]>
Commit | Line | Data |
---|---|---|
c5e8d7af | 1 | # coding: utf-8 |
c5e8d7af | 2 | |
78caa52a PH |
3 | from __future__ import unicode_literals |
4 | ||
5 | ||
0ca96d48 | 6 | import itertools |
c5e8d7af | 7 | import json |
c4417ddb | 8 | import os.path |
d77ab8e2 | 9 | import random |
c5e8d7af | 10 | import re |
42939b61 | 11 | import time |
e0df6211 | 12 | import traceback |
c5e8d7af | 13 | |
b05654f0 | 14 | from .common import InfoExtractor, SearchInfoExtractor |
2b25cb5d | 15 | from ..jsinterp import JSInterpreter |
54256267 | 16 | from ..swfinterp import SWFInterpreter |
4bb4a188 | 17 | from ..compat import ( |
edf3e38e | 18 | compat_chr, |
29f7c58a | 19 | compat_HTTPError, |
8d81f3e3 | 20 | compat_kwargs, |
c5e8d7af | 21 | compat_parse_qs, |
7fd002c0 S |
22 | compat_urllib_parse_unquote, |
23 | compat_urllib_parse_unquote_plus, | |
15707c7e | 24 | compat_urllib_parse_urlencode, |
7c80519c | 25 | compat_urllib_parse_urlparse, |
7c61bd36 | 26 | compat_urlparse, |
c5e8d7af | 27 | compat_str, |
4bb4a188 PH |
28 | ) |
29 | from ..utils import ( | |
27019dbb | 30 | bool_or_none, |
c5e8d7af | 31 | clean_html, |
9b9c5355 | 32 | error_to_compat_str, |
c5e8d7af | 33 | ExtractorError, |
b60419c5 | 34 | format_field, |
2d30521a | 35 | float_or_none, |
4bb4a188 | 36 | get_element_by_id, |
dd27fd17 | 37 | int_or_none, |
94278f72 | 38 | mimetype2ext, |
6310acf5 | 39 | parse_codecs, |
b84071c0 | 40 | parse_count, |
7c80519c | 41 | parse_duration, |
0cb58b02 | 42 | remove_quotes, |
3995d37d | 43 | remove_start, |
cf7e015f | 44 | smuggle_url, |
dbdaaa23 | 45 | str_or_none, |
c93d53f5 | 46 | str_to_int, |
556dbe7f | 47 | try_get, |
c5e8d7af PH |
48 | unescapeHTML, |
49 | unified_strdate, | |
cf7e015f | 50 | unsmuggle_url, |
8bdd16b4 | 51 | update_url_query, |
81c2f20b | 52 | uppercase_escape, |
21c340b8 | 53 | url_or_none, |
6e6bc8da | 54 | urlencode_postdata, |
8bdd16b4 | 55 | urljoin, |
c5e8d7af PH |
56 | ) |
57 | ||
5f6a1245 | 58 | |
de7f3446 | 59 | class YoutubeBaseInfoExtractor(InfoExtractor): |
b2e8bc1b JMF |
60 | """Provide base functions for Youtube extractors""" |
61 | _LOGIN_URL = 'https://accounts.google.com/ServiceLogin' | |
9303ce3e | 62 | _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge' |
e00eb564 S |
63 | |
64 | _LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup' | |
3995d37d S |
65 | _CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge' |
66 | _TFA_URL = 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}' | |
e00eb564 | 67 | |
3462ffa8 | 68 | _RESERVED_NAMES = ( |
29f7c58a | 69 | r'embed|e|watch_popup|channel|c|user|playlist|watch|w|v|movies|results|shared|' |
70 | r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout|' | |
71 | r'feed/(?:watch_later|history|subscriptions|library|trending|recommended)') | |
3462ffa8 | 72 | |
b2e8bc1b JMF |
73 | _NETRC_MACHINE = 'youtube' |
74 | # If True it will raise an error if no login info is provided | |
75 | _LOGIN_REQUIRED = False | |
76 | ||
70d5c17b | 77 | _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)' |
d0ba5587 | 78 | |
b2e8bc1b | 79 | def _set_language(self): |
810fb84d | 80 | self._set_cookie( |
ee0b726c | 81 | '.youtube.com', 'PREF', 'f1=50000000&f6=8&hl=en', |
42939b61 | 82 | # YouTube sets the expire time to about two months |
810fb84d | 83 | expire_time=time.time() + 2 * 30 * 24 * 3600) |
b2e8bc1b | 84 | |
25f14e9f S |
85 | def _ids_to_results(self, ids): |
86 | return [ | |
87 | self.url_result(vid_id, 'Youtube', video_id=vid_id) | |
88 | for vid_id in ids] | |
89 | ||
b2e8bc1b | 90 | def _login(self): |
83317f69 | 91 | """ |
92 | Attempt to log in to YouTube. | |
93 | True is returned if successful or skipped. | |
94 | False is returned if login failed. | |
95 | ||
96 | If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised. | |
97 | """ | |
68217024 | 98 | username, password = self._get_login_info() |
b2e8bc1b JMF |
99 | # No authentication to be performed |
100 | if username is None: | |
70d35d16 | 101 | if self._LOGIN_REQUIRED and self._downloader.params.get('cookiefile') is None: |
69ea8ca4 | 102 | raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) |
957c523e U |
103 | if self._downloader.params.get('cookiefile') and False: # TODO remove 'and False' later - too many people using outdated cookies and open issues, remind them. |
104 | self.to_screen('[Cookies] Reminder - Make sure to always use up to date cookies!') | |
83317f69 | 105 | return True |
b2e8bc1b | 106 | |
7cc3570e PH |
107 | login_page = self._download_webpage( |
108 | self._LOGIN_URL, None, | |
69ea8ca4 PH |
109 | note='Downloading login page', |
110 | errnote='unable to fetch login page', fatal=False) | |
7cc3570e PH |
111 | if login_page is False: |
112 | return | |
b2e8bc1b | 113 | |
1212e997 | 114 | login_form = self._hidden_inputs(login_page) |
c5e8d7af | 115 | |
e00eb564 S |
116 | def req(url, f_req, note, errnote): |
117 | data = login_form.copy() | |
118 | data.update({ | |
119 | 'pstMsg': 1, | |
120 | 'checkConnection': 'youtube', | |
121 | 'checkedDomains': 'youtube', | |
122 | 'hl': 'en', | |
123 | 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]', | |
3995d37d | 124 | 'f.req': json.dumps(f_req), |
e00eb564 S |
125 | 'flowName': 'GlifWebSignIn', |
126 | 'flowEntry': 'ServiceLogin', | |
baf67a60 S |
127 | # TODO: reverse actual botguard identifier generation algo |
128 | 'bgRequest': '["identifier",""]', | |
041bc3ad | 129 | }) |
e00eb564 S |
130 | return self._download_json( |
131 | url, None, note=note, errnote=errnote, | |
132 | transform_source=lambda s: re.sub(r'^[^[]*', '', s), | |
133 | fatal=False, | |
134 | data=urlencode_postdata(data), headers={ | |
135 | 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8', | |
136 | 'Google-Accounts-XSRF': 1, | |
137 | }) | |
138 | ||
3995d37d S |
139 | def warn(message): |
140 | self._downloader.report_warning(message) | |
141 | ||
142 | lookup_req = [ | |
143 | username, | |
144 | None, [], None, 'US', None, None, 2, False, True, | |
145 | [ | |
