]>
Commit | Line | Data |
---|---|---|
1 | # coding: utf-8 | |
2 | ||
3 | from __future__ import unicode_literals | |
4 | ||
5 | import itertools | |
6 | import json | |
7 | import os.path | |
8 | import random | |
9 | import re | |
10 | import time | |
11 | import traceback | |
12 | ||
13 | from .common import InfoExtractor, SearchInfoExtractor | |
14 | from ..compat import ( | |
15 | compat_chr, | |
16 | compat_HTTPError, | |
17 | compat_kwargs, | |
18 | compat_parse_qs, | |
19 | compat_str, | |
20 | compat_urllib_parse_unquote_plus, | |
21 | compat_urllib_parse_urlencode, | |
22 | compat_urllib_parse_urlparse, | |
23 | compat_urlparse, | |
24 | ) | |
25 | from ..jsinterp import JSInterpreter | |
26 | from ..utils import ( | |
27 | clean_html, | |
28 | ExtractorError, | |
29 | format_field, | |
30 | float_or_none, | |
31 | int_or_none, | |
32 | mimetype2ext, | |
33 | parse_codecs, | |
34 | parse_duration, | |
35 | qualities, | |
36 | remove_start, | |
37 | smuggle_url, | |
38 | str_or_none, | |
39 | str_to_int, | |
40 | try_get, | |
41 | unescapeHTML, | |
42 | unified_strdate, | |
43 | unsmuggle_url, | |
44 | update_url_query, | |
45 | url_or_none, | |
46 | urlencode_postdata, | |
47 | urljoin, | |
48 | ) | |
49 | ||
50 | ||
51 | class YoutubeBaseInfoExtractor(InfoExtractor): | |
52 | """Provide base functions for Youtube extractors""" | |
53 | _LOGIN_URL = 'https://accounts.google.com/ServiceLogin' | |
54 | _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge' | |
55 | ||
56 | _LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup' | |
57 | _CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge' | |
58 | _TFA_URL = 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}' | |
59 | ||
60 | _RESERVED_NAMES = ( | |
61 | r'embed|e|watch_popup|channel|c|user|playlist|watch|w|v|movies|results|shared|hashtag|' | |
62 | r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout|' | |
63 | r'feed/(?:watch_later|history|subscriptions|library|trending|recommended)') | |
64 | ||
65 | _NETRC_MACHINE = 'youtube' | |
66 | # If True it will raise an error if no login info is provided | |
67 | _LOGIN_REQUIRED = False | |
68 | ||
69 | _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)' | |
70 | ||
71 | def _ids_to_results(self, ids): | |
72 | return [ | |
73 | self.url_result(vid_id, 'Youtube', video_id=vid_id) | |
74 | for vid_id in ids] | |
75 | ||
76 | def _login(self): | |
77 | """ | |
78 | Attempt to log in to YouTube. | |
79 | True is returned if successful or skipped. | |
80 | False is returned if login failed. | |
81 | ||
82 | If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised. | |
83 | """ | |
84 | username, password = self._get_login_info() | |
85 | # No authentication to be performed | |
86 | if username is None: | |
87 | if self._LOGIN_REQUIRED and self._downloader.params.get('cookiefile') is None: | |
88 | raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) | |
89 | # if self._downloader.params.get('cookiefile'): # TODO remove 'and False' later - too many people using outdated cookies and open issues, remind them. | |
90 | # self.to_screen('[Cookies] Reminder - Make sure to always use up to date cookies!') | |
91 | return True | |
92 | ||
93 | login_page = self._download_webpage( | |
94 | self._LOGIN_URL, None, | |
95 | note='Downloading login page', | |
96 | errnote='unable to fetch login page', fatal=False) | |
97 | if login_page is False: | |
98 | return | |
99 | ||
100 | login_form = self._hidden_inputs(login_page) | |
101 | ||
102 | def req(url, f_req, note, errnote): | |
103 | data = login_form.copy() | |
104 | data.update({ | |
105 | 'pstMsg': 1, | |
106 | 'checkConnection': 'youtube', | |
107 | 'checkedDomains': 'youtube', | |
108 | 'hl': 'en', | |
109 | 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]', | |
110 | 'f.req': json.dumps(f_req), | |
111 | 'flowName': 'GlifWebSignIn', | |
112 | 'flowEntry': 'ServiceLogin', | |
113 | # TODO: reverse actual botguard identifier generation algo | |
114 | 'bgRequest': '["identifier",""]', | |
115 | }) | |
116 | return self._download_json( | |
117 | url, None, note=note, errnote=errnote, | |
118 | transform_source=lambda s: re.sub(r'^[^[]*', '', s), | |
119 | fatal=False, | |
120 | data=urlencode_postdata(data), headers={ | |
121 | 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8', | |
122 | 'Google-Accounts-XSRF': 1, | |
123 | }) | |
124 | ||
125 | def warn(message): | |
126 | self._downloader.report_warning(message) | |
127 | ||
128 | lookup_req = [ | |
129 | username, | |
130 | None, [], None, 'US', None, None, 2, False, True, | |
131 | [ | |
132 | None, None, | |
133 | [2, 1, None, 1, | |
134 | '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', | |
135 | None, [], 4], | |
136 | 1, [None, None, []], None, None, None, True | |
137 | ], | |
138 | username, | |
139 | ] | |
140 | ||
141 | lookup_results = req( | |
142 | self._LOOKUP_URL, lookup_req, | |
143 | 'Looking up account info', 'Unable to look up account info') | |
144 | ||
145 | if lookup_results is False: | |
146 | return False | |
147 | ||
148 | user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str) | |
149 | if not user_hash: | |
150 | warn('Unable to extract user hash') | |
151 | return False | |
152 | ||
153 | challenge_req = [ | |
154 | user_hash, | |
155 | None, 1, None, [1, None, None, None, [password, None, True]], | |
156 | [ | |
157 | 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], | |
158 | 1, [None, None, []], None, None, None, True | |
159 | ]] | |
160 | ||
161 | challenge_results = req( | |
162 | self._CHALLENGE_URL, challenge_req, | |
163 | 'Logging in', 'Unable to log in') | |
164 | ||
165 | if challenge_results is False: | |
166 | return | |
167 | ||
168 | login_res = try_get(challenge_results, lambda x: x[0][5], list) | |
169 | if login_res: | |
170 | login_msg = try_get(login_res, lambda x: x[5], compat_str) | |
171 | warn( | |
172 | 'Unable to login: %s' % 'Invalid password' | |
173 | if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg) | |
174 | return False | |
175 | ||
176 | res = try_get(challenge_results, lambda x: x[0][-1], list) | |
177 | if not res: | |
178 | warn('Unable to extract result entry') | |
179 | return False | |
180 | ||
181 | login_challenge = try_get(res, lambda x: x[0][0], list) | |
182 | if login_challenge: | |
183 | challenge_str = try_get(login_challenge, lambda x: x[2], compat_str) | |
184 | if challenge_str == 'TWO_STEP_VERIFICATION': | |
185 | # SEND_SUCCESS - TFA code has been successfully sent to phone | |
186 | # QUOTA_EXCEEDED - reached the limit of TFA codes | |
187 | status = try_get(login_challenge, lambda x: x[5], compat_str) | |
188 | if status == 'QUOTA_EXCEEDED': | |
189 | warn('Exceeded the limit of TFA codes, try later') | |
190 | return False | |
191 | ||
192 | tl = try_get(challenge_results, lambda x: x[1][2], compat_str) | |
193 | if not tl: | |
194 | warn('Unable to extract TL') | |
195 | return False | |
196 | ||
197 | tfa_code = self._get_tfa_info('2-step verification code') | |
198 | ||
199 | if not tfa_code: | |
200 | warn( | |
201 | 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>' | |
202 | '(Note that only TOTP (Google Authenticator App) codes work at this time.)') | |
203 | return False | |
204 | ||
205 | tfa_code = remove_start(tfa_code, 'G-') | |
206 | ||
207 | tfa_req = [ | |
208 | user_hash, None, 2, None, | |
209 | [ | |
210 | 9, None, None, None, None, None, None, None, | |
211 | [None, tfa_code, True, 2] | |
212 | ]] | |
213 | ||
214 | tfa_results = req( | |
215 | self._TFA_URL.format(tl), tfa_req, | |
216 | 'Submitting TFA code', 'Unable to submit TFA code') | |
217 | ||
218 | if tfa_results is False: | |
219 | return False | |
220 | ||
221 | tfa_res = try_get(tfa_results, lambda x: x[0][5], list) | |
222 | if tfa_res: | |
223 | tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str) | |
224 | warn( | |
225 | 'Unable to finish TFA: %s' % 'Invalid TFA code' | |
226 | if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg) | |
227 | return False | |
228 | ||
229 | check_cookie_url = try_get( | |
230 | tfa_results, lambda x: x[0][-1][2], compat_str) | |
231 | else: | |
232 | CHALLENGES = { | |
233 | 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.", | |
234 | 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.', | |
235 | 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.", | |
236 | } | |
237 | challenge = CHALLENGES.get( | |
238 | challenge_str, | |
239 | '%s returned error %s.' % (self.IE_NAME, challenge_str)) | |
240 | warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge) | |
241 | return False | |
242 | else: | |
243 | check_cookie_url = try_get(res, lambda x: x[2], compat_str) | |
244 | ||
245 | if not check_cookie_url: | |
246 | warn('Unable to extract CheckCookie URL') | |
247 | return False | |
248 | ||
249 | check_cookie_results = self._download_webpage( | |
250 | check_cookie_url, None, 'Checking cookie', fatal=False) | |
251 | ||
252 | if check_cookie_results is False: | |
253 | return False | |
254 | ||
255 | if 'https://myaccount.google.com/' not in check_cookie_results: | |
256 | warn('Unable to log in') | |
257 | return False | |
258 | ||
259 | return True | |
260 | ||
261 | def _download_webpage_handle(self, *args, **kwargs): | |
262 | query = kwargs.get('query', {}).copy() | |
263 | kwargs['query'] = query | |
264 | return super(YoutubeBaseInfoExtractor, self)._download_webpage_handle( | |
265 | *args, **compat_kwargs(kwargs)) | |
266 | ||
267 | def _real_initialize(self): | |
268 | if self._downloader is None: | |
269 | return | |
270 | if not self._login(): | |
271 | return | |
272 | ||
273 | _DEFAULT_API_DATA = { | |
274 | 'context': { | |
275 | 'client': { | |
276 | 'clientName': 'WEB', | |
277 | 'clientVersion': '2.20201021.03.00', | |
278 | } | |
279 | }, | |
280 | } | |
281 | ||
282 | _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;' | |
283 | _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;' | |
284 | _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)' | |
285 | ||
286 | def _call_api(self, ep, query, video_id, fatal=True): | |
287 | data = self._DEFAULT_API_DATA.copy() | |
288 | data.update(query) | |
289 | ||
290 | return self._download_json( | |
291 | 'https://www.youtube.com/youtubei/v1/%s' % ep, video_id=video_id, | |
292 | note='Downloading API JSON', errnote='Unable to download API page', | |
293 | data=json.dumps(data).encode('utf8'), fatal=fatal, | |
294 | headers={'content-type': 'application/json'}, | |
295 | query={'key': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'}) | |
296 | ||
297 | def _extract_yt_initial_data(self, video_id, webpage): | |
298 | return self._parse_json( | |
299 | self._search_regex( | |
300 | (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE), | |
301 | self._YT_INITIAL_DATA_RE), webpage, 'yt initial data'), | |
302 | video_id) | |
303 | ||
304 | def _extract_ytcfg(self, video_id, webpage): | |
305 | return self._parse_json( | |
306 | self._search_regex( | |
307 | r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg', | |
308 | default='{}'), video_id, fatal=False) | |
309 | ||
310 | def _extract_video(self, renderer): | |
311 | video_id = renderer.get('videoId') | |
312 | title = try_get( | |
313 | renderer, | |
314 | (lambda x: x['title']['runs'][0]['text'], | |
315 | lambda x: x['title']['simpleText']), compat_str) | |
316 | description = try_get( | |
317 | renderer, lambda x: x['descriptionSnippet']['runs'][0]['text'], | |
318 | compat_str) | |
319 | duration = parse_duration(try_get( | |
320 | renderer, lambda x: x['lengthText']['simpleText'], compat_str)) | |
321 | view_count_text = try_get( | |
322 | renderer, lambda x: x['viewCountText']['simpleText'], compat_str) or '' | |
323 | view_count = str_to_int(self._search_regex( | |
324 | r'^([\d,]+)', re.sub(r'\s', '', view_count_text), | |
325 | 'view count', default=None)) | |
326 | uploader = try_get( | |
327 | renderer, | |
328 | (lambda x: x['ownerText']['runs'][0]['text'], | |
329 | lambda x: x['shortBylineText']['runs'][0]['text']), compat_str) | |
330 | return { | |
331 | '_type': 'url_transparent', | |
332 | 'ie_key': YoutubeIE.ie_key(), | |
333 | 'id': video_id, | |
334 | 'url': video_id, | |
335 | 'title': title, | |
336 | 'description': description, | |
337 | 'duration': duration, | |
338 | 'view_count': view_count, | |
339 | 'uploader': uploader, | |
340 | } | |
341 | ||
342 | ||
343 | class YoutubeIE(YoutubeBaseInfoExtractor): | |
344 | IE_DESC = 'YouTube.com' | |
345 | _INVIDIOUS_SITES = ( | |
346 | # invidious-redirect websites | |
347 | r'(?:www\.)?redirect\.invidious\.io', | |
348 | r'(?:(?:www|dev)\.)?invidio\.us', | |
349 | # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md | |
350 | r'(?:www\.)?invidious\.pussthecat\.org', | |
351 | r'(?:www\.)?invidious\.048596\.xyz', | |
352 | r'(?:www\.)?invidious\.zee\.li', | |
353 | r'(?:www\.)?vid\.puffyan\.us', | |
354 | r'(?:(?:www|au)\.)?ytprivate\.com', | |
355 | r'(?:www\.)?invidious\.namazso\.eu', | |
356 | r'(?:www\.)?invidious\.ethibox\.fr', | |
357 | r'(?:www\.)?inv\.skyn3t\.in', | |
358 | r'(?:www\.)?invidious\.himiko\.cloud', | |
359 | r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion', | |
360 | r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion', | |
361 | r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion', | |
362 | r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion', | |
363 | # youtube-dl invidious instances list | |
364 | r'(?:(?:www|no)\.)?invidiou\.sh', | |
365 | r'(?:(?:www|fi)\.)?invidious\.snopyta\.org', | |
366 | r'(?:www\.)?invidious\.kabi\.tk', | |
367 | r'(?:www\.)?invidious\.13ad\.de', | |
368 | r'(?:www\.)?invidious\.mastodon\.host', | |
369 | r'(?:www\.)?invidious\.zapashcanon\.fr', | |
370 | r'(?:www\.)?invidious\.kavin\.rocks', | |
371 | r'(?:www\.)?invidious\.tube', | |
372 | r'(?:www\.)?invidiou\.site', | |
373 | r'(?:www\.)?invidious\.site', | |
374 | r'(?:www\.)?invidious\.xyz', | |
375 | r'(?:www\.)?invidious\.nixnet\.xyz', | |
376 | r'(?:www\.)?invidious\.drycat\.fr', | |
377 | r'(?:www\.)?tube\.poal\.co', | |
378 | r'(?:www\.)?tube\.connect\.cafe', | |
379 | r'(?:www\.)?vid\.wxzm\.sx', | |
380 | r'(?:www\.)?vid\.mint\.lgbt', | |
381 | r'(?:www\.)?yewtu\.be', | |
382 | r'(?:www\.)?yt\.elukerio\.org', | |
383 | r'(?:www\.)?yt\.lelux\.fi', | |
384 | r'(?:www\.)?invidious\.ggc-project\.de', | |
385 | r'(?:www\.)?yt\.maisputain\.ovh', | |
386 | r'(?:www\.)?invidious\.toot\.koeln', | |
387 | r'(?:www\.)?invidious\.fdn\.fr', | |
388 | r'(?:www\.)?watch\.nettohikari\.com', | |
389 | r'(?:www\.)?kgg2m7yk5aybusll\.onion', | |
390 | r'(?:www\.)?qklhadlycap4cnod\.onion', | |
391 | r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion', | |
392 | r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion', | |
393 | r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion', | |
394 | r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion', | |
395 | r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p', | |
396 | r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion', | |
397 | ) | |
398 | _VALID_URL = r"""(?x)^ | |
399 | ( | |
400 | (?:https?://|//) # http(s):// or protocol-independent URL | |
401 | (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com| | |
402 | (?:www\.)?deturl\.com/www\.youtube\.com| | |
403 | (?:www\.)?pwnyoutube\.com| | |
404 | (?:www\.)?hooktube\.com| | |
405 | (?:www\.)?yourepeat\.com| | |
406 | tube\.majestyc\.net| | |
407 | %(invidious)s| | |
408 | youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains | |
409 | (?:.*?\#/)? # handle anchor (#/) redirect urls | |
410 | (?: # the various things that can precede the ID: | |
411 | (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/ | |
412 | |(?: # or the v= param in all its forms | |
413 | (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) | |
414 | (?:\?|\#!?) # the params delimiter ? or # or #! | |
415 | (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY) | |
416 | v= | |
417 | ) | |
418 | )) | |
419 | |(?: | |
420 | youtu\.be| # just youtu.be/xxxx | |
421 | vid\.plus| # or vid.plus/xxxx | |
422 | zwearz\.com/watch| # or zwearz.com/watch/xxxx | |
423 | %(invidious)s | |
424 | )/ | |
425 | |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId= | |
426 | ) | |
427 | )? # all until now is optional -> you can pass the naked ID | |
428 | (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID | |
429 | (?!.*?\blist= | |
430 | (?: | |
431 | %(playlist_id)s| # combined list/video URLs are handled by the playlist IE | |
432 | WL # WL are handled by the watch later IE | |
433 | ) | |
434 | ) | |
435 | (?(1).+)? # if we found the ID, everything can follow | |
436 | $""" % { | |
437 | 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE, | |
438 | 'invidious': '|'.join(_INVIDIOUS_SITES), | |
439 | } | |
440 | _PLAYER_INFO_RE = ( | |
441 | r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player', | |
442 | r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$', | |
443 | r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$', | |
444 | ) | |
445 | _formats = { | |
446 | '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, | |
447 | '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, | |
448 | '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}, | |
449 | '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}, | |
