ythis" for short (requires authentication)' | |
4673 | _VALID_URL = r':ythis(?:tory)?' | |
4674 | _FEED_NAME = 'history' | |
4675 | _TESTS = [{ | |
4676 | 'url': ':ythistory', | |
4677 | 'only_matching': True, | |
4678 | }] | |
4679 | ||
4680 | ||
4681 | class YoutubeTruncatedURLIE(InfoExtractor): | |
4682 | IE_NAME = 'youtube:truncated_url' | |
4683 | IE_DESC = False # Do not list | |
4684 | _VALID_URL = r'''(?x) | |
4685 | (?:https?://)? | |
4686 | (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/ | |
4687 | (?:watch\?(?: | |
4688 | feature=[a-z_]+| | |
4689 | annotation_id=annotation_[^&]+| | |
4690 | x-yt-cl=[0-9]+| | |
4691 | hl=[^&]*| | |
4692 | t=[0-9]+ | |
4693 | )? | |
4694 | | | |
4695 | attribution_link\?a=[^&]+ | |
4696 | ) | |
4697 | $ | |
4698 | ''' | |
4699 | ||
4700 | _TESTS = [{ | |
4701 | 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041', | |
4702 | 'only_matching': True, | |
4703 | }, { | |
4704 | 'url': 'https://www.youtube.com/watch?', | |
4705 | 'only_matching': True, | |
4706 | }, { | |
4707 | 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534', | |
4708 | 'only_matching': True, | |
4709 | }, { | |
4710 | 'url': 'https://www.youtube.com/watch?feature=foo', | |
4711 | 'only_matching': True, | |
4712 | }, { | |
4713 | 'url': 'https://www.youtube.com/watch?hl=en-GB', | |
4714 | 'only_matching': True, | |
4715 | }, { | |
4716 | 'url': 'https://www.youtube.com/watch?t=2372', | |
4717 | 'only_matching': True, | |
4718 | }] | |
4719 | ||
4720 | def _real_extract(self, url): | |
4721 | raise ExtractorError( | |
4722 | 'Did you forget to quote the URL? Remember that & is a meta ' | |
4723 | 'character in most shells, so you want to put the URL in quotes, ' | |
4724 | 'like youtube-dl ' | |
4725 | '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' | |
4726 | ' or simply youtube-dl BaW_jenozKc .', | |
4727 | expected=True) | |
4728 | ||
4729 | ||
4730 | class YoutubeClipIE(InfoExtractor): | |
4731 | IE_NAME = 'youtube:clip' | |
4732 | IE_DESC = False # Do not list | |
4733 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/' | |
4734 | ||
4735 | def _real_extract(self, url): | |
4736 | self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead') | |
4737 | return self.url_result(url, 'Generic') | |
4738 | ||
4739 | ||
4740 | class YoutubeTruncatedIDIE(InfoExtractor): | |
4741 | IE_NAME = 'youtube:truncated_id' | |
4742 | IE_DESC = False # Do not list | |
4743 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$' | |
4744 | ||
4745 | _TESTS = [{ | |
4746 | 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob', | |
4747 | 'only_matching': True, | |
4748 | }] | |
4749 | ||
4750 | def _real_extract(self, url): | |
4751 | video_id = self._match_id(url) | |
4752 | raise ExtractorError( | |
4753 | 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url), | |
4754 | expected=True) |