146 | None, None, | |
147 | [2, 1, None, 1, | |
148 | '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', | |
149 | None, [], 4], | |
150 | 1, [None, None, []], None, None, None, True | |
151 | ], | |
152 | username, | |
153 | ] | |
154 | ||
e00eb564 | 155 | lookup_results = req( |
3995d37d | 156 | self._LOOKUP_URL, lookup_req, |
e00eb564 S |
157 | 'Looking up account info', 'Unable to look up account info') |
158 | ||
159 | if lookup_results is False: | |
160 | return False | |
041bc3ad | 161 | |
3995d37d S |
162 | user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str) |
163 | if not user_hash: | |
164 | warn('Unable to extract user hash') | |
165 | return False | |
166 | ||
167 | challenge_req = [ | |
168 | user_hash, | |
169 | None, 1, None, [1, None, None, None, [password, None, True]], | |
170 | [ | |
171 | 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], | |
172 | 1, [None, None, []], None, None, None, True | |
173 | ]] | |
83317f69 | 174 | |
3995d37d S |
175 | challenge_results = req( |
176 | self._CHALLENGE_URL, challenge_req, | |
177 | 'Logging in', 'Unable to log in') | |
83317f69 | 178 | |
3995d37d | 179 | if challenge_results is False: |
e00eb564 | 180 | return |
83317f69 | 181 | |
3995d37d S |
182 | login_res = try_get(challenge_results, lambda x: x[0][5], list) |
183 | if login_res: | |
184 | login_msg = try_get(login_res, lambda x: x[5], compat_str) | |
185 | warn( | |
186 | 'Unable to login: %s' % 'Invalid password' | |
187 | if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg) | |
188 | return False | |
189 | ||
190 | res = try_get(challenge_results, lambda x: x[0][-1], list) | |
191 | if not res: | |
192 | warn('Unable to extract result entry') | |
193 | return False | |
194 | ||
9a6628aa S |
195 | login_challenge = try_get(res, lambda x: x[0][0], list) |
196 | if login_challenge: | |
197 | challenge_str = try_get(login_challenge, lambda x: x[2], compat_str) | |
198 | if challenge_str == 'TWO_STEP_VERIFICATION': | |
3995d37d S |
199 | # SEND_SUCCESS - TFA code has been successfully sent to phone |
200 | # QUOTA_EXCEEDED - reached the limit of TFA codes | |
9a6628aa | 201 | status = try_get(login_challenge, lambda x: x[5], compat_str) |
3995d37d S |
202 | if status == 'QUOTA_EXCEEDED': |
203 | warn('Exceeded the limit of TFA codes, try later') | |
204 | return False | |
205 | ||
206 | tl = try_get(challenge_results, lambda x: x[1][2], compat_str) | |
207 | if not tl: | |
208 | warn('Unable to extract TL') | |
209 | return False | |
210 | ||
211 | tfa_code = self._get_tfa_info('2-step verification code') | |
212 | ||
213 | if not tfa_code: | |
214 | warn( | |
215 | 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>' | |
216 | '(Note that only TOTP (Google Authenticator App) codes work at this time.)') | |
217 | return False | |
218 | ||
219 | tfa_code = remove_start(tfa_code, 'G-') | |
220 | ||
221 | tfa_req = [ | |
222 | user_hash, None, 2, None, | |
223 | [ | |
224 | 9, None, None, None, None, None, None, None, | |
225 | [None, tfa_code, True, 2] | |
226 | ]] | |
227 | ||
228 | tfa_results = req( | |
229 | self._TFA_URL.format(tl), tfa_req, | |
230 | 'Submitting TFA code', 'Unable to submit TFA code') | |
231 | ||
232 | if tfa_results is False: | |
233 | return False | |
234 | ||
235 | tfa_res = try_get(tfa_results, lambda x: x[0][5], list) | |
236 | if tfa_res: | |
237 | tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str) | |
238 | warn( | |
239 | 'Unable to finish TFA: %s' % 'Invalid TFA code' | |
240 | if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg) | |
241 | return False | |
242 | ||
243 | check_cookie_url = try_get( | |
244 | tfa_results, lambda x: x[0][-1][2], compat_str) | |
9a6628aa S |
245 | else: |
246 | CHALLENGES = { | |
247 | 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.", | |
248 | 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.', | |
249 | 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.", | |
250 | } | |
251 | challenge = CHALLENGES.get( | |
252 | challenge_str, | |
253 | '%s returned error %s.' % (self.IE_NAME, challenge_str)) | |
254 | warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge) | |
255 | return False | |
3995d37d S |
256 | else: |
257 | check_cookie_url = try_get(res, lambda x: x[2], compat_str) | |
258 | ||
259 | if not check_cookie_url: | |
260 | warn('Unable to extract CheckCookie URL') | |
261 | return False | |
e00eb564 S |
262 | |
263 | check_cookie_results = self._download_webpage( | |
3995d37d S |
264 | check_cookie_url, None, 'Checking cookie', fatal=False) |
265 | ||
266 | if check_cookie_results is False: | |
267 | return False | |
e00eb564 | 268 | |
3995d37d S |
269 | if 'https://myaccount.google.com/' not in check_cookie_results: |
270 | warn('Unable to log in') | |
b2e8bc1b | 271 | return False |
e00eb564 | 272 | |
b2e8bc1b JMF |
273 | return True |
274 | ||
30226342 | 275 | def _download_webpage_handle(self, *args, **kwargs): |
c1148516 | 276 | query = kwargs.get('query', {}).copy() |
c1148516 | 277 | kwargs['query'] = query |
30226342 | 278 | return super(YoutubeBaseInfoExtractor, self)._download_webpage_handle( |
8d81f3e3 S |
279 | *args, **compat_kwargs(kwargs)) |
280 | ||
b2e8bc1b JMF |
281 | def _real_initialize(self): |
282 | if self._downloader is None: | |
283 | return | |
42939b61 | 284 | self._set_language() |
b2e8bc1b JMF |
285 | if not self._login(): |
286 | return | |
c5e8d7af | 287 | |
8bdd16b4 | 288 | _DEFAULT_API_DATA = { |
289 | 'context': { | |
290 | 'client': { | |
291 | 'clientName': 'WEB', | |
292 | 'clientVersion': '2.20201021.03.00', | |
293 | } | |
294 | }, | |
295 | } | |
8377574c | 296 | |
a0566bbf | 297 | _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;' |
29f7c58a | 298 | _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;' |
299 | _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)' | |
a0566bbf | 300 | |
8bdd16b4 | 301 | def _call_api(self, ep, query, video_id): |
302 | data = self._DEFAULT_API_DATA.copy() | |