450 | '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}, | |
451 | '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
452 | '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
453 | '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
454 | # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well | |
455 | '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}, | |
456 | '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
457 | '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
458 | '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
459 | '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
460 | '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, | |
461 | '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, | |
462 | '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
463 | '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
464 | ||
465 | ||
466 | # 3D videos | |
467 | '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, | |
468 | '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, | |
469 | '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
470 | '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
471 | '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}, | |
472 | '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
473 | '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
474 | ||
475 | # Apple HTTP Live Streaming | |
476 | '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, | |
477 | '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, | |
478 | '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
479 | '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
480 | '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
481 | '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
482 | '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, | |
483 | '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}, | |
484 | ||
485 | # DASH mp4 video | |
486 | '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
487 | '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
488 | '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
489 | '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
490 | '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
491 | '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559) | |
492 | '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
493 | '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
494 | '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
495 | '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
496 | '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
497 | '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
498 | ||
499 | # Dash mp4 audio | |
500 | '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}, | |
501 | '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}, | |
502 | '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}, | |
503 | '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
504 | '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
505 | '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}, | |
506 | '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}, | |
507 | ||
508 | # Dash webm | |
509 | '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
510 | '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
511 | '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
512 | '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
513 | '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
514 | '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
515 | '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}, | |
516 | '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
517 | '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
518 | '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
519 | '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
520 | '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
521 | '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
522 | '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
523 | '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
524 | # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug) | |
525 | '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
526 | '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
527 | '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
528 | '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
529 | '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
530 | '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
531 | ||
532 | # Dash webm audio | |
533 | '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}, | |
534 | '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}, | |
535 | ||
536 | # Dash webm audio with opus inside | |
537 | '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}, | |
538 | '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}, | |
539 | '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}, | |
540 | ||
541 | # RTMP (unnamed) | |
542 | '_rtmp': {'protocol': 'rtmp'}, | |
543 | ||
544 | # av01 video only formats sometimes served with "unknown" codecs | |
545 | '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}, | |
546 | '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}, | |
547 | '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}, | |
548 | '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}, | |
549 | } | |
550 | _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt') | |
551 | ||
552 | _GEO_BYPASS = False | |
553 | ||
554 | IE_NAME = 'youtube' | |
555 | _TESTS = [ | |
556 | { | |
557 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9', | |
558 | 'info_dict': { | |
559 | 'id': 'BaW_jenozKc', | |
560 | 'ext': 'mp4', | |
561 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
562 | 'uploader': 'Philipp Hagemeister', | |
563 | 'uploader_id': 'phihag', | |
564 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', | |
565 | 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', | |
566 | 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', | |
567 | 'upload_date': '20121002', | |
568 | '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 .', | |
569 | 'categories': ['Science & Technology'], | |
570 | 'tags': ['youtube-dl'], | |
571 | 'duration': 10, | |
572 | 'view_count': int, | |
573 | 'like_count': int, | |
574 | 'dislike_count': int, | |
575 | 'start_time': 1, | |
576 | 'end_time': 9, | |
577 | } | |
578 | }, | |
579 | { | |
580 | 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ', | |
581 | 'note': 'Embed-only video (#1746)', | |
582 | 'info_dict': { | |
583 | 'id': 'yZIXLfi8CZQ', | |
584 | 'ext': 'mp4', | |
585 | 'upload_date': '20120608', | |
586 | 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012', | |
587 | 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7', | |
588 | 'uploader': 'SET India', | |
589 | 'uploader_id': 'setindia', | |
590 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia', | |
591 | 'age_limit': 18, | |
592 | }, | |
593 | 'skip': 'Private video', | |
594 | }, | |
595 | { | |
596 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ', | |
597 | 'note': 'Use the first video ID in the URL', | |
598 | 'info_dict': { | |
599 | 'id': 'BaW_jenozKc', | |
600 | 'ext': 'mp4', | |
601 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
602 | 'uploader': 'Philipp Hagemeister', | |
603 | 'uploader_id': 'phihag', | |
604 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', | |
605 | 'upload_date': '20121002', | |
606 | '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 .', | |
607 | 'categories': ['Science & Technology'], | |
608 | 'tags': ['youtube-dl'], | |
609 | 'duration': 10, | |
610 | 'view_count': int, | |
611 | 'like_count': int, | |
612 | 'dislike_count': int, | |
613 | }, | |
614 | 'params': { | |
615 | 'skip_download': True, | |
616 | }, | |
617 | }, | |
618 | { | |
619 | 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I', | |
620 | 'note': '256k DASH audio (format 141) via DASH manifest', | |
621 | 'info_dict': { | |
622 | 'id': 'a9LDPn-MO4I', | |
623 | 'ext': 'm4a', | |
624 | 'upload_date': '20121002', | |
625 | 'uploader_id': '8KVIDEO', | |
626 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO', | |
627 | 'description': '', | |
628 | 'uploader': '8KVIDEO', | |
629 | 'title': 'UHDTV TEST 8K VIDEO.mp4' | |
630 | }, | |
631 | 'params': { | |
632 | 'youtube_include_dash_manifest': True, | |
633 | 'format': '141', | |
634 | }, | |
635 | 'skip': 'format 141 not served anymore', | |
636 | }, | |
637 | # DASH manifest with encrypted signature | |
638 | { | |
639 | 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA', | |
640 | 'info_dict': { | |
641 | 'id': 'IB3lcPjvWLA', | |
642 | 'ext': 'm4a', | |
643 | 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson', | |
644 | 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf', | |
645 | 'duration': 244, | |
646 | 'uploader': 'AfrojackVEVO', | |
647 | 'uploader_id': 'AfrojackVEVO', | |
648 | 'upload_date': '20131011', | |
649 | 'abr': 129.495, | |
650 | }, | |
651 | 'params': { | |
652 | 'youtube_include_dash_manifest': True, | |
653 | 'format': '141/bestaudio[ext=m4a]', | |
654 | }, | |
655 | }, | |
656 | # Controversy video | |
657 | { | |
658 | 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8', | |
659 | 'info_dict': { | |
660 | 'id': 'T4XJQO3qol8', | |
661 | 'ext': 'mp4', | |
662 | 'duration': 219, | |
663 | 'upload_date': '20100909', | |
664 | 'uploader': 'Amazing Atheist', | |
665 | 'uploader_id': 'TheAmazingAtheist', | |
666 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist', | |
667 | 'title': 'Burning Everyone\'s Koran', | |
668 | 'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms \r\n\r\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html', | |
669 | } | |
670 | }, | |
671 | # Normal age-gate video (embed allowed) | |
672 | { | |
673 | 'url': 'https://youtube.com/watch?v=HtVdAasjOgU', | |
674 | 'info_dict': { | |
675 | 'id': 'HtVdAasjOgU', | |
676 | 'ext': 'mp4', | |
677 | 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer', | |
678 | 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}', | |
679 | 'duration': 142, | |
680 | 'uploader': 'The Witcher', | |
681 | 'uploader_id': 'WitcherGame', | |
682 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame', | |
683 | 'upload_date': '20140605', | |
684 | 'age_limit': 18, | |
685 | }, | |
686 | }, | |
687 | # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421) | |
688 | # YouTube Red ad is not captured for creator | |
689 | { | |
690 | 'url': '__2ABJjxzNo', | |
691 | 'info_dict': { | |
692 | 'id': '__2ABJjxzNo', | |
693 | 'ext': 'mp4', | |
694 | 'duration': 266, | |
695 | 'upload_date': '20100430', | |
696 | 'uploader_id': 'deadmau5', | |
697 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5', | |
698 | 'creator': 'deadmau5', | |
699 | 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336', | |
700 | 'uploader': 'deadmau5', | |
701 | 'title': 'Deadmau5 - Some Chords (HD)', | |
702 | 'alt_title': 'Some Chords', | |
703 | }, | |
704 | 'expected_warnings': [ | |
705 | 'DASH manifest missing', | |
706 | ] | |
707 | }, | |
708 | # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431) | |
709 | { | |
710 | 'url': 'lqQg6PlCWgI', | |
711 | 'info_dict': { | |
712 | 'id': 'lqQg6PlCWgI', | |
713 | 'ext': 'mp4', | |
714 | 'duration': 6085, | |
715 | 'upload_date': '20150827', | |
716 | 'uploader_id': 'olympic', | |
717 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic', | |
718 | 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', | |
719 | 'uploader': 'Olympic', | |
720 | 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', | |
721 | }, | |
722 | 'params': { | |
723 | 'skip_download': 'requires avconv', | |
724 | } | |
725 | }, | |
726 | # Non-square pixels | |
727 | { | |
728 | 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0', | |
729 | 'info_dict': { | |
730 | 'id': '_b-2C3KPAM0', | |
731 | 'ext': 'mp4', | |
732 | 'stretched_ratio': 16 / 9., | |
733 | 'duration': 85, | |
734 | 'upload_date': '20110310', | |
735 | 'uploader_id': 'AllenMeow', | |
736 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow', | |
737 | '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', | |
738 | 'uploader': '孫ᄋᄅ', | |
739 | 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', | |
740 | }, | |
741 | }, | |
742 | # url_encoded_fmt_stream_map is empty string | |
743 | { | |
744 | 'url': 'qEJwOuvDf7I', | |
745 | 'info_dict': { | |
746 | 'id': 'qEJwOuvDf7I', | |
747 | 'ext': 'webm', | |
748 | 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге', | |
749 | 'description': '', | |
750 | 'upload_date': '20150404', | |
751 | 'uploader_id': 'spbelect', | |
752 | 'uploader': 'Наблюдатели Петербурга', | |
753 | }, | |
754 | 'params': { | |
755 | 'skip_download': 'requires avconv', | |
756 | }, | |
757 | 'skip': 'This live event has ended.', | |
758 | }, | |
759 | # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097) | |
760 | { | |
761 | 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y', | |
762 | 'info_dict': { | |
763 | 'id': 'FIl7x6_3R5Y', | |
764 | 'ext': 'webm', | |
765 | 'title': 'md5:7b81415841e02ecd4313668cde88737a', | |
766 | 'description': 'md5:116377fd2963b81ec4ce64b542173306', | |
767 | 'duration': 220, | |
768 | 'upload_date': '20150625', | |
769 | 'uploader_id': 'dorappi2000', | |
770 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000', | |
771 | 'uploader': 'dorappi2000', | |
772 | 'formats': 'mincount:31', | |
773 | }, | |
774 | 'skip': 'not actual anymore', | |
775 | }, | |
776 | # DASH manifest with segment_list | |
777 | { | |
778 | 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8', | |
779 | 'md5': '8ce563a1d667b599d21064e982ab9e31', | |
780 | 'info_dict': { | |
781 | 'id': 'CsmdDsKjzN8', | |
782 | 'ext': 'mp4', | |
783 | 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510 | |
784 | 'uploader': 'Airtek', | |
785 | 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.', | |
786 | 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ', | |
787 | 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015', | |
788 | }, | |
789 | 'params': { | |
790 | 'youtube_include_dash_manifest': True, | |
791 | 'format': '135', # bestvideo | |
792 | }, | |
793 | 'skip': 'This live event has ended.', | |
794 | }, | |
795 | { | |
796 | # Multifeed videos (multiple cameras), URL is for Main Camera | |
797 | 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg', | |
798 | 'info_dict': { | |
799 | 'id': 'jvGDaLqkpTg', | |
800 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever', | |
801 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
802 | }, | |
803 | 'playlist': [{ | |
804 | 'info_dict': { | |
805 | 'id': 'jvGDaLqkpTg', | |
806 | 'ext': 'mp4', | |
807 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)', | |
808 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
809 | 'duration': 10643, | |
810 | 'upload_date': '20161111', | |
811 | 'uploader': 'Team PGP', | |
812 | 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg', | |
813 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg', | |
814 | }, | |
815 | }, { | |
816 | 'info_dict': { | |
817 | 'id': '3AKt1R1aDnw', | |
818 | 'ext': 'mp4', | |
819 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)', | |
820 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
821 | 'duration': 10991, | |
822 | 'upload_date': '20161111', | |
823 | 'uploader': 'Team PGP', | |
824 | 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg', | |
825 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg', | |
826 | }, | |
827 | }, { | |
828 | 'info_dict': { | |
829 | 'id': 'RtAMM00gpVc', | |
830 | 'ext': 'mp4', | |
831 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)', | |
832 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
833 | 'duration': 10995, | |
834 | 'upload_date': '20161111', | |
835 | 'uploader': 'Team PGP', | |
836 | 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg', | |
837 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg', | |
838 | }, | |
839 | }, { | |
840 | 'info_dict': { | |
841 | 'id': '6N2fdlP3C5U', | |
842 | 'ext': 'mp4', | |
843 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)', | |
844 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
845 | 'duration': 10990, | |
846 | 'upload_date': '20161111', | |
847 | 'uploader': 'Team PGP', | |
848 | 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg', | |
849 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg', | |
850 | }, | |
851 | }], | |
852 | 'params': { | |
853 | 'skip_download': True, | |
854 | }, | |
855 | }, | |
856 | { | |
857 | # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536) | |
858 | 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo', | |
859 | 'info_dict': { | |
860 | 'id': 'gVfLd0zydlo', | |
861 | 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30', | |
862 | }, | |
863 | 'playlist_count': 2, | |
864 | 'skip': 'Not multifeed anymore', | |
865 | }, | |
866 | { | |
867 | 'url': 'https://vid.plus/FlRa-iH7PGw', | |
868 | 'only_matching': True, | |
869 | }, | |
870 | { | |
871 | 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html', | |
872 | 'only_matching': True, | |
873 | }, | |
874 | { | |
875 | # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468) | |