303 | data.update(query) | |
9833e7a0 | 304 | |
8bdd16b4 | 305 | response = self._download_json( |
306 | 'https://www.youtube.com/youtubei/v1/%s' % ep, video_id=video_id, | |
307 | note='Downloading API JSON', errnote='Unable to download API page', | |
308 | data=json.dumps(data).encode('utf8'), | |
309 | headers={'content-type': 'application/json'}, | |
310 | query={'key': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'}) | |
c54f4aad | 311 | |
8bdd16b4 | 312 | return response |
061a75ed | 313 | |
8bdd16b4 | 314 | def _extract_yt_initial_data(self, video_id, webpage): |
315 | return self._parse_json( | |
316 | self._search_regex( | |
29f7c58a | 317 | (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE), |
a0566bbf | 318 | self._YT_INITIAL_DATA_RE), webpage, 'yt initial data'), |
8bdd16b4 | 319 | video_id) |
0c148415 | 320 | |
29f7c58a | 321 | def _extract_ytcfg(self, video_id, webpage): |
322 | return self._parse_json( | |
323 | self._search_regex( | |
324 | r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg', | |
325 | default='{}'), video_id, fatal=False) | |
326 | ||
30a074c2 | 327 | def _extract_video(self, renderer): |
328 | video_id = renderer.get('videoId') | |
329 | title = try_get( | |
330 | renderer, | |
331 | (lambda x: x['title']['runs'][0]['text'], | |
332 | lambda x: x['title']['simpleText']), compat_str) | |
333 | description = try_get( | |
334 | renderer, lambda x: x['descriptionSnippet']['runs'][0]['text'], | |
335 | compat_str) | |
336 | duration = parse_duration(try_get( | |
337 | renderer, lambda x: x['lengthText']['simpleText'], compat_str)) | |
338 | view_count_text = try_get( | |
339 | renderer, lambda x: x['viewCountText']['simpleText'], compat_str) or '' | |
340 | view_count = str_to_int(self._search_regex( | |
341 | r'^([\d,]+)', re.sub(r'\s', '', view_count_text), | |
342 | 'view count', default=None)) | |
343 | uploader = try_get( | |
344 | renderer, lambda x: x['ownerText']['runs'][0]['text'], compat_str) | |
345 | return { | |
346 | '_type': 'url_transparent', | |
347 | 'ie_key': YoutubeIE.ie_key(), | |
348 | 'id': video_id, | |
349 | 'url': video_id, | |
350 | 'title': title, | |
351 | 'description': description, | |
352 | 'duration': duration, | |
353 | 'view_count': view_count, | |
354 | 'uploader': uploader, | |
355 | } | |
356 | ||
0c148415 | 357 | |
360e1ca5 | 358 | class YoutubeIE(YoutubeBaseInfoExtractor): |
78caa52a | 359 | IE_DESC = 'YouTube.com' |
cb7dfeea | 360 | _VALID_URL = r"""(?x)^ |
c5e8d7af | 361 | ( |
edb53e2d | 362 | (?:https?://|//) # http(s):// or protocol-independent URL |
66b48727 | 363 | (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com/| |
484aaeb2 | 364 | (?:www\.)?deturl\.com/www\.youtube\.com/| |
e70dc1d1 | 365 | (?:www\.)?pwnyoutube\.com/| |
8b561bfc | 366 | (?:www\.)?hooktube\.com/| |
f7000f3a | 367 | (?:www\.)?yourepeat\.com/| |
e69ae5b9 | 368 | tube\.majestyc\.net/| |
ba036333 | 369 | # Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances |
77d95677 | 370 | (?:(?:www|dev)\.)?invidio\.us/| |
ba036333 | 371 | (?:(?:www|no)\.)?invidiou\.sh/| |
29f7c58a | 372 | (?:(?:www|fi)\.)?invidious\.snopyta\.org/| |
8ae113ca | 373 | (?:www\.)?invidious\.kabi\.tk/| |
ba036333 | 374 | (?:www\.)?invidious\.13ad\.de/| |
791d2e81 | 375 | (?:www\.)?invidious\.mastodon\.host/| |
29f7c58a | 376 | (?:www\.)?invidious\.zapashcanon\.fr/| |
377 | (?:www\.)?invidious\.kavin\.rocks/| | |
378 | (?:www\.)?invidious\.tube/| | |
379 | (?:www\.)?invidiou\.site/| | |
380 | (?:www\.)?invidious\.site/| | |
381 | (?:www\.)?invidious\.xyz/| | |
494d664e | 382 | (?:www\.)?invidious\.nixnet\.xyz/| |
666d808e | 383 | (?:www\.)?invidious\.drycat\.fr/| |
ba036333 | 384 | (?:www\.)?tube\.poal\.co/| |
29f7c58a | 385 | (?:www\.)?tube\.connect\.cafe/| |
8ae113ca | 386 | (?:www\.)?vid\.wxzm\.sx/| |
29f7c58a | 387 | (?:www\.)?vid\.mint\.lgbt/| |
384bf91f | 388 | (?:www\.)?yewtu\.be/| |
494d664e | 389 | (?:www\.)?yt\.elukerio\.org/| |
894b3826 | 390 | (?:www\.)?yt\.lelux\.fi/| |
1db5ab6b | 391 | (?:www\.)?invidious\.ggc-project\.de/| |
392 | (?:www\.)?yt\.maisputain\.ovh/| | |
393 | (?:www\.)?invidious\.13ad\.de/| | |
394 | (?:www\.)?invidious\.toot\.koeln/| | |
395 | (?:www\.)?invidious\.fdn\.fr/| | |
396 | (?:www\.)?watch\.nettohikari\.com/| | |
bff90fc5 | 397 | (?:www\.)?kgg2m7yk5aybusll\.onion/| |
398 | (?:www\.)?qklhadlycap4cnod\.onion/| | |
399 | (?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion/| | |
400 | (?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion/| | |
401 | (?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion/| | |
402 | (?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion/| | |
33c1c7d8 | 403 | (?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p/| |
1db5ab6b | 404 | (?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion/| |
e69ae5b9 | 405 | youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains |
c5e8d7af PH |
406 | (?:.*?\#/)? # handle anchor (#/) redirect urls |
407 | (?: # the various things that can precede the ID: | |
ac7553d0 | 408 | (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/ |
c5e8d7af | 409 | |(?: # or the v= param in all its forms |
f7000f3a | 410 | (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) |
c5e8d7af | 411 | (?:\?|\#!?) # the params delimiter ? or # or #! |
040ac686 | 412 | (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY) |
c5e8d7af PH |
413 | v= |
414 | ) | |
f4b05232 | 415 | )) |
cbaed4bb S |
416 | |(?: |
417 | youtu\.be| # just youtu.be/xxxx | |
6d4fc66b S |
418 | vid\.plus| # or vid.plus/xxxx |
419 | zwearz\.com/watch| # or zwearz.com/watch/xxxx | |
cbaed4bb | 420 | )/ |
edb53e2d | 421 | |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId= |
f4b05232 | 422 | ) |
c5e8d7af | 423 | )? # all until now is optional -> you can pass the naked ID |
8bdd16b4 | 424 | (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID |
d0ba5587 S |
425 | (?!.*?\blist= |
426 | (?: | |
427 | %(playlist_id)s| # combined list/video URLs are handled by the playlist IE | |