876 | # Also tests cut-off URL expansion in video description (see | |
877 | # https://github.com/ytdl-org/youtube-dl/issues/1892, | |
878 | # https://github.com/ytdl-org/youtube-dl/issues/8164) | |
879 | 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg', | |
880 | 'info_dict': { | |
881 | 'id': 'lsguqyKfVQg', | |
882 | 'ext': 'mp4', | |
883 | 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21', | |
884 | 'alt_title': 'Dark Walk - Position Music', | |
885 | 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a', | |
886 | 'duration': 133, | |
887 | 'upload_date': '20151119', | |
888 | 'uploader_id': 'IronSoulElf', | |
889 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf', | |
890 | 'uploader': 'IronSoulElf', | |
891 | 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan', | |
892 | 'track': 'Dark Walk - Position Music', | |
893 | 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan', | |
894 | 'album': 'Position Music - Production Music Vol. 143 - Dark Walk', | |
895 | }, | |
896 | 'params': { | |
897 | 'skip_download': True, | |
898 | }, | |
899 | }, | |
900 | { | |
901 | # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468) | |
902 | 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8', | |
903 | 'only_matching': True, | |
904 | }, | |
905 | { | |
906 | # Video with yt:stretch=17:0 | |
907 | 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM', | |
908 | 'info_dict': { | |
909 | 'id': 'Q39EVAstoRM', | |
910 | 'ext': 'mp4', | |
911 | 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4', | |
912 | 'description': 'md5:ee18a25c350637c8faff806845bddee9', | |
913 | 'upload_date': '20151107', | |
914 | 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA', | |
915 | 'uploader': 'CH GAMER DROID', | |
916 | }, | |
917 | 'params': { | |
918 | 'skip_download': True, | |
919 | }, | |
920 | 'skip': 'This video does not exist.', | |
921 | }, | |
922 | { | |
923 | # Video licensed under Creative Commons | |
924 | 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA', | |
925 | 'info_dict': { | |
926 | 'id': 'M4gD1WSo5mA', | |
927 | 'ext': 'mp4', | |
928 | 'title': 'md5:e41008789470fc2533a3252216f1c1d1', | |
929 | 'description': 'md5:a677553cf0840649b731a3024aeff4cc', | |
930 | 'duration': 721, | |
931 | 'upload_date': '20150127', | |
932 | 'uploader_id': 'BerkmanCenter', | |
933 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter', | |
934 | 'uploader': 'The Berkman Klein Center for Internet & Society', | |
935 | 'license': 'Creative Commons Attribution license (reuse allowed)', | |
936 | }, | |
937 | 'params': { | |
938 | 'skip_download': True, | |
939 | }, | |
940 | }, | |
941 | { | |
942 | # Channel-like uploader_url | |
943 | 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg', | |
944 | 'info_dict': { | |
945 | 'id': 'eQcmzGIKrzg', | |
946 | 'ext': 'mp4', | |
947 | 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders', | |
948 | 'description': 'md5:13a2503d7b5904ef4b223aa101628f39', | |
949 | 'duration': 4060, | |
950 | 'upload_date': '20151119', | |
951 | 'uploader': 'Bernie Sanders', | |
952 | 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg', | |
953 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg', | |
954 | 'license': 'Creative Commons Attribution license (reuse allowed)', | |
955 | }, | |
956 | 'params': { | |
957 | 'skip_download': True, | |
958 | }, | |
959 | }, | |
960 | { | |
961 | 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY', | |
962 | 'only_matching': True, | |
963 | }, | |
964 | { | |
965 | # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059) | |
966 | 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo', | |
967 | 'only_matching': True, | |
968 | }, | |
969 | { | |
970 | # Rental video preview | |
971 | 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg', | |
972 | 'info_dict': { | |
973 | 'id': 'uGpuVWrhIzE', | |
974 | 'ext': 'mp4', | |
975 | 'title': 'Piku - Trailer', | |
976 | 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb', | |
977 | 'upload_date': '20150811', | |
978 | 'uploader': 'FlixMatrix', | |
979 | 'uploader_id': 'FlixMatrixKaravan', | |
980 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan', | |
981 | 'license': 'Standard YouTube License', | |
982 | }, | |
983 | 'params': { | |
984 | 'skip_download': True, | |
985 | }, | |
986 | 'skip': 'This video is not available.', | |
987 | }, | |
988 | { | |
989 | # YouTube Red video with episode data | |
990 | 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4', | |
991 | 'info_dict': { | |
992 | 'id': 'iqKdEhx-dD4', | |
993 | 'ext': 'mp4', | |
994 | 'title': 'Isolation - Mind Field (Ep 1)', | |
995 | 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd', | |
996 | 'duration': 2085, | |
997 | 'upload_date': '20170118', | |
998 | 'uploader': 'Vsauce', | |
999 | 'uploader_id': 'Vsauce', | |
1000 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce', | |
1001 | 'series': 'Mind Field', | |
1002 | 'season_number': 1, | |
1003 | 'episode_number': 1, | |
1004 | }, | |
1005 | 'params': { | |
1006 | 'skip_download': True, | |
1007 | }, | |
1008 | 'expected_warnings': [ | |
1009 | 'Skipping DASH manifest', | |
1010 | ], | |
1011 | }, | |
1012 | { | |
1013 | # The following content has been identified by the YouTube community | |
1014 | # as inappropriate or offensive to some audiences. | |
1015 | 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI', | |
1016 | 'info_dict': { | |
1017 | 'id': '6SJNVb0GnPI', | |
1018 | 'ext': 'mp4', | |
1019 | 'title': 'Race Differences in Intelligence', | |
1020 | 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1', | |
1021 | 'duration': 965, | |
1022 | 'upload_date': '20140124', | |
1023 | 'uploader': 'New Century Foundation', | |
1024 | 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg', | |
1025 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg', | |
1026 | }, | |
1027 | 'params': { | |
1028 | 'skip_download': True, | |
1029 | }, | |
1030 | 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.', | |
1031 | }, | |
1032 | { | |
1033 | # itag 212 | |
1034 | 'url': '1t24XAntNCY', | |
1035 | 'only_matching': True, | |
1036 | }, | |
1037 | { | |
1038 | # geo restricted to JP | |
1039 | 'url': 'sJL6WA-aGkQ', | |
1040 | 'only_matching': True, | |
1041 | }, | |
1042 | { | |
1043 | 'url': 'https://invidio.us/watch?v=BaW_jenozKc', | |
1044 | 'only_matching': True, | |
1045 | }, | |
1046 | { | |
1047 | 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc', | |
1048 | 'only_matching': True, | |
1049 | }, | |
1050 | { | |
1051 | # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m | |
1052 | 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA', | |
1053 | 'only_matching': True, | |
1054 | }, | |
1055 | { | |
1056 | # DRM protected | |
1057 | 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc', | |
1058 | 'only_matching': True, | |
1059 | }, | |
1060 | { | |
1061 | # Video with unsupported adaptive stream type formats | |
1062 | 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U', | |
1063 | 'info_dict': { | |
1064 | 'id': 'Z4Vy8R84T1U', | |
1065 | 'ext': 'mp4', | |
1066 | 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta', | |
1067 | 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', | |
1068 | 'duration': 433, | |
1069 | 'upload_date': '20130923', | |
1070 | 'uploader': 'Amelia Putri Harwita', | |
1071 | 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q', | |
1072 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q', | |
1073 | 'formats': 'maxcount:10', | |
1074 | }, | |
1075 | 'params': { | |
1076 | 'skip_download': True, | |
1077 | 'youtube_include_dash_manifest': False, | |
1078 | }, | |
1079 | 'skip': 'not actual anymore', | |
1080 | }, | |
1081 | { | |
1082 | # Youtube Music Auto-generated description | |
1083 | 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs', | |
1084 | 'info_dict': { | |
1085 | 'id': 'MgNrAu2pzNs', | |
1086 | 'ext': 'mp4', | |
1087 | 'title': 'Voyeur Girl', | |
1088 | 'description': 'md5:7ae382a65843d6df2685993e90a8628f', | |
1089 | 'upload_date': '20190312', | |
1090 | 'uploader': 'Stephen - Topic', | |
1091 | 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA', | |
1092 | 'artist': 'Stephen', | |
1093 | 'track': 'Voyeur Girl', | |
1094 | 'album': 'it\'s too much love to know my dear', | |
1095 | 'release_date': '20190313', | |
1096 | 'release_year': 2019, | |
1097 | }, | |
1098 | 'params': { | |
1099 | 'skip_download': True, | |
1100 | }, | |
1101 | }, | |
1102 | { | |
1103 | 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q', | |
1104 | 'only_matching': True, | |
1105 | }, | |
1106 | { | |
1107 | # invalid -> valid video id redirection | |
1108 | 'url': 'DJztXj2GPfl', | |
1109 | 'info_dict': { | |
1110 | 'id': 'DJztXj2GPfk', | |
1111 | 'ext': 'mp4', | |
1112 | 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)', | |
1113 | 'description': 'md5:bf577a41da97918e94fa9798d9228825', | |
1114 | 'upload_date': '20090125', | |
1115 | 'uploader': 'Prochorowka', | |
1116 | 'uploader_id': 'Prochorowka', | |
1117 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka', | |
1118 | 'artist': 'Panjabi MC', | |
1119 | 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix', | |
1120 | 'album': 'Beware of the Boys (Mundian To Bach Ke)', | |
1121 | }, | |
1122 | 'params': { | |
1123 | 'skip_download': True, | |
1124 | }, | |
1125 | 'skip': 'Video unavailable', | |
1126 | }, | |
1127 | { | |
1128 | # empty description results in an empty string | |
1129 | 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k', | |
1130 | 'info_dict': { | |
1131 | 'id': 'x41yOUIvK2k', | |
1132 | 'ext': 'mp4', | |
1133 | 'title': 'IMG 3456', | |
1134 | 'description': '', | |
1135 | 'upload_date': '20170613', | |
1136 | 'uploader_id': 'ElevageOrVert', | |
1137 | 'uploader': 'ElevageOrVert', | |
1138 | }, | |
1139 | 'params': { | |
1140 | 'skip_download': True, | |
1141 | }, | |
1142 | }, | |
1143 | { | |
1144 | # with '};' inside yt initial data (see [1]) | |
1145 | # see [2] for an example with '};' inside ytInitialPlayerResponse | |
1146 | # 1. https://github.com/ytdl-org/youtube-dl/issues/27093 | |
1147 | # 2. https://github.com/ytdl-org/youtube-dl/issues/27216 | |
1148 | 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no', | |
1149 | 'info_dict': { | |
1150 | 'id': 'CHqg6qOn4no', | |
1151 | 'ext': 'mp4', | |
1152 | 'title': 'Part 77 Sort a list of simple types in c#', | |
1153 | 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc', | |
1154 | 'upload_date': '20130831', | |
1155 | 'uploader_id': 'kudvenkat', | |
1156 | 'uploader': 'kudvenkat', | |
1157 | }, | |
1158 | 'params': { | |
1159 | 'skip_download': True, | |
1160 | }, | |
1161 | }, | |
1162 | { | |
1163 | # another example of '};' in ytInitialData | |
1164 | 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY', | |
1165 | 'only_matching': True, | |
1166 | }, | |
1167 | { | |
1168 | 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ', | |
1169 | 'only_matching': True, | |
1170 | }, | |
1171 | { | |
1172 | # https://github.com/ytdl-org/youtube-dl/pull/28094 | |
1173 | 'url': 'OtqTfy26tG0', | |
1174 | 'info_dict': { | |
1175 | 'id': 'OtqTfy26tG0', | |
1176 | 'ext': 'mp4', | |
1177 | 'title': 'Burn Out', | |
1178 | 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131', | |
1179 | 'upload_date': '20141120', | |
1180 | 'uploader': 'The Cinematic Orchestra - Topic', | |
1181 | 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw', | |
1182 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw', | |
1183 | 'artist': 'The Cinematic Orchestra', | |
1184 | 'track': 'Burn Out', | |
1185 | 'album': 'Every Day', | |
1186 | 'release_data': None, | |
1187 | 'release_year': None, | |
1188 | }, | |
1189 | 'params': { | |
1190 | 'skip_download': True, | |
1191 | }, | |
1192 | }, | |
1193 | { | |
1194 | # controversial video, only works with bpctr when authenticated with cookies | |
1195 | 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg', | |
1196 | 'only_matching': True, | |
1197 | }, | |
1198 | ] | |
1199 | ||
1200 | def __init__(self, *args, **kwargs): | |
1201 | super(YoutubeIE, self).__init__(*args, **kwargs) | |
1202 | self._code_cache = {} | |
1203 | self._player_cache = {} | |
1204 | ||
1205 | def _signature_cache_id(self, example_sig): | |
1206 | """ Return a string representation of a signature """ | |
1207 | return '.'.join(compat_str(len(part)) for part in example_sig.split('.')) | |
1208 | ||
1209 | @classmethod | |
1210 | def _extract_player_info(cls, player_url): | |
1211 | for player_re in cls._PLAYER_INFO_RE: | |
1212 | id_m = re.search(player_re, player_url) | |
1213 | if id_m: | |
1214 | break | |
1215 | else: | |
1216 | raise ExtractorError('Cannot identify player %r' % player_url) | |
1217 | return id_m.group('id') | |
1218 | ||
1219 | def _extract_signature_function(self, video_id, player_url, example_sig): | |
1220 | player_id = self._extract_player_info(player_url) | |
1221 | ||
1222 | # Read from filesystem cache | |
1223 | func_id = 'js_%s_%s' % ( | |
1224 | player_id, self._signature_cache_id(example_sig)) | |
1225 | assert os.path.basename(func_id) == func_id | |
1226 | ||
1227 | cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id) | |
1228 | if cache_spec is not None: | |
1229 | return lambda s: ''.join(s[i] for i in cache_spec) | |
1230 | ||
1231 | if player_id not in self._code_cache: | |
1232 | self._code_cache[player_id] = self._download_webpage( | |
1233 | player_url, video_id, | |
1234 | note='Downloading player ' + player_id, | |
1235 | errnote='Download of %s failed' % player_url) | |
1236 | code = self._code_cache[player_id] | |
1237 | res = self._parse_sig_js(code) | |
1238 | ||
1239 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) | |
1240 | cache_res = res(test_string) | |
1241 | cache_spec = [ord(c) for c in cache_res] | |
1242 | ||
1243 | self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec) | |
1244 | return res | |
1245 | ||
1246 | def _print_sig_code(self, func, example_sig): | |
1247 | def gen_sig_code(idxs): | |
1248 | def _genslice(start, end, step): | |
1249 | starts = '' if start == 0 else str(start) | |
1250 | ends = (':%d' % (end + step)) if end + step >= 0 else ':' | |
1251 | steps = '' if step == 1 else (':%d' % step) | |
1252 | return 's[%s%s%s]' % (starts, ends, steps) | |
1253 | ||
1254 | step = None | |
1255 | # Quelch pyflakes warnings - start will be set when step is set | |
1256 | start = '(Never used)' | |
1257 | for i, prev in zip(idxs[1:], idxs[:-1]): | |
1258 | if step is not None: | |
1259 | if i - prev == step: | |
1260 | continue | |
1261 | yield _genslice(start, prev, step) | |
1262 | step = None | |
1263 | continue | |
1264 | if i - prev in [-1, 1]: | |
1265 | step = i - prev | |
1266 | start = prev | |
1267 | continue | |
1268 | else: | |
1269 | yield 's[%d]' % prev | |
1270 | if step is None: | |
1271 | yield 's[%d]' % i | |
1272 | else: | |
1273 | yield _genslice(start, i, step) | |
1274 | ||
1275 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) | |
1276 | cache_res = func(test_string) | |
1277 | cache_spec = [ord(c) for c in cache_res] | |
1278 | expr_code = ' + '.join(gen_sig_code(cache_spec)) | |
1279 | signature_id_tuple = '(%s)' % ( | |
1280 | ', '.join(compat_str(len(p)) for p in example_sig.split('.'))) | |
1281 | code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n' | |
1282 | ' return %s\n') % (signature_id_tuple, expr_code) | |
1283 | self.to_screen('Extracted signature function:\n' + code) | |
1284 | ||
1285 | def _parse_sig_js(self, jscode): | |
1286 | funcname = self._search_regex( | |
1287 | (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1288 | r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1289 | r'\bm=(?P<sig>[a-zA-Z0-9$]{2})\(decodeURIComponent\(h\.s\)\)', | |
1290 | r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2})\(decodeURIComponent\(c\)\)', | |
1291 | 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}\(a,\d+\)', | |
1292 | 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\(\s*""\s*\)', | |
1293 | r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)', | |
1294 | # Obsolete patterns | |
1295 | r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1296 | r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(', | |
1297 | r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1298 | r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1299 | r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1300 | r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1301 | r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1302 | r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('), | |
1303 | jscode, 'Initial JS player signature function name', group='sig') | |
1304 | ||
1305 | jsi = JSInterpreter(jscode) | |
1306 | initial_function = jsi.extract_function(funcname) | |
1307 | return lambda s: initial_function([s]) | |
1308 | ||
1309 | def _decrypt_signature(self, s, video_id, player_url): | |
1310 | """Turn the encrypted s field into a working signature""" | |
1311 | ||
1312 | if player_url is None: | |
1313 | raise ExtractorError('Cannot decrypt signature without player_url') | |
1314 | ||
1315 | if player_url.startswith('//'): | |
1316 | player_url = 'https:' + player_url | |
1317 | elif not re.match(r'https?://', player_url): | |
1318 | player_url = compat_urlparse.urljoin( | |
1319 | 'https://www.youtube.com', player_url) | |