428 | WL # WL are handled by the watch later IE | |
429 | ) | |
430 | ) | |
c5e8d7af | 431 | (?(1).+)? # if we found the ID, everything can follow |
d0ba5587 | 432 | $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE} |
c5e8d7af | 433 | _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' |
e40c758c S |
434 | _PLAYER_INFO_RE = ( |
435 | r'/(?P<id>[a-zA-Z0-9_-]{8,})/player_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?/base\.(?P<ext>[a-z]+)$', | |
436 | r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.(?P<ext>[a-z]+)$', | |
437 | ) | |
2c62dc26 | 438 | _formats = { |
c2d3cb4c | 439 | '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, |
440 | '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, | |
441 | '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}, | |
442 | '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}, | |
443 | '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}, | |
444 | '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
445 | '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
446 | '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
3834d3e3 | 447 | # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well |
c2d3cb4c | 448 | '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}, |
449 | '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
450 | '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
451 | '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
452 | '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
453 | '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, | |
e1a0bfdf | 454 | '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, |
c2d3cb4c | 455 | '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, |
456 | '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
e1a0bfdf | 457 | |
458 | ||
459 | # 3D videos | |
c2d3cb4c | 460 | '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, |
461 | '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, | |
462 | '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
463 | '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
e1a0bfdf | 464 | '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}, |
465 | '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
466 | '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
836a086c | 467 | |
96fb5605 | 468 | # Apple HTTP Live Streaming |
11f12195 | 469 | '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, |
c2d3cb4c | 470 | '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, |
471 | '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
472 | '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
473 | '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
474 | '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
e1a0bfdf | 475 | '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, |
476 | '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}, | |
2c62dc26 PH |
477 | |
478 | # DASH mp4 video | |
d23028a8 S |
479 | '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}, |
480 | '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
481 | '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
482 | '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
483 | '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
067aa17e | 484 | '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559) |
d23028a8 S |
485 | '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}, |
486 | '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
487 | '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
488 | '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
489 | '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
490 | '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
836a086c | 491 | |
f6f1fc92 | 492 | # Dash mp4 audio |
d23028a8 S |
493 | '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}, |
494 | '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}, | |
495 | '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}, | |
496 | '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
497 | '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
498 | '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}, | |
499 | '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}, | |
836a086c AZ |
500 | |
501 | # Dash webm | |
d23028a8 S |
502 | '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, |
503 | '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
504 | '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
505 | '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
506 | '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
507 | '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
508 | '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}, | |
509 | '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
510 | '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
511 | '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
512 | '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
513 | '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
514 | '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
515 | '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
516 | '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
4c6b4764 | 517 | # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug) |
d23028a8 S |
518 | '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, |
519 | '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
520 | '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
521 | '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
522 | '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
523 | '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
2c62dc26 PH |
524 | |
525 | # Dash webm audio | |
d23028a8 S |
526 | '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}, |
527 | '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}, | |
ce6b9a2d | 528 | |
0857baad | 529 | # Dash webm audio with opus inside |
d23028a8 S |