1320 | try: | |
1321 | player_id = (player_url, self._signature_cache_id(s)) | |
1322 | if player_id not in self._player_cache: | |
1323 | func = self._extract_signature_function( | |
1324 | video_id, player_url, s | |
1325 | ) | |
1326 | self._player_cache[player_id] = func | |
1327 | func = self._player_cache[player_id] | |
1328 | if self._downloader.params.get('youtube_print_sig_code'): | |
1329 | self._print_sig_code(func, s) | |
1330 | return func(s) | |
1331 | except Exception as e: | |
1332 | tb = traceback.format_exc() | |
1333 | raise ExtractorError( | |
1334 | 'Signature extraction failed: ' + tb, cause=e) | |
1335 | ||
1336 | def _mark_watched(self, video_id, player_response): | |
1337 | playback_url = url_or_none(try_get( | |
1338 | player_response, | |
1339 | lambda x: x['playbackTracking']['videostatsPlaybackUrl']['baseUrl'])) | |
1340 | if not playback_url: | |
1341 | return | |
1342 | parsed_playback_url = compat_urlparse.urlparse(playback_url) | |
1343 | qs = compat_urlparse.parse_qs(parsed_playback_url.query) | |
1344 | ||
1345 | # cpn generation algorithm is reverse engineered from base.js. | |
1346 | # In fact it works even with dummy cpn. | |
1347 | CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_' | |
1348 | cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))) | |
1349 | ||
1350 | qs.update({ | |
1351 | 'ver': ['2'], | |
1352 | 'cpn': [cpn], | |
1353 | }) | |
1354 | playback_url = compat_urlparse.urlunparse( | |
1355 | parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True))) | |
1356 | ||
1357 | self._download_webpage( | |
1358 | playback_url, video_id, 'Marking watched', | |
1359 | 'Unable to mark watched', fatal=False) | |
1360 | ||
1361 | @staticmethod | |
1362 | def _extract_urls(webpage): | |
1363 | # Embedded YouTube player | |
1364 | entries = [ | |
1365 | unescapeHTML(mobj.group('url')) | |
1366 | for mobj in re.finditer(r'''(?x) | |
1367 | (?: | |
1368 | <iframe[^>]+?src=| | |
1369 | data-video-url=| | |
1370 | <embed[^>]+?src=| | |
1371 | embedSWF\(?:\s*| | |
1372 | <object[^>]+data=| | |
1373 | new\s+SWFObject\( | |
1374 | ) | |
1375 | (["\']) | |
1376 | (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/ | |
1377 | (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?) | |
1378 | \1''', webpage)] | |
1379 | ||
1380 | # lazyYT YouTube embed | |
1381 | entries.extend(list(map( | |
1382 | unescapeHTML, | |
1383 | re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)))) | |
1384 | ||
1385 | # Wordpress "YouTube Video Importer" plugin | |
1386 | matches = re.findall(r'''(?x)<div[^>]+ | |
1387 | class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+ | |
1388 | data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage) | |
1389 | entries.extend(m[-1] for m in matches) | |
1390 | ||
1391 | return entries | |
1392 | ||
1393 | @staticmethod | |
1394 | def _extract_url(webpage): | |
1395 | urls = YoutubeIE._extract_urls(webpage) | |
1396 | return urls[0] if urls else None | |
1397 | ||
1398 | @classmethod | |
1399 | def extract_id(cls, url): | |
1400 | mobj = re.match(cls._VALID_URL, url, re.VERBOSE) | |
1401 | if mobj is None: | |
1402 | raise ExtractorError('Invalid URL: %s' % url) | |
1403 | video_id = mobj.group(2) | |
1404 | return video_id | |
1405 | ||
1406 | def _extract_chapters_from_json(self, data, video_id, duration): | |
1407 | chapters_list = try_get( | |
1408 | data, | |
1409 | lambda x: x['playerOverlays'] | |
1410 | ['playerOverlayRenderer'] | |
1411 | ['decoratedPlayerBarRenderer'] | |
1412 | ['decoratedPlayerBarRenderer'] | |
1413 | ['playerBar'] | |
1414 | ['chapteredPlayerBarRenderer'] | |
1415 | ['chapters'], | |
1416 | list) | |
1417 | if not chapters_list: | |
1418 | return | |
1419 | ||
1420 | def chapter_time(chapter): | |
1421 | return float_or_none( | |
1422 | try_get( | |
1423 | chapter, | |
1424 | lambda x: x['chapterRenderer']['timeRangeStartMillis'], | |
1425 | int), | |
1426 | scale=1000) | |
1427 | chapters = [] | |
1428 | for next_num, chapter in enumerate(chapters_list, start=1): | |
1429 | start_time = chapter_time(chapter) | |
1430 | if start_time is None: | |
1431 | continue | |
1432 | end_time = (chapter_time(chapters_list[next_num]) | |
1433 | if next_num < len(chapters_list) else duration) | |
1434 | if end_time is None: | |
1435 | continue | |
1436 | title = try_get( | |
1437 | chapter, lambda x: x['chapterRenderer']['title']['simpleText'], | |
1438 | compat_str) | |
1439 | chapters.append({ | |
1440 | 'start_time': start_time, | |
1441 | 'end_time': end_time, | |
1442 | 'title': title, | |
1443 | }) | |
1444 | return chapters | |
1445 | ||
1446 | def _extract_yt_initial_variable(self, webpage, regex, video_id, name): | |
1447 | return self._parse_json(self._search_regex( | |
1448 | (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE), | |
1449 | regex), webpage, name, default='{}'), video_id, fatal=False) | |
1450 | ||
1451 | def _real_extract(self, url): | |
1452 | url, smuggled_data = unsmuggle_url(url, {}) | |
1453 | video_id = self._match_id(url) | |
1454 | base_url = self.http_scheme() + '//www.youtube.com/' | |
1455 | webpage_url = base_url + 'watch?v=' + video_id + '&has_verified=1&bpctr=9999999999' | |
1456 | webpage = self._download_webpage(webpage_url, video_id, fatal=False) | |
1457 | ||
1458 | player_response = None | |
1459 | if webpage: | |
1460 | player_response = self._extract_yt_initial_variable( | |
1461 | webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE, | |
1462 | video_id, 'initial player response') | |
1463 | if not player_response: | |
1464 | player_response = self._call_api( | |
1465 | 'player', {'videoId': video_id}, video_id) | |
1466 | ||
1467 | playability_status = player_response.get('playabilityStatus') or {} | |
1468 | if playability_status.get('reason') == 'Sign in to confirm your age': | |
1469 | pr = self._parse_json(try_get(compat_parse_qs( | |
1470 | self._download_webpage( | |
1471 | base_url + 'get_video_info', video_id, | |
1472 | 'Refetching age-gated info webpage', | |
1473 | 'unable to download video info webpage', query={ | |
1474 | 'video_id': video_id, | |
1475 | 'eurl': 'https://youtube.googleapis.com/v/' + video_id, | |
1476 | }, fatal=False)), | |
1477 | lambda x: x['player_response'][0], | |
1478 | compat_str) or '{}', video_id) | |
1479 | if pr: | |
1480 | player_response = pr | |
1481 | ||
1482 | trailer_video_id = try_get( | |
1483 | playability_status, | |
1484 | lambda x: x['errorScreen']['playerLegacyDesktopYpcTrailerRenderer']['trailerVideoId'], | |
1485 | compat_str) | |
1486 | if trailer_video_id: | |
1487 | return self.url_result( | |
1488 | trailer_video_id, self.ie_key(), trailer_video_id) | |
1489 | ||
1490 | def get_text(x): | |
1491 | if not x: | |
1492 | return | |
1493 | return x.get('simpleText') or ''.join([r['text'] for r in x['runs']]) | |
1494 | ||
1495 | search_meta = ( | |
1496 | lambda x: self._html_search_meta(x, webpage, default=None)) \ | |
1497 | if webpage else lambda x: None | |
1498 | ||
1499 | video_details = player_response.get('videoDetails') or {} | |
1500 | microformat = try_get( | |
1501 | player_response, | |
1502 | lambda x: x['microformat']['playerMicroformatRenderer'], | |
1503 | dict) or {} | |
1504 | video_title = video_details.get('title') \ | |
1505 | or get_text(microformat.get('title')) \ | |
1506 | or search_meta(['og:title', 'twitter:title', 'title']) | |
1507 | video_description = video_details.get('shortDescription') | |
1508 | ||
1509 | if not smuggled_data.get('force_singlefeed', False): | |
1510 | if not self._downloader.params.get('noplaylist'): | |
1511 | multifeed_metadata_list = try_get( | |
1512 | player_response, | |
1513 | lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'], | |
1514 | compat_str) | |
1515 | if multifeed_metadata_list: | |
1516 | entries = [] | |
1517 | feed_ids = [] | |
1518 | for feed in multifeed_metadata_list.split(','): | |
1519 | # Unquote should take place before split on comma (,) since textual | |
1520 | # fields may contain comma as well (see | |
1521 | # https://github.com/ytdl-org/youtube-dl/issues/8536) | |
1522 | feed_data = compat_parse_qs( | |
1523 | compat_urllib_parse_unquote_plus(feed)) | |
1524 | ||
1525 | def feed_entry(name): | |
1526 | return try_get( | |
1527 | feed_data, lambda x: x[name][0], compat_str) | |
1528 | ||
1529 | feed_id = feed_entry('id') | |
1530 | if not feed_id: | |
1531 | continue | |
1532 | feed_title = feed_entry('title') | |
1533 | title = video_title | |
1534 | if feed_title: | |
1535 | title += ' (%s)' % feed_title | |
1536 | entries.append({ | |
1537 | '_type': 'url_transparent', | |
1538 | 'ie_key': 'Youtube', | |
1539 | 'url': smuggle_url( | |
1540 | base_url + 'watch?v=' + feed_data['id'][0], | |
1541 | {'force_singlefeed': True}), | |
1542 | 'title': title, | |
1543 | }) | |
1544 | feed_ids.append(feed_id) | |
1545 | self.to_screen( | |
1546 | 'Downloading multifeed video (%s) - add --no-playlist to just download video %s' | |
1547 | % (', '.join(feed_ids), video_id)) | |
1548 | return self.playlist_result( | |
1549 | entries, video_id, video_title, video_description) | |
1550 | else: | |
1551 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
1552 | ||
1553 | formats = [] | |
1554 | itags = [] | |
1555 | itag_qualities = {} | |
1556 | player_url = None | |
1557 | q = qualities(['tiny', 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres']) | |
1558 | streaming_data = player_response.get('streamingData') or {} | |
1559 | streaming_formats = streaming_data.get('formats') or [] | |
1560 | streaming_formats.extend(streaming_data.get('adaptiveFormats') or []) | |
1561 | for fmt in streaming_formats: | |
1562 | if fmt.get('targetDurationSec') or fmt.get('drmFamilies'): | |
1563 | continue | |
1564 | ||
1565 | itag = str_or_none(fmt.get('itag')) | |
1566 | quality = fmt.get('quality') | |
1567 | if itag and quality: | |
1568 | itag_qualities[itag] = quality | |
1569 | # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment | |
1570 | # (adding `&sq=0` to the URL) and parsing emsg box to determine the | |
1571 | # number of fragment that would subsequently requested with (`&sq=N`) | |
1572 | if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF': | |
1573 | continue | |
1574 | ||
1575 | fmt_url = fmt.get('url') | |
1576 | if not fmt_url: | |
1577 | sc = compat_parse_qs(fmt.get('signatureCipher')) | |
1578 | fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0])) | |
1579 | encrypted_sig = try_get(sc, lambda x: x['s'][0]) | |
1580 | if not (sc and fmt_url and encrypted_sig): | |
1581 | continue | |
1582 | if not player_url: | |
1583 | if not webpage: | |
1584 | continue | |
1585 | player_url = self._search_regex( | |
1586 | r'"(?:PLAYER_JS_URL|jsUrl)"\s*:\s*"([^"]+)"', | |
1587 | webpage, 'player URL', fatal=False) | |
1588 | if not player_url: | |
1589 | continue | |
1590 | signature = self._decrypt_signature(sc['s'][0], video_id, player_url) | |
1591 | sp = try_get(sc, lambda x: x['sp'][0]) or 'signature' | |
1592 | fmt_url += '&' + sp + '=' + signature | |
1593 | ||
1594 | if itag: | |
1595 | itags.append(itag) | |
1596 | tbr = float_or_none( | |
1597 | fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) | |
1598 | dct = { | |
1599 | 'asr': int_or_none(fmt.get('audioSampleRate')), | |
1600 | 'filesize': int_or_none(fmt.get('contentLength')), | |
1601 | 'format_id': itag, | |
1602 | 'format_note': fmt.get('qualityLabel') or quality, | |
1603 | 'fps': int_or_none(fmt.get('fps')), | |
1604 | 'height': int_or_none(fmt.get('height')), | |
1605 | 'quality': q(quality), | |
1606 | 'tbr': tbr, | |
1607 | 'url': fmt_url, | |
1608 | 'width': fmt.get('width'), | |
1609 | } | |
1610 | mimetype = fmt.get('mimeType') | |
1611 | if mimetype: | |
1612 | mobj = re.match( | |
1613 | r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', mimetype) | |
1614 | if mobj: | |
1615 | dct['ext'] = mimetype2ext(mobj.group(1)) | |
1616 | dct.update(parse_codecs(mobj.group(2))) | |
1617 | no_audio = dct.get('acodec') == 'none' | |
1618 | no_video = dct.get('vcodec') == 'none' | |
1619 | if no_audio: | |
1620 | dct['vbr'] = tbr | |
1621 | if no_video: | |
1622 | dct['abr'] = tbr | |
1623 | if no_audio or no_video: | |
1624 | dct['downloader_options'] = { | |
1625 | # Youtube throttles chunks >~10M | |
1626 | 'http_chunk_size': 10485760, | |
1627 | } | |
1628 | if dct.get('ext'): | |
1629 | dct['container'] = dct['ext'] + '_dash' | |
1630 | formats.append(dct) | |
1631 | ||
1632 | hls_manifest_url = streaming_data.get('hlsManifestUrl') | |
1633 | if hls_manifest_url: | |
1634 | for f in self._extract_m3u8_formats( | |
1635 | hls_manifest_url, video_id, 'mp4', fatal=False): | |
1636 | itag = self._search_regex( | |
1637 | r'/itag/(\d+)', f['url'], 'itag', default=None) | |
1638 | if itag: | |
1639 | f['format_id'] = itag | |
1640 | formats.append(f) | |
1641 | ||
1642 | if self._downloader.params.get('youtube_include_dash_manifest'): | |
1643 | dash_manifest_url = streaming_data.get('dashManifestUrl') | |
1644 | if dash_manifest_url: | |
1645 | for f in self._extract_mpd_formats( | |
1646 | dash_manifest_url, video_id, fatal=False): | |
1647 | itag = f['format_id'] | |
1648 | if itag in itags: | |
1649 | continue | |
1650 | if itag in itag_qualities: | |
1651 | # Not actually usefull since the sorting is already done with "quality,res,fps,codec" | |
1652 | # but kept to maintain feature parity (and code similarity) with youtube-dl | |
1653 | # Remove if this causes any issues with sorting in future | |
1654 | f['quality'] = q(itag_qualities[itag]) | |
1655 | filesize = int_or_none(self._search_regex( | |
1656 | r'/clen/(\d+)', f.get('fragment_base_url') | |
1657 | or f['url'], 'file size', default=None)) | |
1658 | if filesize: | |
1659 | f['filesize'] = filesize | |
1660 | formats.append(f) | |
1661 | ||
1662 | if not formats: | |
1663 | if not self._downloader.params.get('allow_unplayable_formats') and streaming_data.get('licenseInfos'): | |
1664 | raise ExtractorError( | |
1665 | 'This video is DRM protected.', expected=True) | |
1666 | pemr = try_get( | |
1667 | playability_status, | |
1668 | lambda x: x['errorScreen']['playerErrorMessageRenderer'], | |
1669 | dict) or {} | |
1670 | reason = get_text(pemr.get('reason')) or playability_status.get('reason') | |
1671 | subreason = pemr.get('subreason') | |
1672 | if subreason: | |
1673 | subreason = clean_html(get_text(subreason)) | |
1674 | if subreason == 'The uploader has not made this video available in your country.': | |
1675 | countries = microformat.get('availableCountries') | |
1676 | if not countries: | |
1677 | regions_allowed = search_meta('regionsAllowed') | |
1678 | countries = regions_allowed.split(',') if regions_allowed else None | |
1679 | self.raise_geo_restricted( | |
1680 | subreason, countries) | |
1681 | reason += '\n' + subreason | |
1682 | if reason: | |
1683 | raise ExtractorError(reason, expected=True) | |
1684 | ||
1685 | self._sort_formats(formats) | |
1686 | ||
1687 | keywords = video_details.get('keywords') or [] | |
1688 | if not keywords and webpage: | |
1689 | keywords = [ | |
1690 | unescapeHTML(m.group('content')) | |
1691 | for m in re.finditer(self._meta_regex('og:video:tag'), webpage)] | |
1692 | for keyword in keywords: | |
1693 | if keyword.startswith('yt:stretch='): | |
1694 | w, h = keyword.split('=')[1].split(':') | |
1695 | w, h = int(w), int(h) | |
1696 | if w > 0 and h > 0: | |
1697 | ratio = w / h | |
1698 | for f in formats: | |
1699 | if f.get('vcodec') != 'none': | |
1700 | f['stretched_ratio'] = ratio | |
1701 | ||
1702 | thumbnails = [] | |
1703 | for container in (video_details, microformat): | |
1704 | for thumbnail in (try_get( | |
1705 | container, | |
1706 | lambda x: x['thumbnail']['thumbnails'], list) or []): | |
1707 | thumbnail_url = thumbnail.get('url') | |
1708 | if not thumbnail_url: | |
1709 | continue | |
1710 | thumbnails.append({ | |
1711 | 'height': int_or_none(thumbnail.get('height')), | |
1712 | 'url': thumbnail_url, | |
1713 | 'width': int_or_none(thumbnail.get('width')), | |
1714 | }) | |
1715 | if thumbnails: | |
1716 | break | |
1717 | else: | |
1718 | thumbnail = search_meta(['og:image', 'twitter:image']) | |
1719 | if thumbnail: | |
1720 | thumbnails = [{'url': thumbnail}] | |
1721 | ||
1722 | category = microformat.get('category') or search_meta('genre') | |
1723 | channel_id = video_details.get('channelId') \ | |
1724 | or microformat.get('externalChannelId') \ | |
1725 | or search_meta('channelId') | |
1726 | duration = int_or_none( | |
1727 | video_details.get('lengthSeconds') | |
1728 | or microformat.get('lengthSeconds')) \ | |
1729 | or parse_duration(search_meta('duration')) | |
1730 | is_live = video_details.get('isLive') | |
1731 | owner_profile_url = microformat.get('ownerProfileUrl') | |
1732 | ||
1733 | info = { | |
1734 | 'id': video_id, | |
1735 | 'title': self._live_title(video_title) if is_live else video_title, | |
1736 | 'formats': formats, | |
1737 | 'thumbnails': thumbnails, | |
1738 | 'description': video_description, | |
1739 | 'upload_date': unified_strdate( | |
1740 | microformat.get('uploadDate') | |
1741 | or search_meta('uploadDate')), | |
1742 | 'uploader': video_details['author'], | |
1743 | 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None, | |
1744 | 'uploader_url': owner_profile_url, | |
1745 | 'channel_id': channel_id, | |