530 | '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}, |
531 | '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}, | |
532 | '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}, | |
0857baad | 533 | |
ce6b9a2d PH |
534 | # RTMP (unnamed) |
535 | '_rtmp': {'protocol': 'rtmp'}, | |
b85eae0f S |
536 | |
537 | # av01 video only formats sometimes served with "unknown" codecs | |
538 | '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}, | |
539 | '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}, | |
540 | '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}, | |
541 | '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}, | |
c5e8d7af | 542 | } |
29f7c58a | 543 | _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt') |
836a086c | 544 | |
fd5c4aab S |
545 | _GEO_BYPASS = False |
546 | ||
78caa52a | 547 | IE_NAME = 'youtube' |
2eb88d95 PH |
548 | _TESTS = [ |
549 | { | |
2d3d2997 | 550 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9', |
4bc3a23e PH |
551 | 'info_dict': { |
552 | 'id': 'BaW_jenozKc', | |
553 | 'ext': 'mp4', | |
3867038a | 554 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', |
4bc3a23e PH |
555 | 'uploader': 'Philipp Hagemeister', |
556 | 'uploader_id': 'phihag', | |
ec85ded8 | 557 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', |
dd4c4492 S |
558 | 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', |
559 | 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', | |
4bc3a23e | 560 | 'upload_date': '20121002', |
3867038a | 561 | 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .', |
4bc3a23e | 562 | 'categories': ['Science & Technology'], |
3867038a | 563 | 'tags': ['youtube-dl'], |
556dbe7f | 564 | 'duration': 10, |
dbdaaa23 | 565 | 'view_count': int, |
3e7c1224 PH |
566 | 'like_count': int, |
567 | 'dislike_count': int, | |
7c80519c | 568 | 'start_time': 1, |
297a564b | 569 | 'end_time': 9, |
2eb88d95 | 570 | } |
0e853ca4 | 571 | }, |
fccd3771 | 572 | { |
4bc3a23e PH |
573 | 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ', |
574 | 'note': 'Embed-only video (#1746)', | |
575 | 'info_dict': { | |
576 | 'id': 'yZIXLfi8CZQ', | |
577 | 'ext': 'mp4', | |
578 | 'upload_date': '20120608', | |
579 | 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012', | |
580 | 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7', | |
581 | 'uploader': 'SET India', | |
94bfcd23 | 582 | 'uploader_id': 'setindia', |
ec85ded8 | 583 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia', |
94bfcd23 | 584 | 'age_limit': 18, |
fccd3771 PH |
585 | } |
586 | }, | |
11b56058 | 587 | { |
8bdd16b4 | 588 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ', |
11b56058 PM |
589 | 'note': 'Use the first video ID in the URL', |
590 | 'info_dict': { | |
591 | 'id': 'BaW_jenozKc', | |
592 | 'ext': 'mp4', | |
3867038a | 593 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', |
11b56058 PM |
594 | 'uploader': 'Philipp Hagemeister', |
595 | 'uploader_id': 'phihag', | |
ec85ded8 | 596 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', |
11b56058 | 597 | 'upload_date': '20121002', |
3867038a | 598 | 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .', |
11b56058 | 599 | 'categories': ['Science & Technology'], |
3867038a | 600 | 'tags': ['youtube-dl'], |
556dbe7f | 601 | 'duration': 10, |
dbdaaa23 | 602 | 'view_count': int, |
11b56058 PM |
603 | 'like_count': int, |
604 | 'dislike_count': int, | |
34a7de29 S |
605 | }, |
606 | 'params': { | |
607 | 'skip_download': True, | |
608 | }, | |
11b56058 | 609 | }, |
dd27fd17 | 610 | { |
2d3d2997 | 611 | 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I', |
4bc3a23e PH |
612 | 'note': '256k DASH audio (format 141) via DASH manifest', |
613 | 'info_dict': { | |
614 | 'id': 'a9LDPn-MO4I', | |
615 | 'ext': 'm4a', | |
616 | 'upload_date': '20121002', | |
617 | 'uploader_id': '8KVIDEO', | |
ec85ded8 | 618 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO', |
4bc3a23e PH |
619 | 'description': '', |
620 | 'uploader': '8KVIDEO', | |
621 | 'title': 'UHDTV TEST 8K VIDEO.mp4' | |
4919603f | 622 | }, |
4bc3a23e PH |
623 | 'params': { |
624 | 'youtube_include_dash_manifest': True, | |
625 | 'format': '141', | |
4919603f | 626 | }, |
de3c7fe0 | 627 | 'skip': 'format 141 not served anymore', |
dd27fd17 | 628 | }, |
8bdd16b4 | 629 | # DASH manifest with encrypted signature |
630 | { | |
631 | 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA', | |
632 | 'info_dict': { | |
633 | 'id': 'IB3lcPjvWLA', | |
634 | 'ext': 'm4a', | |
635 | 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson', | |
636 | 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf', | |
637 | 'duration': 244, | |
638 | 'uploader': 'AfrojackVEVO', | |
639 | 'uploader_id': 'AfrojackVEVO', | |
640 | 'upload_date': '20131011', | |
641 | }, | |
642 | 'params': { | |
643 | 'youtube_include_dash_manifest': True, | |
644 | 'format': '141/bestaudio[ext=m4a]', | |
645 | }, | |
646 | }, | |
aa79ac0c PH |
647 | # Controversy video |
648 | { | |
649 | 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8', | |
650 | 'info_dict': { | |
651 | 'id': 'T4XJQO3qol8', | |
652 | 'ext': 'mp4', | |
556dbe7f | 653 | 'duration': 219, |
aa79ac0c | 654 | 'upload_date': '20100909', |
4fe54c12 | 655 | 'uploader': 'Amazing Atheist', |
aa79ac0c | 656 | 'uploader_id': 'TheAmazingAtheist', |
ec85ded8 | 657 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist', |
aa79ac0c PH |
658 | 'title': 'Burning Everyone\'s Koran', |
659 | 'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms\n\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', | |
660 | } | |
c522adb1 | 661 | }, |
dd2d55f1 | 662 | # Normal age-gate video (embed allowed) |
c522adb1 | 663 | { |
2d3d2997 | 664 | 'url': 'https://youtube.com/watch?v=HtVdAasjOgU', |
c522adb1 JMF |
665 | 'info_dict': { |
666 | 'id': 'HtVdAasjOgU', | |
667 | 'ext': 'mp4', | |
668 | 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer', | |
ec85ded8 | 669 | 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}', |