1746 | 'channel_url': 'https://www.youtube.com/channel/' + channel_id if channel_id else None, | |
1747 | 'duration': duration, | |
1748 | 'view_count': int_or_none( | |
1749 | video_details.get('viewCount') | |
1750 | or microformat.get('viewCount') | |
1751 | or search_meta('interactionCount')), | |
1752 | 'average_rating': float_or_none(video_details.get('averageRating')), | |
1753 | 'age_limit': 18 if ( | |
1754 | microformat.get('isFamilySafe') is False | |
1755 | or search_meta('isFamilyFriendly') == 'false' | |
1756 | or search_meta('og:restrictions:age') == '18+') else 0, | |
1757 | 'webpage_url': webpage_url, | |
1758 | 'categories': [category] if category else None, | |
1759 | 'tags': keywords, | |
1760 | 'is_live': is_live, | |
1761 | 'playable_in_embed': playability_status.get('playableInEmbed'), | |
1762 | 'was_live': video_details.get('isLiveContent') | |
1763 | } | |
1764 | ||
1765 | pctr = try_get( | |
1766 | player_response, | |
1767 | lambda x: x['captions']['playerCaptionsTracklistRenderer'], dict) | |
1768 | subtitles = {} | |
1769 | if pctr: | |
1770 | def process_language(container, base_url, lang_code, query): | |
1771 | lang_subs = [] | |
1772 | for fmt in self._SUBTITLE_FORMATS: | |
1773 | query.update({ | |
1774 | 'fmt': fmt, | |
1775 | }) | |
1776 | lang_subs.append({ | |
1777 | 'ext': fmt, | |
1778 | 'url': update_url_query(base_url, query), | |
1779 | }) | |
1780 | container[lang_code] = lang_subs | |
1781 | ||
1782 | for caption_track in (pctr.get('captionTracks') or []): | |
1783 | base_url = caption_track.get('baseUrl') | |
1784 | if not base_url: | |
1785 | continue | |
1786 | if caption_track.get('kind') != 'asr': | |
1787 | lang_code = caption_track.get('languageCode') | |
1788 | if not lang_code: | |
1789 | continue | |
1790 | process_language( | |
1791 | subtitles, base_url, lang_code, {}) | |
1792 | continue | |
1793 | automatic_captions = {} | |
1794 | for translation_language in (pctr.get('translationLanguages') or []): | |
1795 | translation_language_code = translation_language.get('languageCode') | |
1796 | if not translation_language_code: | |
1797 | continue | |
1798 | process_language( | |
1799 | automatic_captions, base_url, translation_language_code, | |
1800 | {'tlang': translation_language_code}) | |
1801 | info['automatic_captions'] = automatic_captions | |
1802 | info['subtitles'] = subtitles | |
1803 | ||
1804 | parsed_url = compat_urllib_parse_urlparse(url) | |
1805 | for component in [parsed_url.fragment, parsed_url.query]: | |
1806 | query = compat_parse_qs(component) | |
1807 | for k, v in query.items(): | |
1808 | for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]: | |
1809 | d_k += '_time' | |
1810 | if d_k not in info and k in s_ks: | |
1811 | info[d_k] = parse_duration(query[k][0]) | |
1812 | ||
1813 | # Youtube Music Auto-generated description | |
1814 | if video_description: | |
1815 | 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) | |
1816 | if mobj: | |
1817 | release_year = mobj.group('release_year') | |
1818 | release_date = mobj.group('release_date') | |
1819 | if release_date: | |
1820 | release_date = release_date.replace('-', '') | |
1821 | if not release_year: | |
1822 | release_year = release_date[:4] | |
1823 | info.update({ | |
1824 | 'album': mobj.group('album'.strip()), | |
1825 | 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')), | |
1826 | 'track': mobj.group('track').strip(), | |
1827 | 'release_date': release_date, | |
1828 | 'release_year': int_or_none(release_year), | |
1829 | }) | |
1830 | ||
1831 | initial_data = None | |
1832 | if webpage: | |
1833 | initial_data = self._extract_yt_initial_variable( | |
1834 | webpage, self._YT_INITIAL_DATA_RE, video_id, | |
1835 | 'yt initial data') | |
1836 | if not initial_data: | |
1837 | initial_data = self._call_api( | |
1838 | 'next', {'videoId': video_id}, video_id, fatal=False) | |
1839 | ||
1840 | if not is_live: | |
1841 | try: | |
1842 | # This will error if there is no livechat | |
1843 | initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation'] | |
1844 | info['subtitles']['live_chat'] = [{ | |
1845 | 'video_id': video_id, | |
1846 | 'ext': 'json', | |
1847 | 'protocol': 'youtube_live_chat_replay', | |
1848 | }] | |
1849 | except (KeyError, IndexError, TypeError): | |
1850 | pass | |
1851 | ||
1852 | if initial_data: | |
1853 | chapters = self._extract_chapters_from_json( | |
1854 | initial_data, video_id, duration) | |
1855 | if not chapters: | |
1856 | for engagment_pannel in (initial_data.get('engagementPanels') or []): | |
1857 | contents = try_get( | |
1858 | engagment_pannel, lambda x: x['engagementPanelSectionListRenderer']['content']['macroMarkersListRenderer']['contents'], | |
1859 | list) | |
1860 | if not contents: | |
1861 | continue | |
1862 | ||
1863 | def chapter_time(mmlir): | |
1864 | return parse_duration( | |
1865 | get_text(mmlir.get('timeDescription'))) | |
1866 | ||
1867 | chapters = [] | |
1868 | for next_num, content in enumerate(contents, start=1): | |
1869 | mmlir = content.get('macroMarkersListItemRenderer') or {} | |
1870 | start_time = chapter_time(mmlir) | |
1871 | end_time = chapter_time(try_get( | |
1872 | contents, lambda x: x[next_num]['macroMarkersListItemRenderer'])) \ | |
1873 | if next_num < len(contents) else duration | |
1874 | if start_time is None or end_time is None: | |
1875 | continue | |
1876 | chapters.append({ | |
1877 | 'start_time': start_time, | |
1878 | 'end_time': end_time, | |
1879 | 'title': get_text(mmlir.get('title')), | |
1880 | }) | |
1881 | if chapters: | |
1882 | break | |
1883 | if chapters: | |
1884 | info['chapters'] = chapters | |
1885 | ||
1886 | contents = try_get( | |
1887 | initial_data, | |
1888 | lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], | |
1889 | list) or [] | |
1890 | for content in contents: | |
1891 | vpir = content.get('videoPrimaryInfoRenderer') | |
1892 | if vpir: | |
1893 | stl = vpir.get('superTitleLink') | |
1894 | if stl: | |
1895 | stl = get_text(stl) | |
1896 | if try_get( | |
1897 | vpir, | |
1898 | lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN': | |
1899 | info['location'] = stl | |
1900 | else: | |
1901 | mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl) | |
1902 | if mobj: | |
1903 | info.update({ | |
1904 | 'series': mobj.group(1), | |
1905 | 'season_number': int(mobj.group(2)), | |
1906 | 'episode_number': int(mobj.group(3)), | |
1907 | }) | |
1908 | for tlb in (try_get( | |
1909 | vpir, | |
1910 | lambda x: x['videoActions']['menuRenderer']['topLevelButtons'], | |
1911 | list) or []): | |
1912 | tbr = tlb.get('toggleButtonRenderer') or {} | |
1913 | for getter, regex in [( | |
1914 | lambda x: x['defaultText']['accessibility']['accessibilityData'], | |
1915 | r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([ | |
1916 | lambda x: x['accessibility'], | |
1917 | lambda x: x['accessibilityData']['accessibilityData'], | |
1918 | ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]: | |
1919 | label = (try_get(tbr, getter, dict) or {}).get('label') | |
1920 | if label: | |
1921 | mobj = re.match(regex, label) | |
1922 | if mobj: | |
1923 | info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count')) | |
1924 | break | |
1925 | sbr_tooltip = try_get( | |
1926 | vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip']) | |
1927 | if sbr_tooltip: | |
1928 | like_count, dislike_count = sbr_tooltip.split(' / ') | |
1929 | info.update({ | |
1930 | 'like_count': str_to_int(like_count), | |
1931 | 'dislike_count': str_to_int(dislike_count), | |
1932 | }) | |
1933 | vsir = content.get('videoSecondaryInfoRenderer') | |
1934 | if vsir: | |
1935 | info['channel'] = get_text(try_get( | |
1936 | vsir, | |
1937 | lambda x: x['owner']['videoOwnerRenderer']['title'], | |
1938 | compat_str)) | |
1939 | rows = try_get( | |
1940 | vsir, | |
1941 | lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'], | |
1942 | list) or [] | |
1943 | multiple_songs = False | |
1944 | for row in rows: | |
1945 | if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True: | |
1946 | multiple_songs = True | |
1947 | break | |
1948 | for row in rows: | |
1949 | mrr = row.get('metadataRowRenderer') or {} | |
1950 | mrr_title = mrr.get('title') | |
1951 | if not mrr_title: | |
1952 | continue | |
1953 | mrr_title = get_text(mrr['title']) | |
1954 | mrr_contents_text = get_text(mrr['contents'][0]) | |
1955 | if mrr_title == 'License': | |
1956 | info['license'] = mrr_contents_text | |
1957 | elif not multiple_songs: | |
1958 | if mrr_title == 'Album': | |
1959 | info['album'] = mrr_contents_text | |
1960 | elif mrr_title == 'Artist': | |
1961 | info['artist'] = mrr_contents_text | |
1962 | elif mrr_title == 'Song': | |
1963 | info['track'] = mrr_contents_text | |
1964 | ||
1965 | fallbacks = { | |
1966 | 'channel': 'uploader', | |
1967 | 'channel_id': 'uploader_id', | |
1968 | 'channel_url': 'uploader_url', | |
1969 | } | |
1970 | for to, frm in fallbacks.items(): | |
1971 | if not info.get(to): | |
1972 | info[to] = info.get(frm) | |
1973 | ||
1974 | for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]: | |
1975 | v = info.get(s_k) | |
1976 | if v: | |
1977 | info[d_k] = v | |
1978 | ||
1979 | # get xsrf for annotations or comments | |
1980 | get_annotations = self._downloader.params.get('writeannotations', False) | |
1981 | get_comments = self._downloader.params.get('getcomments', False) | |
1982 | if get_annotations or get_comments: | |
1983 | xsrf_token = None | |
1984 | ytcfg = self._extract_ytcfg(video_id, webpage) | |
1985 | if ytcfg: | |
1986 | xsrf_token = try_get(ytcfg, lambda x: x['XSRF_TOKEN'], compat_str) | |
1987 | if not xsrf_token: | |
1988 | xsrf_token = self._search_regex( | |
1989 | r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P<xsrf_token>(?:(?!\2).)+)\2', | |
1990 | webpage, 'xsrf token', group='xsrf_token', fatal=False) | |
1991 | ||
1992 | # annotations | |
1993 | if get_annotations: | |
1994 | invideo_url = try_get( | |
1995 | player_response, lambda x: x['annotations'][0]['playerAnnotationsUrlsRenderer']['invideoUrl'], compat_str) | |
1996 | if xsrf_token and invideo_url: | |
1997 | xsrf_field_name = None | |
1998 | if ytcfg: | |
1999 | xsrf_field_name = try_get(ytcfg, lambda x: x['XSRF_FIELD_NAME'], compat_str) | |
2000 | if not xsrf_field_name: | |
2001 | xsrf_field_name = self._search_regex( | |
2002 | r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P<xsrf_field_name>\w+)\2', | |
2003 | webpage, 'xsrf field name', | |
2004 | group='xsrf_field_name', default='session_token') | |
2005 | info['annotations'] = self._download_webpage( | |
2006 | self._proto_relative_url(invideo_url), | |
2007 | video_id, note='Downloading annotations', | |
2008 | errnote='Unable to download video annotations', fatal=False, | |
2009 | data=urlencode_postdata({xsrf_field_name: xsrf_token})) | |
2010 | ||
2011 | # Get comments | |
2012 | # TODO: Refactor and move to seperate function | |
2013 | if get_comments: | |
2014 | expected_video_comment_count = 0 | |
2015 | video_comments = [] | |
2016 | ||
2017 | def find_value(html, key, num_chars=2, separator='"'): | |
2018 | pos_begin = html.find(key) + len(key) + num_chars | |
2019 | pos_end = html.find(separator, pos_begin) | |
2020 | return html[pos_begin: pos_end] | |
2021 | ||
2022 | def search_dict(partial, key): | |
2023 | if isinstance(partial, dict): | |
2024 | for k, v in partial.items(): | |
2025 | if k == key: | |
2026 | yield v | |
2027 | else: | |
2028 | for o in search_dict(v, key): | |
2029 | yield o | |
2030 | elif isinstance(partial, list): | |
2031 | for i in partial: | |
2032 | for o in search_dict(i, key): | |
2033 | yield o | |
2034 | ||
2035 | continuations = [] | |
2036 | if initial_data: | |
2037 | try: | |
2038 | ncd = next(search_dict(initial_data, 'nextContinuationData')) | |
2039 | continuations = [ncd['continuation']] | |
2040 | # Handle videos where comments have been disabled entirely | |
2041 | except StopIteration: | |
2042 | pass | |
2043 | ||
2044 | def get_continuation(continuation, session_token, replies=False): | |
2045 | query = { | |
2046 | 'pbj': 1, | |
2047 | 'ctoken': continuation, | |
2048 | } | |
2049 | if replies: | |
2050 | query['action_get_comment_replies'] = 1 | |
2051 | else: | |
2052 | query['action_get_comments'] = 1 | |
2053 | ||
2054 | while True: | |
2055 | content, handle = self._download_webpage_handle( | |
2056 | 'https://www.youtube.com/comment_service_ajax', | |
2057 | video_id, | |
2058 | note=False, | |
2059 | expected_status=[413], | |
2060 | data=urlencode_postdata({ | |
2061 | 'session_token': session_token | |
2062 | }), | |
2063 | query=query, | |
2064 | headers={ | |
2065 | 'Accept': '*/*', | |
2066 | 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:76.0) Gecko/20100101 Firefox/76.0', | |
2067 | 'X-YouTube-Client-Name': '1', | |
2068 | 'X-YouTube-Client-Version': '2.20201202.06.01' | |
2069 | } | |
2070 | ) | |
2071 | ||
2072 | response_code = handle.getcode() | |
2073 | if (response_code == 200): | |
2074 | return self._parse_json(content, video_id) | |
2075 | if (response_code == 413): | |
2076 | return None | |
2077 | raise ExtractorError('Unexpected HTTP error code: %s' % response_code) | |
2078 | ||
2079 | first_continuation = True | |
2080 | chain_msg = '' | |
2081 | self.to_screen('Downloading comments') | |
2082 | while continuations: | |
2083 | continuation = continuations.pop() | |
2084 | comment_response = get_continuation(continuation, xsrf_token) | |
2085 | if not comment_response: | |
2086 | continue | |
2087 | if list(search_dict(comment_response, 'externalErrorMessage')): | |
2088 | raise ExtractorError('Error returned from server: ' + next(search_dict(comment_response, 'externalErrorMessage'))) | |
2089 | ||
2090 | if 'continuationContents' not in comment_response['response']: | |
2091 | # Something is wrong here. Youtube won't accept this continuation token for some reason and responds with a user satisfaction dialog (error?) | |
2092 | continue | |
2093 | # not sure if this actually helps | |
2094 | if 'xsrf_token' in comment_response: | |
2095 | xsrf_token = comment_response['xsrf_token'] | |
2096 | ||
2097 | item_section = comment_response['response']['continuationContents']['itemSectionContinuation'] | |
2098 | if first_continuation: | |
2099 | expected_video_comment_count = int(item_section['header']['commentsHeaderRenderer']['countText']['runs'][0]['text'].replace(' Comments', '').replace('1 Comment', '1').replace(',', '')) | |
2100 | first_continuation = False | |
2101 | if 'contents' not in item_section: | |
2102 | # continuation returned no comments? | |
2103 | # set an empty array as to not break the for loop | |
2104 | item_section['contents'] = [] | |
2105 | ||
2106 | for meta_comment in item_section['contents']: | |
2107 | comment = meta_comment['commentThreadRenderer']['comment']['commentRenderer'] | |
2108 | video_comments.append({ | |
2109 | 'id': comment['commentId'], | |
2110 | 'text': ''.join([c['text'] for c in try_get(comment, lambda x: x['contentText']['runs'], list) or []]), | |
2111 | 'time_text': ''.join([c['text'] for c in comment['publishedTimeText']['runs']]), | |
2112 | 'author': comment.get('authorText', {}).get('simpleText', ''), | |
2113 | 'votes': comment.get('voteCount', {}).get('simpleText', '0'), | |
2114 | 'author_thumbnail': comment['authorThumbnail']['thumbnails'][-1]['url'], | |
2115 | 'parent': 'root' | |
2116 | }) | |
2117 | if 'replies' not in meta_comment['commentThreadRenderer']: | |
2118 | continue | |
2119 | ||
2120 | reply_continuations = [rcn['nextContinuationData']['continuation'] for rcn in meta_comment['commentThreadRenderer']['replies']['commentRepliesRenderer']['continuations']] | |
2121 | while reply_continuations: | |
2122 | time.sleep(1) | |
2123 | continuation = reply_continuations.pop() | |
2124 | replies_data = get_continuation(continuation, xsrf_token, True) | |
2125 | if not replies_data or 'continuationContents' not in replies_data[1]['response']: | |
2126 | continue | |
2127 | ||
2128 | if self._downloader.params.get('verbose', False): | |
2129 | chain_msg = ' (chain %s)' % comment['commentId'] | |
2130 | self.to_screen('Comments downloaded: %d of ~%d%s' % (len(video_comments), expected_video_comment_count, chain_msg)) | |
2131 | reply_comment_meta = replies_data[1]['response']['continuationContents']['commentRepliesContinuation'] | |
2132 | for reply_meta in reply_comment_meta.get('contents', {}): | |
2133 | reply_comment = reply_meta['commentRenderer'] | |
2134 | video_comments.append({ | |
2135 | 'id': reply_comment['commentId'], | |
2136 | 'text': ''.join([c['text'] for c in reply_comment['contentText']['runs']]), | |
2137 | 'time_text': ''.join([c['text'] for c in reply_comment['publishedTimeText']['runs']]), | |
2138 | 'author': reply_comment.get('authorText', {}).get('simpleText', ''), | |
2139 | 'votes': reply_comment.get('voteCount', {}).get('simpleText', '0'), | |
2140 | 'author_thumbnail': reply_comment['authorThumbnail']['thumbnails'][-1]['url'], | |
2141 | 'parent': comment['commentId'] | |
2142 | }) | |
2143 | if 'continuations' not in reply_comment_meta or len(reply_comment_meta['continuations']) == 0: | |
2144 | continue | |
2145 | reply_continuations += [rcn['nextContinuationData']['continuation'] for rcn in reply_comment_meta['continuations']] | |
2146 | ||
2147 | self.to_screen('Comments downloaded: %d of ~%d' % (len(video_comments), expected_video_comment_count)) | |
2148 | if 'continuations' in item_section: | |
2149 | continuations += [ncd['nextContinuationData']['continuation'] for ncd in item_section['continuations']] | |
2150 | time.sleep(1) | |
2151 | ||
2152 | self.to_screen('Total comments downloaded: %d of ~%d' % (len(video_comments), expected_video_comment_count)) | |
2153 | info.update({ | |
2154 | 'comments': video_comments, | |
2155 | 'comment_count': expected_video_comment_count | |
2156 | }) | |
2157 | ||
2158 | self.mark_watched(video_id, player_response) | |
2159 | ||
2160 | return info | |
2161 | ||
2162 | ||
2163 | class YoutubeTabIE(YoutubeBaseInfoExtractor): | |
2164 | IE_DESC = 'YouTube.com tab' | |
2165 | _VALID_URL = r'''(?x) | |
2166 | https?:// | |
2167 | (?:\w+\.)? | |
2168 | (?: | |
2169 | youtube(?:kids)?\.com| | |
2170 | invidio\.us | |
2171 | )/ | |
2172 | (?: | |
2173 | (?:channel|c|user)/| | |
2174 | (?P<not_channel> | |
2175 | feed/|hashtag/| | |
2176 | (?:playlist|watch)\?.*?\blist= | |
2177 | )| | |
2178 | (?!(?:%s)\b) # Direct URLs | |
2179 | ) | |
2180 | (?P<id>[^/?\#&]+) | |
2181 | ''' % YoutubeBaseInfoExtractor._RESERVED_NAMES | |
2182 | IE_NAME = 'youtube:tab' | |
2183 | ||
2184 | _TESTS = [{ | |
2185 | # playlists, multipage | |
2186 | 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid', | |
2187 | 'playlist_mincount': 94, | |
2188 | 'info_dict': { | |
2189 | 'id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
2190 | 'title': 'Игорь Клейнер - Playlists', | |
2191 | 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2', | |
2192 | 'uploader': 'Игорь Клейнер', | |
2193 | 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
2194 | }, | |
2195 | }, { | |
2196 | # playlists, multipage, different order | |
2197 | 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd', | |
2198 | 'playlist_mincount': 94, | |
2199 | 'info_dict': { | |
2200 | 'id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
2201 | 'title': 'Игорь Клейнер - Playlists', | |
2202 | 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2', | |
2203 | 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
2204 | 'uploader': 'Игорь Клейнер', | |
2205 | }, | |
2206 | }, { | |
2207 | # playlists, singlepage | |
2208 | 'url': 'https://www.youtube.com/user/ThirstForScience/playlists', | |
2209 | 'playlist_mincount': 4, | |
2210 | 'info_dict': { | |
2211 | 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ', | |
2212 | 'title': 'ThirstForScience - Playlists', | |
2213 | 'description': 'md5:609399d937ea957b0f53cbffb747a14c', | |
2214 | 'uploader': 'ThirstForScience', | |
2215 | 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ', | |
2216 | } | |
2217 | }, { | |
2218 | 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists', | |
2219 | 'only_matching': True, | |
2220 | }, { | |
2221 | # basic, single video playlist | |
2222 | 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', | |
2223 | 'info_dict': { | |
2224 | 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', | |
2225 | 'uploader': 'Sergey M.', | |
2226 | 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', | |
2227 | 'title': 'youtube-dl public playlist', | |
2228 | }, | |
2229 | 'playlist_count': 1, | |
2230 | }, { | |
2231 | # empty playlist | |
2232 | 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', | |
2233 | 'info_dict': { | |
2234 | 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', | |
2235 | 'uploader': 'Sergey M.', | |
2236 | 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', | |
2237 | 'title': 'youtube-dl empty playlist', | |
2238 | }, | |
2239 | 'playlist_count': 0, | |
2240 | }, { | |
2241 | # Home tab | |
2242 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured', | |
2243 | 'info_dict': { | |
2244 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
2245 | 'title': 'lex will - Home', | |
2246 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
2247 | 'uploader': 'lex will', | |
2248 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
2249 | }, | |
2250 | 'playlist_mincount': 2, | |
2251 | }, { | |
2252 | # Videos tab | |
2253 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos', | |
2254 | 'info_dict': { | |
2255 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
2256 | 'title': 'lex will - Videos', | |
2257 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
2258 | 'uploader': 'lex will', | |
2259 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
2260 | }, | |
2261 | 'playlist_mincount': 975, | |
2262 | }, { | |
2263 | # Videos tab, sorted by popular | |
2264 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid', | |
2265 | 'info_dict': { | |
2266 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
2267 | 'title': 'lex will - Videos', | |
2268 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
2269 | 'uploader': 'lex will', | |
2270 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
2271 | }, | |
2272 | 'playlist_mincount': 199, | |
2273 | }, { | |
2274 | # Playlists tab | |
2275 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists', | |
2276 | 'info_dict': { | |
2277 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
2278 | 'title': 'lex will - Playlists', | |
2279 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
2280 | 'uploader': 'lex will', | |
2281 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
2282 | }, | |
2283 | 'playlist_mincount': 17, | |
2284 | }, { | |
2285 | # Community tab | |
2286 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community', | |
2287 | 'info_dict': { | |
2288 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
2289 | 'title': 'lex will - Community', | |
2290 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
2291 | 'uploader': 'lex will', | |
2292 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
2293 | }, | |
2294 | 'playlist_mincount': 18, | |
2295 | }, { | |
2296 | # Channels tab | |
2297 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels', | |
2298 | 'info_dict': { | |
2299 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
2300 | 'title': 'lex will - Channels', | |
2301 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
2302 | 'uploader': 'lex will', | |
2303 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
2304 | }, | |
2305 | 'playlist_mincount': 12, | |
2306 | }, { | |
2307 | 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
2308 | 'only_matching': True, | |
2309 | }, { | |
2310 | 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
2311 | 'only_matching': True, | |
2312 | }, { | |
2313 | 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
2314 | 'only_matching': True, | |
2315 | }, { | |
2316 | 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', | |
2317 | 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
2318 | 'info_dict': { | |
2319 | 'title': '29C3: Not my department', | |
2320 | 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
2321 | 'uploader': 'Christiaan008', | |
2322 | 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg', | |
2323 | 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268', | |
2324 | }, | |
2325 | 'playlist_count': 96, | |
2326 | }, { | |
2327 | 'note': 'Large playlist', | |
2328 | 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', | |
2329 | 'info_dict': { | |
2330 | 'title': 'Uploads from Cauchemar', | |
2331 | 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', | |
2332 | 'uploader': 'Cauchemar', | |
2333 | 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q', | |
2334 | }, | |
2335 | 'playlist_mincount': 1123, | |
2336 | }, { | |
2337 | # even larger playlist, 8832 videos | |
2338 | 'url': 'http://www.youtube.com/user/NASAgovVideo/videos', | |
2339 | 'only_matching': True, | |
2340 | }, { | |
2341 | 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', | |
2342 | 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', | |
2343 | 'info_dict': { | |
2344 | 'title': 'Uploads from Interstellar Movie', | |
2345 | 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', | |
2346 | 'uploader': 'Interstellar Movie', | |
2347 | 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA', | |
2348 | }, | |
2349 | 'playlist_mincount': 21, | |
2350 | }, { | |
2351 | # https://github.com/ytdl-org/youtube-dl/issues/21844 | |
2352 | 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', | |
2353 | 'info_dict': { | |
2354 | 'title': 'Data Analysis with Dr Mike Pound', | |
2355 | 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', | |
2356 | 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA', | |
2357 | 'uploader': 'Computerphile', | |
2358 | 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487', | |
2359 | }, | |
2360 | 'playlist_mincount': 11, | |
2361 | }, { | |
2362 | 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', | |
2363 | 'only_matching': True, | |
2364 | }, { | |
2365 | # Playlist URL that does not actually serve a playlist | |
2366 | 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4', | |
2367 | 'info_dict': { | |
2368 | 'id': 'FqZTN594JQw', | |
2369 | 'ext': 'webm', | |
2370 | 'title': "Smiley's People 01 detective, Adventure Series, Action", | |
2371 | 'uploader': 'STREEM', | |
2372 | 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng', | |
2373 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng', | |
2374 | 'upload_date': '20150526', | |
2375 | 'license': 'Standard YouTube License', | |
2376 | 'description': 'md5:507cdcb5a49ac0da37a920ece610be80', | |
2377 | 'categories': ['People & Blogs'], | |
2378 | 'tags': list, | |
2379 | 'view_count': int, | |
2380 | 'like_count': int, | |
2381 | 'dislike_count': int, | |
2382 | }, | |
2383 | 'params': { | |
2384 | 'skip_download': True, | |
2385 | }, | |
2386 | 'skip': 'This video is not available.', | |
2387 | 'add_ie': [YoutubeIE.ie_key()], | |
2388 | }, { | |
2389 | 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g', | |
2390 | 'only_matching': True, | |
2391 | }, { | |
2392 | 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM', | |
2393 | 'only_matching': True, | |
2394 | }, { | |
2395 | 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live', | |
2396 | 'info_dict': { | |
2397 | 'id': '9Auq9mYxFEE', | |
2398 | 'ext': 'mp4', | |
2399 | 'title': compat_str, | |
2400 | 'uploader': 'Sky News', | |
2401 | 'uploader_id': 'skynews', | |
2402 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews', | |
2403 | 'upload_date': '20191102', | |
2404 | 'description': 'md5:85ddd75d888674631aaf9599a9a0b0ae', | |
2405 | 'categories': ['News & Politics'], | |
2406 | 'tags': list, | |
2407 | 'like_count': int, | |
2408 | 'dislike_count': int, | |
2409 | }, | |
2410 | 'params': { | |
2411 | 'skip_download': True, | |
2412 | }, | |
2413 | }, { | |
2414 | 'url': 'https://www.youtube.com/user/TheYoungTurks/live', | |
2415 | 'info_dict': { | |
2416 | 'id': 'a48o2S1cPoo', | |
2417 | 'ext': 'mp4', | |
2418 | 'title': 'The Young Turks - Live Main Show', | |
2419 | 'uploader': 'The Young Turks', | |
2420 | 'uploader_id': 'TheYoungTurks', | |
2421 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks', | |
2422 | 'upload_date': '20150715', | |
2423 | 'license': 'Standard YouTube License', | |
2424 | 'description': 'md5:438179573adcdff3c97ebb1ee632b891', | |
2425 | 'categories': ['News & Politics'], | |
2426 | 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'], | |
2427 | 'like_count': int, | |
2428 | 'dislike_count': int, | |
2429 | }, | |
2430 | 'params': { | |
2431 | 'skip_download': True, | |
2432 | }, | |
2433 | 'only_matching': True, | |
2434 | }, { | |
2435 | 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live', | |
2436 | 'only_matching': True, | |
2437 | }, { | |
2438 | 'url': 'https://www.youtube.com/c/CommanderVideoHq/live', | |
2439 | 'only_matching': True, | |
2440 | }, { | |
2441 | 'url': 'https://www.youtube.com/feed/trending', | |
2442 | 'only_matching': True, | |
2443 | }, { | |
2444 | # needs auth | |
2445 | 'url': 'https://www.youtube.com/feed/library', | |
2446 | 'only_matching': True, | |
2447 | }, { | |
2448 | # needs auth | |
2449 | 'url': 'https://www.youtube.com/feed/history', | |
2450 | 'only_matching': True, | |
2451 | }, { | |
2452 | # needs auth | |
2453 | 'url': 'https://www.youtube.com/feed/subscriptions', | |
2454 | 'only_matching': True, | |
2455 | }, { | |
2456 | # needs auth | |
2457 | 'url': 'https://www.youtube.com/feed/watch_later', | |
2458 | 'only_matching': True, | |
2459 | }, { | |
2460 | # no longer available? | |
2461 | 'url': 'https://www.youtube.com/feed/recommended', | |
2462 | 'only_matching': True, | |
2463 | }, { | |
2464 | # inline playlist with not always working continuations | |
2465 | 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C', | |
2466 | 'only_matching': True, | |
2467 | }, { | |
2468 | 'url': 'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8', | |
2469 | 'only_matching': True, | |
2470 | }, { | |
2471 | 'url': 'https://www.youtube.com/course', | |
2472 | 'only_matching': True, | |
2473 | }, { | |
2474 | 'url': 'https://www.youtube.com/zsecurity', | |
2475 | 'only_matching': True, | |
2476 | }, { | |
2477 | 'url': 'http://www.youtube.com/NASAgovVideo/videos', | |
2478 | 'only_matching': True, | |
2479 | }, { | |
2480 | 'url': 'https://www.youtube.com/TheYoungTurks/live', | |
2481 | 'only_matching': True, | |
2482 | }] | |
2483 | ||
2484 | @classmethod | |
2485 | def suitable(cls, url): | |
2486 | return False if YoutubeIE.suitable(url) else super( | |
2487 | YoutubeTabIE, cls).suitable(url) | |
2488 | ||
2489 | def _extract_channel_id(self, webpage): | |
2490 | channel_id = self._html_search_meta( | |
2491 | 'channelId', webpage, 'channel id', default=None) | |
2492 | if channel_id: | |
2493 | return channel_id | |
2494 | channel_url = self._html_search_meta( | |
2495 | ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url', | |
2496 | 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad', | |
2497 | 'twitter:app:url:googleplay'), webpage, 'channel url') | |
2498 | return self._search_regex( | |
2499 | r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+', | |
2500 | channel_url, 'channel id') | |
2501 | ||
2502 | @staticmethod | |
2503 | def _extract_grid_item_renderer(item): | |
2504 | for item_kind in ('Playlist', 'Video', 'Channel'): | |
2505 | renderer = item.get('grid%sRenderer' % item_kind) | |
2506 | if renderer: | |
2507 | return renderer | |
2508 | ||
2509 | def _grid_entries(self, grid_renderer): | |
2510 | for item in grid_renderer['items']: | |
2511 | if not isinstance(item, dict): | |
2512 | continue | |
2513 | renderer = self._extract_grid_item_renderer(item) | |
2514 | if not isinstance(renderer, dict): | |
2515 | continue | |
2516 | title = try_get( | |
2517 | renderer, lambda x: x['title']['runs'][0]['text'], compat_str) | |
2518 | # playlist | |
2519 | playlist_id = renderer.get('playlistId') | |
2520 | if playlist_id: | |
2521 | yield self.url_result( | |
2522 | 'https://www.youtube.com/playlist?list=%s' % playlist_id, | |
2523 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id, | |
2524 | video_title=title) | |
2525 | # video | |
2526 | video_id = renderer.get('videoId') | |
2527 | if video_id: | |
2528 | yield self._extract_video(renderer) | |
2529 | # channel | |
2530 | channel_id = renderer.get('channelId') | |
2531 | if channel_id: | |
2532 | title = try_get( | |
2533 | renderer, lambda x: x['title']['simpleText'], compat_str) | |
2534 | yield self.url_result( | |
2535 | 'https://www.youtube.com/channel/%s' % channel_id, | |
2536 | ie=YoutubeTabIE.ie_key(), video_title=title) | |
2537 | ||
2538 | def _shelf_entries_from_content(self, shelf_renderer): | |
2539 | content = shelf_renderer.get('content') | |
2540 | if not isinstance(content, dict): | |
2541 | return | |
2542 | renderer = content.get('gridRenderer') | |
2543 | if renderer: | |
2544 | # TODO: add support for nested playlists so each shelf is processed | |
2545 | # as separate playlist | |
2546 | # TODO: this includes only first N items | |
2547 | for entry in self._grid_entries(renderer): | |
2548 | yield entry | |
2549 | renderer = content.get('horizontalListRenderer') | |
2550 | if renderer: | |
2551 | # TODO | |
2552 | pass | |
2553 | ||
2554 | def _shelf_entries(self, shelf_renderer, skip_channels=False): | |
2555 | ep = try_get( | |
2556 | shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'], | |
2557 | compat_str) | |
2558 | shelf_url = urljoin('https://www.youtube.com', ep) | |
2559 | if shelf_url: | |
2560 | # Skipping links to another channels, note that checking for | |
2561 | # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL | |
2562 | # will not work | |
2563 | if skip_channels and '/channels?' in shelf_url: | |
2564 | return | |
2565 | title = try_get( | |
2566 | shelf_renderer, lambda x: x['title']['runs'][0]['text'], compat_str) | |
2567 | yield self.url_result(shelf_url, video_title=title) | |
2568 | # Shelf may not contain shelf URL, fallback to extraction from content | |
2569 | for entry in self._shelf_entries_from_content(shelf_renderer): | |
2570 | yield entry | |
2571 | ||
2572 | def _playlist_entries(self, video_list_renderer): | |
2573 | for content in video_list_renderer['contents']: | |
2574 | if not isinstance(content, dict): | |
2575 | continue | |
2576 | renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer') | |
2577 | if not isinstance(renderer, dict): | |