556dbe7f | 670 | 'duration': 142, |
c522adb1 JMF |
671 | 'uploader': 'The Witcher', |
672 | 'uploader_id': 'WitcherGame', | |
ec85ded8 | 673 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame', |
c522adb1 | 674 | 'upload_date': '20140605', |
34952f09 | 675 | 'age_limit': 18, |
c522adb1 JMF |
676 | }, |
677 | }, | |
8bdd16b4 | 678 | # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421) |
679 | # YouTube Red ad is not captured for creator | |
680 | { | |
681 | 'url': '__2ABJjxzNo', | |
682 | 'info_dict': { | |
683 | 'id': '__2ABJjxzNo', | |
684 | 'ext': 'mp4', | |
685 | 'duration': 266, | |
686 | 'upload_date': '20100430', | |
687 | 'uploader_id': 'deadmau5', | |
688 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5', | |
689 | 'creator': 'Dada Life, deadmau5', | |
690 | 'description': 'md5:12c56784b8032162bb936a5f76d55360', | |
691 | 'uploader': 'deadmau5', | |
692 | 'title': 'Deadmau5 - Some Chords (HD)', | |
693 | 'alt_title': 'This Machine Kills Some Chords', | |
694 | }, | |
695 | 'expected_warnings': [ | |
696 | 'DASH manifest missing', | |
697 | ] | |
698 | }, | |
067aa17e | 699 | # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431) |
e52a40ab PH |
700 | { |
701 | 'url': 'lqQg6PlCWgI', | |
702 | 'info_dict': { | |
703 | 'id': 'lqQg6PlCWgI', | |
704 | 'ext': 'mp4', | |
556dbe7f | 705 | 'duration': 6085, |
90227264 | 706 | 'upload_date': '20150827', |
cbe2bd91 | 707 | 'uploader_id': 'olympic', |
ec85ded8 | 708 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic', |
cbe2bd91 | 709 | 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', |
be49068d | 710 | 'uploader': 'Olympic', |
cbe2bd91 PH |
711 | 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', |
712 | }, | |
713 | 'params': { | |
714 | 'skip_download': 'requires avconv', | |
e52a40ab | 715 | } |
cbe2bd91 | 716 | }, |
6271f1ca PH |
717 | # Non-square pixels |
718 | { | |
719 | 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0', | |
720 | 'info_dict': { | |
721 | 'id': '_b-2C3KPAM0', | |
722 | 'ext': 'mp4', | |
723 | 'stretched_ratio': 16 / 9., | |
556dbe7f | 724 | 'duration': 85, |
6271f1ca PH |
725 | 'upload_date': '20110310', |
726 | 'uploader_id': 'AllenMeow', | |
ec85ded8 | 727 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow', |
6271f1ca | 728 | 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯', |
eb6793ba | 729 | 'uploader': '孫ᄋᄅ', |
6271f1ca PH |
730 | 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', |
731 | }, | |
06b491eb S |
732 | }, |
733 | # url_encoded_fmt_stream_map is empty string | |
734 | { | |
735 | 'url': 'qEJwOuvDf7I', | |
736 | 'info_dict': { | |
737 | 'id': 'qEJwOuvDf7I', | |
f57b7835 | 738 | 'ext': 'webm', |
06b491eb S |
739 | 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге', |
740 | 'description': '', | |
741 | 'upload_date': '20150404', | |
742 | 'uploader_id': 'spbelect', | |
743 | 'uploader': 'Наблюдатели Петербурга', | |
744 | }, | |
745 | 'params': { | |
746 | 'skip_download': 'requires avconv', | |
e323cf3f S |
747 | }, |
748 | 'skip': 'This live event has ended.', | |
06b491eb | 749 | }, |
067aa17e | 750 | # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097) |
da77d856 S |
751 | { |
752 | 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y', | |
753 | 'info_dict': { | |
754 | 'id': 'FIl7x6_3R5Y', | |
eb6793ba | 755 | 'ext': 'webm', |
da77d856 S |
756 | 'title': 'md5:7b81415841e02ecd4313668cde88737a', |
757 | 'description': 'md5:116377fd2963b81ec4ce64b542173306', | |
556dbe7f | 758 | 'duration': 220, |
da77d856 S |
759 | 'upload_date': '20150625', |
760 | 'uploader_id': 'dorappi2000', | |
ec85ded8 | 761 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000', |
da77d856 | 762 | 'uploader': 'dorappi2000', |
eb6793ba | 763 | 'formats': 'mincount:31', |
da77d856 | 764 | }, |
eb6793ba | 765 | 'skip': 'not actual anymore', |
2ee8f5d8 | 766 | }, |
8a1a26ce YCH |
767 | # DASH manifest with segment_list |
768 | { | |
769 | 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8', | |
770 | 'md5': '8ce563a1d667b599d21064e982ab9e31', | |
771 | 'info_dict': { | |
772 | 'id': 'CsmdDsKjzN8', | |
773 | 'ext': 'mp4', | |
17ee98e1 | 774 | 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510 |
8a1a26ce YCH |
775 | 'uploader': 'Airtek', |
776 | 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.', | |
777 | 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ', | |
778 | 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015', | |
779 | }, | |
780 | 'params': { | |
781 | 'youtube_include_dash_manifest': True, | |
782 | 'format': '135', # bestvideo | |
be49068d S |
783 | }, |
784 | 'skip': 'This live event has ended.', | |
2ee8f5d8 | 785 | }, |
cf7e015f S |
786 | { |
787 | # Multifeed videos (multiple cameras), URL is for Main Camera | |
788 | 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs', | |
789 | 'info_dict': { | |
790 | 'id': 'jqWvoWXjCVs', | |
791 | 'title': 'teamPGP: Rocket League Noob Stream', | |
792 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
793 | }, | |
794 | 'playlist': [{ | |
795 | 'info_dict': { | |
796 | 'id': 'jqWvoWXjCVs', | |
797 | 'ext': 'mp4', | |
798 | 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)', | |
799 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
556dbe7f | 800 | 'duration': 7335, |
cf7e015f S |
801 | 'upload_date': '20150721', |
802 | 'uploader': 'Beer Games Beer', | |
803 | 'uploader_id': 'beergamesbeer', | |
ec85ded8 | 804 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', |
7caf9830 | 805 | 'license': 'Standard YouTube License', |
cf7e015f S |
806 | }, |
807 | }, { | |
808 | 'info_dict': { | |
809 | 'id': '6h8e8xoXJzg', | |
810 | 'ext': 'mp4', | |
811 | 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)', | |
812 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
556dbe7f | 813 | 'duration': 7337, |
cf7e015f S |
814 | 'upload_date': '20150721', |
815 | 'uploader': 'Beer Games Beer', | |
816 | 'uploader_id': 'beergamesbeer', | |
ec85ded8 | 817 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', |
7caf9830 | 818 | 'license': 'Standard YouTube License', |
cf7e015f S |
819 | }, |
820 | }, { | |
821 | 'info_dict': { | |
822 | 'id': 'PUOgX5z9xZw', | |
823 | 'ext': 'mp4', | |
824 | 'title': 'teamPGP: Rocket League Noob Stream (grizzle)', | |
825 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
556dbe7f | 826 | 'duration': 7337, |
cf7e015f S |
827 | 'upload_date': '20150721', |
828 | 'uploader': 'Beer Games Beer', | |
829 | 'uploader_id': 'beergamesbeer', | |
ec85ded8 | 830 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', |
7caf9830 | 831 | 'license': 'Standard YouTube License', |
cf7e015f S |
832 | }, |
833 | }, { | |
834 | 'info_dict': { | |
835 | 'id': 'teuwxikvS5k', | |
836 | 'ext': 'mp4', | |
837 | 'title': 'teamPGP: Rocket League Noob Stream (zim)', | |
838 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
556dbe7f | 839 | 'duration': 7334, |
cf7e015f S |
840 | 'upload_date': '20150721', |
841 | 'uploader': 'Beer Games Beer', | |
842 | 'uploader_id': 'beergamesbeer', | |
ec85ded8 | 843 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', |
7caf9830 | 844 | 'license': 'Standard YouTube License', |
cf7e015f S |
845 | }, |
846 | }], | |
847 | 'params': { | |
848 | 'skip_download': True, | |
849 | }, | |
4fe54c12 | 850 | 'skip': 'This video is not available.', |
cbaed4bb | 851 | }, |
f9f49d87 | 852 | { |
067aa17e | 853 | # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536) |
f9f49d87 S |
854 | 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo', |
855 | 'info_dict': { | |
856 | 'id': 'gVfLd0zydlo', | |
857 | 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30', | |
858 | }, | |
859 | 'playlist_count': 2, | |
be49068d | 860 | 'skip': 'Not multifeed anymore', |
f9f49d87 | 861 | }, |
cbaed4bb | 862 | { |
2d3d2997 | 863 | 'url': 'https://vid.plus/FlRa-iH7PGw', |
cbaed4bb | 864 | 'only_matching': True, |
0e49d9a6 | 865 | }, |
6d4fc66b | 866 | { |
2d3d2997 | 867 | 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html', |
6d4fc66b S |
868 | 'only_matching': True, |
869 | }, | |
0e49d9a6 | 870 | { |
067aa17e | 871 | # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468) |
a8776b10 | 872 | # Also tests cut-off URL expansion in video description (see |
067aa17e S |
873 | # https://github.com/ytdl-org/youtube-dl/issues/1892, |
874 | # https://github.com/ytdl-org/youtube-dl/issues/8164) | |
0e49d9a6 LL |
875 | 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg', |
876 | 'info_dict': { | |
877 | 'id': 'lsguqyKfVQg', | |
878 | 'ext': 'mp4', | |
879 | 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21', | |
eb6793ba | 880 | 'alt_title': 'Dark Walk - Position Music', |
0e49d9a6 | 881 | 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a', |
556dbe7f | 882 | 'duration': 133, |
0e49d9a6 LL |
883 | 'upload_date': '20151119', |
884 | 'uploader_id': 'IronSoulElf', | |
ec85ded8 | 885 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf', |
0e49d9a6 | 886 | 'uploader': 'IronSoulElf', |
eb6793ba S |
887 | 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan', |
888 | 'track': 'Dark Walk - Position Music', | |
889 | 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan', | |
92bc97d3 | 890 | 'album': 'Position Music - Production Music Vol. 143 - Dark Walk', |
0e49d9a6 LL |
891 | }, |
892 | 'params': { | |
893 | 'skip_download': True, | |
894 | }, | |
895 | }, | |
61f92af1 | 896 | { |
067aa17e | 897 | # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468) |
61f92af1 S |
898 | 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8', |
899 | 'only_matching': True, | |
900 | }, | |
313dfc45 LL |
901 | { |
902 | # Video with yt:stretch=17:0 | |
903 | 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM', | |
904 | 'info_dict': { | |
905 | 'id': 'Q39EVAstoRM', | |
906 | 'ext': 'mp4', | |
907 | 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4', | |
908 | 'description': 'md5:ee18a25c350637c8faff806845bddee9', | |
909 | 'upload_date': '20151107', | |
910 | 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA', | |
911 | 'uploader': 'CH GAMER DROID', | |
912 | }, | |
913 | 'params': { | |
914 | 'skip_download': True, | |
915 | }, | |
be49068d | 916 | 'skip': 'This video does not exist.', |
313dfc45 | 917 | }, |
7caf9830 S |
918 | { |
919 | # Video licensed under Creative Commons | |
920 | 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA', | |
921 | 'info_dict': { | |
922 | 'id': 'M4gD1WSo5mA', | |
923 | 'ext': 'mp4', | |
924 | 'title': 'md5:e41008789470fc2533a3252216f1c1d1', | |
925 | 'description': 'md5:a677553cf0840649b731a3024aeff4cc', | |
556dbe7f | 926 | 'duration': 721, |
7caf9830 S |
927 | 'upload_date': '20150127', |
928 | 'uploader_id': 'BerkmanCenter', | |
ec85ded8 | 929 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter', |
556dbe7f | 930 | 'uploader': 'The Berkman Klein Center for Internet & Society', |
7caf9830 S |
931 | 'license': 'Creative Commons Attribution license (reuse allowed)', |
932 | }, | |
933 | 'params': { | |
934 | 'skip_download': True, | |
935 | }, | |
936 | }, | |
fd050249 S |
937 | { |
938 | # Channel-like uploader_url | |
939 | 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg', | |
940 | 'info_dict': { | |
941 | 'id': 'eQcmzGIKrzg', | |
942 | 'ext': 'mp4', | |
943 | 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders', | |
944 | 'description': 'md5:dda0d780d5a6e120758d1711d062a867', | |
556dbe7f | 945 | 'duration': 4060, |
fd050249 | 946 | 'upload_date': '20151119', |
eb6793ba | 947 | 'uploader': 'Bernie Sanders', |
fd050249 | 948 | 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg', |
ec85ded8 | 949 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg', |
fd050249 S |
950 | 'license': 'Creative Commons Attribution license (reuse allowed)', |
951 | }, | |
952 | 'params': { | |
953 | 'skip_download': True, | |
954 | }, | |
955 | }, | |
040ac686 S |
956 | { |
957 | 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY', | |