2578 | continue | |
2579 | video_id = renderer.get('videoId') | |
2580 | if not video_id: | |
2581 | continue | |
2582 | yield self._extract_video(renderer) | |
2583 | ||
2584 | r""" # Not needed in the new implementation | |
2585 | def _itemSection_entries(self, item_sect_renderer): | |
2586 | for content in item_sect_renderer['contents']: | |
2587 | if not isinstance(content, dict): | |
2588 | continue | |
2589 | renderer = content.get('videoRenderer', {}) | |
2590 | if not isinstance(renderer, dict): | |
2591 | continue | |
2592 | video_id = renderer.get('videoId') | |
2593 | if not video_id: | |
2594 | continue | |
2595 | yield self._extract_video(renderer) | |
2596 | """ | |
2597 | ||
2598 | def _rich_entries(self, rich_grid_renderer): | |
2599 | renderer = try_get( | |
2600 | rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {} | |
2601 | video_id = renderer.get('videoId') | |
2602 | if not video_id: | |
2603 | return | |
2604 | yield self._extract_video(renderer) | |
2605 | ||
2606 | def _video_entry(self, video_renderer): | |
2607 | video_id = video_renderer.get('videoId') | |
2608 | if video_id: | |
2609 | return self._extract_video(video_renderer) | |
2610 | ||
2611 | def _post_thread_entries(self, post_thread_renderer): | |
2612 | post_renderer = try_get( | |
2613 | post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict) | |
2614 | if not post_renderer: | |
2615 | return | |
2616 | # video attachment | |
2617 | video_renderer = try_get( | |
2618 | post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) | |
2619 | video_id = None | |
2620 | if video_renderer: | |
2621 | entry = self._video_entry(video_renderer) | |
2622 | if entry: | |
2623 | yield entry | |
2624 | # inline video links | |
2625 | runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or [] | |
2626 | for run in runs: | |
2627 | if not isinstance(run, dict): | |
2628 | continue | |
2629 | ep_url = try_get( | |
2630 | run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str) | |
2631 | if not ep_url: | |
2632 | continue | |
2633 | if not YoutubeIE.suitable(ep_url): | |
2634 | continue | |
2635 | ep_video_id = YoutubeIE._match_id(ep_url) | |
2636 | if video_id == ep_video_id: | |
2637 | continue | |
2638 | yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=video_id) | |
2639 | ||
2640 | def _post_thread_continuation_entries(self, post_thread_continuation): | |
2641 | contents = post_thread_continuation.get('contents') | |
2642 | if not isinstance(contents, list): | |
2643 | return | |
2644 | for content in contents: | |
2645 | renderer = content.get('backstagePostThreadRenderer') | |
2646 | if not isinstance(renderer, dict): | |
2647 | continue | |
2648 | for entry in self._post_thread_entries(renderer): | |
2649 | yield entry | |
2650 | ||
2651 | @staticmethod | |
2652 | def _build_continuation_query(continuation, ctp=None): | |
2653 | query = { | |
2654 | 'ctoken': continuation, | |
2655 | 'continuation': continuation, | |
2656 | } | |
2657 | if ctp: | |
2658 | query['itct'] = ctp | |
2659 | return query | |
2660 | ||
2661 | @staticmethod | |
2662 | def _extract_next_continuation_data(renderer): | |
2663 | next_continuation = try_get( | |
2664 | renderer, lambda x: x['continuations'][0]['nextContinuationData'], dict) | |
2665 | if not next_continuation: | |
2666 | return | |
2667 | continuation = next_continuation.get('continuation') | |
2668 | if not continuation: | |
2669 | return | |
2670 | ctp = next_continuation.get('clickTrackingParams') | |
2671 | return YoutubeTabIE._build_continuation_query(continuation, ctp) | |
2672 | ||
2673 | @classmethod | |
2674 | def _extract_continuation(cls, renderer): | |
2675 | next_continuation = cls._extract_next_continuation_data(renderer) | |
2676 | if next_continuation: | |
2677 | return next_continuation | |
2678 | contents = [] | |
2679 | for key in ('contents', 'items'): | |
2680 | contents.extend(try_get(renderer, lambda x: x[key], list) or []) | |
2681 | for content in contents: | |
2682 | if not isinstance(content, dict): | |
2683 | continue | |
2684 | continuation_ep = try_get( | |
2685 | content, lambda x: x['continuationItemRenderer']['continuationEndpoint'], | |
2686 | dict) | |
2687 | if not continuation_ep: | |
2688 | continue | |
2689 | continuation = try_get( | |
2690 | continuation_ep, lambda x: x['continuationCommand']['token'], compat_str) | |
2691 | if not continuation: | |
2692 | continue | |
2693 | ctp = continuation_ep.get('clickTrackingParams') | |
2694 | return YoutubeTabIE._build_continuation_query(continuation, ctp) | |
2695 | ||
2696 | def _entries(self, tab, identity_token): | |
2697 | ||
2698 | def extract_entries(parent_renderer): # this needs to called again for continuation to work with feeds | |
2699 | contents = try_get(parent_renderer, lambda x: x['contents'], list) or [] | |
2700 | for content in contents: | |
2701 | if not isinstance(content, dict): | |
2702 | continue | |
2703 | is_renderer = try_get(content, lambda x: x['itemSectionRenderer'], dict) | |
2704 | if not is_renderer: | |
2705 | renderer = content.get('richItemRenderer') | |
2706 | if renderer: | |
2707 | for entry in self._rich_entries(renderer): | |
2708 | yield entry | |
2709 | continuation_list[0] = self._extract_continuation(parent_renderer) | |
2710 | continue | |
2711 | isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or [] | |
2712 | for isr_content in isr_contents: | |
2713 | if not isinstance(isr_content, dict): | |
2714 | continue | |
2715 | ||
2716 | known_renderers = { | |
2717 | 'playlistVideoListRenderer': self._playlist_entries, | |
2718 | 'gridRenderer': self._grid_entries, | |
2719 | 'shelfRenderer': lambda x: self._shelf_entries(x, tab.get('title') != 'Channels'), | |
2720 | 'backstagePostThreadRenderer': self._post_thread_entries, | |
2721 | 'videoRenderer': lambda x: [self._video_entry(x)], | |
2722 | } | |
2723 | for key, renderer in isr_content.items(): | |
2724 | if key not in known_renderers: | |
2725 | continue | |
2726 | for entry in known_renderers[key](renderer): | |
2727 | if entry: | |
2728 | yield entry | |
2729 | continuation_list[0] = self._extract_continuation(renderer) | |
2730 | break | |
2731 | ||
2732 | if not continuation_list[0]: | |
2733 | continuation_list[0] = self._extract_continuation(is_renderer) | |
2734 | ||
2735 | if not continuation_list[0]: | |
2736 | continuation_list[0] = self._extract_continuation(parent_renderer) | |
2737 | ||
2738 | continuation_list = [None] # Python 2 doesnot support nonlocal | |
2739 | tab_content = try_get(tab, lambda x: x['content'], dict) | |
2740 | if not tab_content: | |
2741 | return | |
2742 | parent_renderer = ( | |
2743 | try_get(tab_content, lambda x: x['sectionListRenderer'], dict) | |
2744 | or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {}) | |
2745 | for entry in extract_entries(parent_renderer): | |
2746 | yield entry | |
2747 | continuation = continuation_list[0] | |
2748 | ||
2749 | headers = { | |
2750 | 'x-youtube-client-name': '1', | |
2751 | 'x-youtube-client-version': '2.20201112.04.01', | |
2752 | } | |
2753 | if identity_token: | |
2754 | headers['x-youtube-identity-token'] = identity_token | |
2755 | ||
2756 | for page_num in itertools.count(1): | |
2757 | if not continuation: | |
2758 | break | |
2759 | count = 0 | |
2760 | retries = 3 | |
2761 | while count <= retries: | |
2762 | try: | |
2763 | # Downloading page may result in intermittent 5xx HTTP error | |
2764 | # that is usually worked around with a retry | |
2765 | browse = self._download_json( | |
2766 | 'https://www.youtube.com/browse_ajax', None, | |
2767 | 'Downloading page %d%s' | |
2768 | % (page_num, ' (retry #%d)' % count if count else ''), | |
2769 | headers=headers, query=continuation) | |
2770 | break | |
2771 | except ExtractorError as e: | |
2772 | if isinstance(e.cause, compat_HTTPError) and e.cause.code in (500, 503): | |
2773 | count += 1 | |
2774 | if count <= retries: | |
2775 | continue | |
2776 | raise | |
2777 | if not browse: | |
2778 | break | |
2779 | response = try_get(browse, lambda x: x[1]['response'], dict) | |
2780 | if not response: | |
2781 | break | |
2782 | ||
2783 | known_continuation_renderers = { | |
2784 | 'playlistVideoListContinuation': self._playlist_entries, | |
2785 | 'gridContinuation': self._grid_entries, | |
2786 | 'itemSectionContinuation': self._post_thread_continuation_entries, | |
2787 | 'sectionListContinuation': extract_entries, # for feeds | |
2788 | } | |
2789 | continuation_contents = try_get( | |
2790 | response, lambda x: x['continuationContents'], dict) or {} | |
2791 | continuation_renderer = None | |
2792 | for key, value in continuation_contents.items(): | |
2793 | if key not in known_continuation_renderers: | |
2794 | continue | |
2795 | continuation_renderer = value | |
2796 | continuation_list = [None] | |
2797 | for entry in known_continuation_renderers[key](continuation_renderer): | |
2798 | yield entry | |
2799 | continuation = continuation_list[0] or self._extract_continuation(continuation_renderer) | |
2800 | break | |
2801 | if continuation_renderer: | |
2802 | continue | |
2803 | ||
2804 | known_renderers = { | |
2805 | 'gridPlaylistRenderer': (self._grid_entries, 'items'), | |
2806 | 'gridVideoRenderer': (self._grid_entries, 'items'), | |
2807 | 'playlistVideoRenderer': (self._playlist_entries, 'contents'), | |
2808 | 'itemSectionRenderer': (self._playlist_entries, 'contents'), | |
2809 | 'richItemRenderer': (extract_entries, 'contents'), # for hashtag | |
2810 | } | |
2811 | continuation_items = try_get( | |
2812 | response, lambda x: x['onResponseReceivedActions'][0]['appendContinuationItemsAction']['continuationItems'], list) | |
2813 | continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {} | |
2814 | video_items_renderer = None | |
2815 | for key, value in continuation_item.items(): | |
2816 | if key not in known_renderers: | |
2817 | continue | |
2818 | video_items_renderer = {known_renderers[key][1]: continuation_items} | |
2819 | continuation_list = [None] | |
2820 | for entry in known_renderers[key][0](video_items_renderer): | |
2821 | yield entry | |
2822 | continuation = continuation_list[0] or self._extract_continuation(video_items_renderer) | |
2823 | break | |
2824 | if video_items_renderer: | |
2825 | continue | |
2826 | break | |
2827 | ||
2828 | @staticmethod | |
2829 | def _extract_selected_tab(tabs): | |
2830 | for tab in tabs: | |
2831 | if try_get(tab, lambda x: x['tabRenderer']['selected'], bool): | |
2832 | return tab['tabRenderer'] | |
2833 | else: | |
2834 | raise ExtractorError('Unable to find selected tab') | |
2835 | ||
2836 | @staticmethod | |
2837 | def _extract_uploader(data): | |
2838 | uploader = {} | |
2839 | sidebar_renderer = try_get( | |
2840 | data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) | |
2841 | if sidebar_renderer: | |
2842 | for item in sidebar_renderer: | |
2843 | if not isinstance(item, dict): | |
2844 | continue | |
2845 | renderer = item.get('playlistSidebarSecondaryInfoRenderer') | |
2846 | if not isinstance(renderer, dict): | |
2847 | continue | |
2848 | owner = try_get( | |
2849 | renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict) | |
2850 | if owner: | |
2851 | uploader['uploader'] = owner.get('text') | |
2852 | uploader['uploader_id'] = try_get( | |
2853 | owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str) | |
2854 | uploader['uploader_url'] = urljoin( | |
2855 | 'https://www.youtube.com/', | |
2856 | try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str)) | |
2857 | return {k: v for k, v in uploader.items() if v is not None} | |
2858 | ||
2859 | def _extract_from_tabs(self, item_id, webpage, data, tabs, identity_token): | |
2860 | playlist_id = title = description = channel_url = channel_name = channel_id = None | |
2861 | thumbnails_list = tags = [] | |
2862 | ||
2863 | selected_tab = self._extract_selected_tab(tabs) | |
2864 | renderer = try_get( | |
2865 | data, lambda x: x['metadata']['channelMetadataRenderer'], dict) | |
2866 | if renderer: | |
2867 | channel_name = renderer.get('title') | |
2868 | channel_url = renderer.get('channelUrl') | |
2869 | channel_id = renderer.get('externalId') | |
2870 | ||
2871 | if not renderer: | |
2872 | renderer = try_get( | |
2873 | data, lambda x: x['metadata']['playlistMetadataRenderer'], dict) | |
2874 | if renderer: | |
2875 | title = renderer.get('title') | |
2876 | description = renderer.get('description', '') | |
2877 | playlist_id = channel_id | |
2878 | tags = renderer.get('keywords', '').split() | |
2879 | thumbnails_list = ( | |
2880 | try_get(renderer, lambda x: x['avatar']['thumbnails'], list) | |
2881 | or try_get( | |
2882 | data, | |
2883 | lambda x: x['sidebar']['playlistSidebarRenderer']['items'][0]['playlistSidebarPrimaryInfoRenderer']['thumbnailRenderer']['playlistVideoThumbnailRenderer']['thumbnail']['thumbnails'], | |
2884 | list) | |
2885 | or []) | |
2886 | ||
2887 | thumbnails = [] | |
2888 | for t in thumbnails_list: | |
2889 | if not isinstance(t, dict): | |
2890 | continue | |
2891 | thumbnail_url = url_or_none(t.get('url')) | |
2892 | if not thumbnail_url: | |
2893 | continue | |
2894 | thumbnails.append({ | |
2895 | 'url': thumbnail_url, | |
2896 | 'width': int_or_none(t.get('width')), | |
2897 | 'height': int_or_none(t.get('height')), | |
2898 | }) | |
2899 | ||
2900 | if playlist_id is None: | |
2901 | playlist_id = item_id | |
2902 | if title is None: | |
2903 | title = playlist_id | |
2904 | title += format_field(selected_tab, 'title', ' - %s') | |
2905 | ||
2906 | metadata = { | |
2907 | 'playlist_id': playlist_id, | |
2908 | 'playlist_title': title, | |
2909 | 'playlist_description': description, | |
2910 | 'uploader': channel_name, | |
2911 | 'uploader_id': channel_id, | |
2912 | 'uploader_url': channel_url, | |
2913 | 'thumbnails': thumbnails, | |
2914 | 'tags': tags, | |
2915 | } | |
2916 | if not channel_id: | |
2917 | metadata.update(self._extract_uploader(data)) | |
2918 | metadata.update({ | |
2919 | 'channel': metadata['uploader'], | |
2920 | 'channel_id': metadata['uploader_id'], | |
2921 | 'channel_url': metadata['uploader_url']}) | |
2922 | return self.playlist_result( | |
2923 | self._entries(selected_tab, identity_token), | |
2924 | **metadata) | |
2925 | ||
2926 | def _extract_from_playlist(self, item_id, url, data, playlist): | |
2927 | title = playlist.get('title') or try_get( | |
2928 | data, lambda x: x['titleText']['simpleText'], compat_str) | |
2929 | playlist_id = playlist.get('playlistId') or item_id | |
2930 | # Inline playlist rendition continuation does not always work | |
2931 | # at Youtube side, so delegating regular tab-based playlist URL | |
2932 | # processing whenever possible. | |
2933 | playlist_url = urljoin(url, try_get( | |
2934 | playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'], | |
2935 | compat_str)) | |
2936 | if playlist_url and playlist_url != url: | |
2937 | return self.url_result( | |
2938 | playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id, | |
2939 | video_title=title) | |
2940 | return self.playlist_result( | |
2941 | self._playlist_entries(playlist), playlist_id=playlist_id, | |
2942 | playlist_title=title) | |
2943 | ||
2944 | @staticmethod | |
2945 | def _extract_alerts(data): | |
2946 | for alert_dict in try_get(data, lambda x: x['alerts'], list) or []: | |
2947 | if not isinstance(alert_dict, dict): | |
2948 | continue | |
2949 | for renderer in alert_dict: | |
2950 | alert = alert_dict[renderer] | |
2951 | alert_type = alert.get('type') | |
2952 | if not alert_type: | |
2953 | continue | |
2954 | message = try_get(alert, lambda x: x['text']['simpleText'], compat_str) | |
2955 | if message: | |
2956 | yield alert_type, message | |
2957 | for run in try_get(alert, lambda x: x['text']['runs'], list) or []: | |
2958 | message = try_get(run, lambda x: x['text'], compat_str) | |
2959 | if message: | |
2960 | yield alert_type, message | |
2961 | ||
2962 | def _extract_identity_token(self, webpage, item_id): | |
2963 | ytcfg = self._extract_ytcfg(item_id, webpage) | |
2964 | if ytcfg: | |
2965 | token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str) | |
2966 | if token: | |
2967 | return token | |
2968 | return self._search_regex( | |
2969 | r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage, | |
2970 | 'identity token', default=None) | |
2971 | ||
2972 | def _real_extract(self, url): | |
2973 | item_id = self._match_id(url) | |
2974 | url = compat_urlparse.urlunparse( | |
2975 | compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com')) | |
2976 | is_home = re.match(r'(?P<pre>%s)(?P<post>/?(?![^#?]).*$)' % self._VALID_URL, url) | |
2977 | if is_home is not None and is_home.group('not_channel') is None and item_id != 'feed': | |
2978 | self._downloader.report_warning( | |
2979 | 'A channel/user page was given. All the channel\'s videos will be downloaded. ' | |
2980 | 'To download only the videos in the home page, add a "/featured" to the URL') | |
2981 | url = '%s/videos%s' % (is_home.group('pre'), is_home.group('post') or '') | |
2982 | ||
2983 | # Handle both video/playlist URLs | |
2984 | qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) | |
2985 | video_id = qs.get('v', [None])[0] | |
2986 | playlist_id = qs.get('list', [None])[0] | |
2987 | ||
2988 | if is_home is not None and is_home.group('not_channel') is not None and is_home.group('not_channel').startswith('watch') and not video_id: | |
2989 | if playlist_id: | |
2990 | self._downloader.report_warning('%s is not a valid Youtube URL. Trying to download playlist %s' % (url, playlist_id)) | |
2991 | url = 'https://www.youtube.com/playlist?list=%s' % playlist_id | |
2992 | # return self.url_result(playlist_id, ie=YoutubePlaylistIE.ie_key()) | |
2993 | else: | |
2994 | raise ExtractorError('Unable to recognize tab page') | |
2995 | if video_id and playlist_id: | |
2996 | if self._downloader.params.get('noplaylist'): | |
2997 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
2998 | return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id) | |
2999 | self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) | |
3000 | ||
3001 | count = 0 | |
3002 | retries = 3 | |
3003 | while count < retries: | |
3004 | # Sometimes youtube returns a webpage with incomplete ytInitialData | |
3005 | webpage = self._download_webpage(url, item_id) | |
3006 | identity_token = self._extract_identity_token(webpage, item_id) | |
3007 | data = self._extract_yt_initial_data(item_id, webpage) | |
3008 | err_msg = None | |
3009 | for alert_type, alert_message in self._extract_alerts(data): | |
3010 | if alert_type.lower() == 'error': | |
3011 | if err_msg: | |
3012 | self._downloader.report_warning('YouTube said: %s - %s' % ('ERROR', err_msg)) | |
3013 | err_msg = alert_message | |
3014 | else: | |
3015 | self._downloader.report_warning('YouTube said: %s - %s' % (alert_type, alert_message)) | |
3016 | if err_msg: | |
3017 | raise ExtractorError('YouTube said: %s' % err_msg, expected=True) | |
3018 | if data.get('contents') or data.get('currentVideoEndpoint'): | |
3019 | break | |
3020 | count += 1 | |
3021 | self.to_screen( | |
3022 | 'Incomplete yt initial data recieved. Retrying (attempt %d of %d)...' % (count, retries)) | |
3023 | ||
3024 | tabs = try_get( | |
3025 | data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list) | |
3026 | if tabs: | |
3027 | return self._extract_from_tabs(item_id, webpage, data, tabs, identity_token) | |
3028 | playlist = try_get( | |
3029 | data, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict) | |
3030 | if playlist: | |
3031 | return self._extract_from_playlist(item_id, url, data, playlist) | |
3032 | # Fallback to video extraction if no playlist alike page is recognized. | |
3033 | # First check for the current video then try the v attribute of URL query. | |
3034 | video_id = try_get( | |
3035 | data, lambda x: x['currentVideoEndpoint']['watchEndpoint']['videoId'], | |
3036 | compat_str) or video_id | |
3037 | if video_id: | |
3038 | return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id) | |
3039 | # Failed to recognize | |
3040 | raise ExtractorError('Unable to recognize tab page') | |
3041 | ||
3042 | ||
3043 | class YoutubePlaylistIE(InfoExtractor): | |
3044 | IE_DESC = 'YouTube.com playlists' | |
3045 | _VALID_URL = r'''(?x)(?: | |
3046 | (?:https?://)? | |
3047 | (?:\w+\.)? | |
3048 | (?: | |
3049 | (?: | |
3050 | youtube(?:kids)?\.com| | |
3051 | invidio\.us | |
3052 | ) | |
3053 | /.*?\?.*?\blist= | |
3054 | )? | |
3055 | (?P<id>%(playlist_id)s) | |
3056 | )''' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE} | |
3057 | IE_NAME = 'youtube:playlist' | |
3058 | _TESTS = [{ | |
3059 | 'note': 'issue #673', | |
3060 | 'url': 'PLBB231211A4F62143', | |
3061 | 'info_dict': { | |
3062 | 'title': '[OLD]Team Fortress 2 (Class-based LP)', | |
3063 | 'id': 'PLBB231211A4F62143', | |
3064 | 'uploader': 'Wickydoo', | |
3065 | 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q', | |
3066 | }, | |
3067 | 'playlist_mincount': 29, | |
3068 | }, { | |
3069 | 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
3070 | 'info_dict': { | |
3071 | 'title': 'YDL_safe_search', | |
3072 | 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
3073 | }, | |
3074 | 'playlist_count': 2, | |
3075 | 'skip': 'This playlist is private', | |
3076 | }, { | |
3077 | 'note': 'embedded', | |
3078 | 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', | |
3079 | 'playlist_count': 4, | |
3080 | 'info_dict': { | |
3081 | 'title': 'JODA15', | |
3082 | 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', | |
3083 | 'uploader': 'milan', | |
3084 | 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw', | |
3085 | } | |
3086 | }, { | |
3087 | 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', | |
3088 | 'playlist_mincount': 982, | |
3089 | 'info_dict': { | |
3090 | 'title': '2018 Chinese New Singles (11/6 updated)', | |
3091 | 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', | |
3092 | 'uploader': 'LBK', | |
3093 | 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA', | |
3094 | } | |
3095 | }, { | |
3096 | 'url': 'TLGGrESM50VT6acwMjAyMjAxNw', | |
3097 | 'only_matching': True, | |
3098 | }, { | |
3099 | # music album playlist | |
3100 | 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM', | |
3101 | 'only_matching': True, | |
3102 | }] | |
3103 | ||
3104 | @classmethod | |
3105 | def suitable(cls, url): | |
3106 | return False if YoutubeTabIE.suitable(url) else super( | |
3107 | YoutubePlaylistIE, cls).suitable(url) | |
3108 | ||
3109 | def _real_extract(self, url): | |
3110 | playlist_id = self._match_id(url) | |
3111 | qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) | |
3112 | if not qs: | |
3113 | qs = {'list': playlist_id} | |
3114 | return self.url_result( | |
3115 | update_url_query('https://www.youtube.com/playlist', qs), | |
3116 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
3117 | ||
3118 | ||
3119 | class YoutubeYtBeIE(InfoExtractor): | |
3120 | IE_DESC = 'youtu.be' | |
3121 | _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} | |
3122 | _TESTS = [{ | |
3123 | 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5', | |
3124 | 'info_dict': { | |
3125 | 'id': 'yeWKywCrFtk', | |
3126 | 'ext': 'mp4', | |
3127 | 'title': 'Small Scale Baler and Braiding Rugs', | |
3128 | 'uploader': 'Backus-Page House Museum', | |
3129 | 'uploader_id': 'backuspagemuseum', | |
3130 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum', | |
3131 | 'upload_date': '20161008', | |
3132 | 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a', | |
3133 | 'categories': ['Nonprofits & Activism'], | |
3134 | 'tags': list, | |
3135 | 'like_count': int, | |
3136 | 'dislike_count': int, | |
3137 | }, | |
3138 | 'params': { | |
3139 | 'noplaylist': True, | |
3140 | 'skip_download': True, | |
3141 | }, | |
3142 | }, { | |
3143 | 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21', | |
3144 | 'only_matching': True, | |
3145 | }] | |
3146 | ||
3147 | def _real_extract(self, url): | |
3148 | mobj = re.match(self._VALID_URL, url) | |
3149 | video_id = mobj.group('id') | |
3150 | playlist_id = mobj.group('playlist_id') | |
3151 | return self.url_result( | |
3152 | update_url_query('https://www.youtube.com/watch', { | |
3153 | 'v': video_id, | |
3154 | 'list': playlist_id, | |
3155 | 'feature': 'youtu.be', | |
3156 | }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
3157 | ||
3158 | ||
3159 | class YoutubeYtUserIE(InfoExtractor): | |
3160 | IE_DESC = 'YouTube.com user videos, URL or "ytuser" keyword' | |
3161 | _VALID_URL = r'ytuser:(?P<id>.+)' | |
3162 | _TESTS = [{ | |
3163 | 'url': 'ytuser:phihag', | |
3164 | 'only_matching': True, | |
3165 | }] | |
3166 | ||
3167 | def _real_extract(self, url): | |
3168 | user_id = self._match_id(url) | |
3169 | return self.url_result( | |
3170 | 'https://www.youtube.com/user/%s' % user_id, | |
3171 | ie=YoutubeTabIE.ie_key(), video_id=user_id) | |
3172 | ||
3173 | ||
3174 | class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): | |
3175 | IE_NAME = 'youtube:favorites' | |
3176 | IE_DESC = 'YouTube.com liked videos, ":ytfav" for short (requires authentication)' | |
3177 | _VALID_URL = r':ytfav(?:ou?rite)?s?' | |
3178 | _LOGIN_REQUIRED = True | |
3179 | _TESTS = [{ | |
3180 | 'url': ':ytfav', | |
3181 | 'only_matching': True, | |
3182 | }, { | |
3183 | 'url': ':ytfavorites', | |
3184 | 'only_matching': True, | |
3185 | }] | |
3186 | ||
3187 | def _real_extract(self, url): | |
3188 | return self.url_result( | |
3189 | 'https://www.youtube.com/playlist?list=LL', | |
3190 | ie=YoutubeTabIE.ie_key()) | |
3191 | ||
3192 | ||
3193 | class YoutubeSearchIE(SearchInfoExtractor, YoutubeBaseInfoExtractor): | |
3194 | IE_DESC = 'YouTube.com searches, "ytsearch" keyword' | |
3195 | # there doesn't appear to be a real limit, for example if you search for | |
3196 | # 'python' you get more than 8.000.000 results | |
3197 | _MAX_RESULTS = float('inf') | |
3198 | IE_NAME = 'youtube:search' | |
3199 | _SEARCH_KEY = 'ytsearch' | |
3200 | _SEARCH_PARAMS = None | |
3201 | _TESTS = [] | |
3202 | ||
3203 | def _entries(self, query, n): | |
3204 | data = { | |
3205 | 'context': { | |
3206 | 'client': { | |
3207 | 'clientName': 'WEB', | |
3208 | 'clientVersion': '2.20201021.03.00', | |
3209 | } | |
3210 | }, | |
3211 | 'query': query, | |
3212 | } | |
3213 | if self._SEARCH_PARAMS: | |
3214 | data['params'] = self._SEARCH_PARAMS | |
3215 | total = 0 | |
3216 | for page_num in itertools.count(1): | |
3217 | search = self._download_json( | |
3218 | 'https://www.youtube.com/youtubei/v1/search?key=AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', | |
3219 | video_id='query "%s"' % query, | |
3220 | note='Downloading page %s' % page_num, | |
3221 | errnote='Unable to download API page', fatal=False, | |
3222 | data=json.dumps(data).encode('utf8'), | |
3223 | headers={'content-type': 'application/json'}) | |
3224 | if not search: | |
3225 | break | |
3226 | slr_contents = try_get( | |
3227 | search, | |
3228 | (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'], | |
3229 | lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']), | |
3230 | list) | |
3231 | if not slr_contents: | |
3232 | break | |
3233 | ||
3234 | # Youtube sometimes adds promoted content to searches, | |
3235 | # changing the index location of videos and token. | |
3236 | # So we search through all entries till we find them. | |
3237 | continuation_token = None | |
3238 | for slr_content in slr_contents: | |
3239 | if continuation_token is None: | |
3240 | continuation_token = try_get( | |
3241 | slr_content, | |
3242 | lambda x: x['continuationItemRenderer']['continuationEndpoint']['continuationCommand']['token'], | |
3243 | compat_str) | |
3244 | ||
3245 | isr_contents = try_get( | |
3246 | slr_content, | |
3247 | lambda x: x['itemSectionRenderer']['contents'], | |
3248 | list) | |
3249 | if not isr_contents: | |
3250 | continue | |
3251 | for content in isr_contents: | |
3252 | if not isinstance(content, dict): | |
3253 | continue | |
3254 | video = content.get('videoRenderer') | |
3255 | if not isinstance(video, dict): | |
3256 | continue | |
3257 | video_id = video.get('videoId') | |
3258 | if not video_id: | |
3259 | continue | |
3260 | ||
3261 | yield self._extract_video(video) | |
3262 | total += 1 | |
3263 | if total == n: | |
3264 | return | |
3265 | ||
3266 | if not continuation_token: | |
3267 | break | |
3268 | data['continuation'] = continuation_token | |
3269 | ||
3270 | def _get_n_results(self, query, n): | |
3271 | """Get a specified number of results for a query""" | |
3272 | return self.playlist_result(self._entries(query, n), query) | |
3273 | ||
3274 | ||
3275 | class YoutubeSearchDateIE(YoutubeSearchIE): | |
3276 | IE_NAME = YoutubeSearchIE.IE_NAME + ':date' | |
3277 | _SEARCH_KEY = 'ytsearchdate' | |
3278 | IE_DESC = 'YouTube.com searches, newest videos first, "ytsearchdate" keyword' | |
3279 | _SEARCH_PARAMS = 'CAI%3D' | |
3280 | ||
3281 | ||
3282 | class YoutubeSearchURLIE(YoutubeSearchIE): | |
3283 | IE_DESC = 'YouTube.com search URLs' | |
3284 | IE_NAME = YoutubeSearchIE.IE_NAME + '_url' | |
3285 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)' | |
3286 | # _MAX_RESULTS = 100 | |
3287 | _TESTS = [{ | |
3288 | 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', | |
3289 | 'playlist_mincount': 5, | |
3290 | 'info_dict': { | |
3291 | 'title': 'youtube-dl test video', | |
3292 | } | |
3293 | }, { | |
3294 | 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB', | |
3295 | 'only_matching': True, | |
3296 | }] | |
3297 | ||
3298 | @classmethod | |
3299 | def _make_valid_url(cls): | |
3300 | return cls._VALID_URL | |
3301 | ||
3302 | def _real_extract(self, url): | |
3303 | qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query) | |
3304 | query = (qs.get('search_query') or qs.get('q'))[0] | |
3305 | self._SEARCH_PARAMS = qs.get('sp', ('',))[0] | |
3306 | return self._get_n_results(query, self._MAX_RESULTS) | |
3307 | ||
3308 | ||
3309 | class YoutubeFeedsInfoExtractor(YoutubeTabIE): | |
3310 | """ | |
3311 | Base class for feed extractors | |
3312 | Subclasses must define the _FEED_NAME property. | |
3313 | """ | |
3314 | _LOGIN_REQUIRED = True | |
3315 | # _MAX_PAGES = 5 | |
3316 | _TESTS = [] | |
3317 | ||
3318 | @property | |
3319 | def IE_NAME(self): | |
3320 | return 'youtube:%s' % self._FEED_NAME | |
3321 | ||
3322 | def _real_initialize(self): | |
3323 | self._login() | |
3324 | ||
3325 | def _real_extract(self, url): | |
3326 | return self.url_result( | |
3327 | 'https://www.youtube.com/feed/%s' % self._FEED_NAME, | |
3328 | ie=YoutubeTabIE.ie_key()) | |
3329 | ||
3330 | ||
3331 | class YoutubeWatchLaterIE(InfoExtractor): | |
3332 | IE_NAME = 'youtube:watchlater' | |
3333 | IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)' | |
3334 | _VALID_URL = r':ytwatchlater' | |
3335 | _TESTS = [{ | |
3336 | 'url': ':ytwatchlater', | |
3337 | 'only_matching': True, | |
3338 | }] | |
3339 | ||
3340 | def _real_extract(self, url): | |
3341 | return self.url_result( | |
3342 | 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key()) | |
3343 | ||
3344 | ||
3345 | class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): | |
3346 | IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)' | |
3347 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?' | |
3348 | _FEED_NAME = 'recommended' | |
3349 | _TESTS = [{ | |
3350 | 'url': ':ytrec', | |
3351 | 'only_matching': True, | |
3352 | }, { | |
3353 | 'url': ':ytrecommended', | |
3354 | 'only_matching': True, | |
3355 | }, { | |
3356 | 'url': 'https://youtube.com', | |
3357 | 'only_matching': True, | |
3358 | }] | |
3359 | ||
3360 | ||
3361 | class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): | |
3362 | IE_DESC = 'YouTube.com subscriptions feed, ":ytsubs" for short (requires authentication)' | |
3363 | _VALID_URL = r':ytsub(?:scription)?s?' | |
3364 | _FEED_NAME = 'subscriptions' | |
3365 | _TESTS = [{ | |
3366 | 'url': ':ytsubs', | |
3367 | 'only_matching': True, | |
3368 | }, { | |
3369 | 'url': ':ytsubscriptions', | |
3370 | 'only_matching': True, | |
3371 | }] | |
3372 | ||
3373 | ||
3374 | class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): | |
3375 | IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)' | |
3376 | _VALID_URL = r':ythistory' | |
3377 | _FEED_NAME = 'history' | |
3378 | _TESTS = [{ | |
3379 | 'url': ':ythistory', | |
3380 | 'only_matching': True, | |
3381 | }] | |
3382 | ||
3383 | ||
3384 | class YoutubeTruncatedURLIE(InfoExtractor): | |
3385 | IE_NAME = 'youtube:truncated_url' | |
3386 | IE_DESC = False # Do not list | |
3387 | _VALID_URL = r'''(?x) | |
3388 | (?:https?://)? | |
3389 | (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/ | |
3390 | (?:watch\?(?: | |
3391 | feature=[a-z_]+| | |
3392 | annotation_id=annotation_[^&]+| | |
3393 | x-yt-cl=[0-9]+| | |
3394 | hl=[^&]*| | |
3395 | t=[0-9]+ | |
3396 | )? | |
3397 | | | |
3398 | attribution_link\?a=[^&]+ | |
3399 | ) | |
3400 | $ | |
3401 | ''' | |
3402 | ||
3403 | _TESTS = [{ | |
3404 | 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041', | |
3405 | 'only_matching': True, | |
3406 | }, { | |
3407 | 'url': 'https://www.youtube.com/watch?', | |
3408 | 'only_matching': True, | |
3409 | }, { | |
3410 | 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534', | |
3411 | 'only_matching': True, | |
3412 | }, { | |
3413 | 'url': 'https://www.youtube.com/watch?feature=foo', | |
3414 | 'only_matching': True, | |
3415 | }, { | |
3416 | 'url': 'https://www.youtube.com/watch?hl=en-GB', | |
3417 | 'only_matching': True, | |
3418 | }, { | |
3419 | 'url': 'https://www.youtube.com/watch?t=2372', | |
3420 | 'only_matching': True, | |
3421 | }] | |
3422 | ||
3423 | def _real_extract(self, url): | |
3424 | raise ExtractorError( | |
3425 | 'Did you forget to quote the URL? Remember that & is a meta ' | |
3426 | 'character in most shells, so you want to put the URL in quotes, ' | |
3427 | 'like youtube-dl ' | |
3428 | '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' | |
3429 | ' or simply youtube-dl BaW_jenozKc .', | |
3430 | expected=True) | |
3431 | ||
3432 | ||
3433 | class YoutubeTruncatedIDIE(InfoExtractor): | |
3434 | IE_NAME = 'youtube:truncated_id' | |
3435 | IE_DESC = False # Do not list | |
3436 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$' | |
3437 | ||
3438 | _TESTS = [{ | |
3439 | 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob', | |
3440 | 'only_matching': True, | |
3441 | }] | |
3442 | ||
3443 | def _real_extract(self, url): | |
3444 | video_id = self._match_id(url) | |
3445 | raise ExtractorError( | |
3446 | 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url), | |
3447 | expected=True) |