958 | 'only_matching': True, | |
7f29cf54 S |
959 | }, |
960 | { | |
067aa17e | 961 | # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059) |
7f29cf54 S |
962 | 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo', |
963 | 'only_matching': True, | |
6496ccb4 S |
964 | }, |
965 | { | |
966 | # Rental video preview | |
967 | 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg', | |
968 | 'info_dict': { | |
969 | 'id': 'uGpuVWrhIzE', | |
970 | 'ext': 'mp4', | |
971 | 'title': 'Piku - Trailer', | |
972 | 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb', | |
973 | 'upload_date': '20150811', | |
974 | 'uploader': 'FlixMatrix', | |
975 | 'uploader_id': 'FlixMatrixKaravan', | |
ec85ded8 | 976 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan', |
6496ccb4 S |
977 | 'license': 'Standard YouTube License', |
978 | }, | |
979 | 'params': { | |
980 | 'skip_download': True, | |
981 | }, | |
eb6793ba | 982 | 'skip': 'This video is not available.', |
022a5d66 | 983 | }, |
12afdc2a S |
984 | { |
985 | # YouTube Red video with episode data | |
986 | 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4', | |
987 | 'info_dict': { | |
988 | 'id': 'iqKdEhx-dD4', | |
989 | 'ext': 'mp4', | |
990 | 'title': 'Isolation - Mind Field (Ep 1)', | |
4fe54c12 | 991 | 'description': 'md5:46a29be4ceffa65b92d277b93f463c0f', |
556dbe7f | 992 | 'duration': 2085, |
12afdc2a S |
993 | 'upload_date': '20170118', |
994 | 'uploader': 'Vsauce', | |
995 | 'uploader_id': 'Vsauce', | |
996 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce', | |
12afdc2a S |
997 | 'series': 'Mind Field', |
998 | 'season_number': 1, | |
999 | 'episode_number': 1, | |
1000 | }, | |
1001 | 'params': { | |
1002 | 'skip_download': True, | |
1003 | }, | |
1004 | 'expected_warnings': [ | |
1005 | 'Skipping DASH manifest', | |
1006 | ], | |
1007 | }, | |
c7121fa7 S |
1008 | { |
1009 | # The following content has been identified by the YouTube community | |
1010 | # as inappropriate or offensive to some audiences. | |
1011 | 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI', | |
1012 | 'info_dict': { | |
1013 | 'id': '6SJNVb0GnPI', | |
1014 | 'ext': 'mp4', | |
1015 | 'title': 'Race Differences in Intelligence', | |
1016 | 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1', | |
1017 | 'duration': 965, | |
1018 | 'upload_date': '20140124', | |
1019 | 'uploader': 'New Century Foundation', | |
1020 | 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg', | |
1021 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg', | |
c7121fa7 S |
1022 | }, |
1023 | 'params': { | |
1024 | 'skip_download': True, | |
1025 | }, | |
1026 | }, | |
022a5d66 S |
1027 | { |
1028 | # itag 212 | |
1029 | 'url': '1t24XAntNCY', | |
1030 | 'only_matching': True, | |
fd5c4aab S |
1031 | }, |
1032 | { | |
1033 | # geo restricted to JP | |
1034 | 'url': 'sJL6WA-aGkQ', | |
1035 | 'only_matching': True, | |
1036 | }, | |
cd5a74a2 S |
1037 | { |
1038 | 'url': 'https://invidio.us/watch?v=BaW_jenozKc', | |
1039 | 'only_matching': True, | |
1040 | }, | |
825cd268 RA |
1041 | { |
1042 | # DRM protected | |
1043 | 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc', | |
1044 | 'only_matching': True, | |
4fe54c12 S |
1045 | }, |
1046 | { | |
1047 | # Video with unsupported adaptive stream type formats | |
1048 | 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U', | |
1049 | 'info_dict': { | |
1050 | 'id': 'Z4Vy8R84T1U', | |
1051 | 'ext': 'mp4', | |
1052 | 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta', | |
1053 | 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', | |
1054 | 'duration': 433, | |
1055 | 'upload_date': '20130923', | |
1056 | 'uploader': 'Amelia Putri Harwita', | |
1057 | 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q', | |
1058 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q', | |
1059 | 'formats': 'maxcount:10', | |
1060 | }, | |
1061 | 'params': { | |
1062 | 'skip_download': True, | |
1063 | 'youtube_include_dash_manifest': False, | |
1064 | }, | |
5429d6a9 | 1065 | 'skip': 'not actual anymore', |
5caabd3c | 1066 | }, |
1067 | { | |
822b9d9c | 1068 | # Youtube Music Auto-generated description |
5caabd3c | 1069 | 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs', |
1070 | 'info_dict': { | |
1071 | 'id': 'MgNrAu2pzNs', | |
1072 | 'ext': 'mp4', | |
1073 | 'title': 'Voyeur Girl', | |
1074 | 'description': 'md5:7ae382a65843d6df2685993e90a8628f', | |
1075 | 'upload_date': '20190312', | |
5429d6a9 S |
1076 | 'uploader': 'Stephen - Topic', |
1077 | 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA', | |
5caabd3c | 1078 | 'artist': 'Stephen', |
1079 | 'track': 'Voyeur Girl', | |
1080 | 'album': 'it\'s too much love to know my dear', | |
1081 | 'release_date': '20190313', | |
1082 | 'release_year': 2019, | |
1083 | }, | |
1084 | 'params': { | |
1085 | 'skip_download': True, | |
1086 | }, | |
1087 | }, | |
66b48727 RA |
1088 | { |
1089 | 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q', | |
1090 | 'only_matching': True, | |
1091 | }, | |
011e75e6 S |
1092 | { |
1093 | # invalid -> valid video id redirection | |
1094 | 'url': 'DJztXj2GPfl', | |
1095 | 'info_dict': { | |
1096 | 'id': 'DJztXj2GPfk', | |
1097 | 'ext': 'mp4', | |
1098 | 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)', | |
1099 | 'description': 'md5:bf577a41da97918e94fa9798d9228825', | |
1100 | 'upload_date': '20090125', | |
1101 | 'uploader': 'Prochorowka', | |
1102 | 'uploader_id': 'Prochorowka', | |
1103 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka', | |
1104 | 'artist': 'Panjabi MC', | |
1105 | 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix', | |
1106 | 'album': 'Beware of the Boys (Mundian To Bach Ke)', | |
1107 | }, | |
1108 | 'params': { | |
1109 | 'skip_download': True, | |
1110 | }, | |
ea74e00b DP |
1111 | }, |
1112 | { | |
1113 | # empty description results in an empty string | |
1114 | 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k', | |
1115 | 'info_dict': { | |
1116 | 'id': 'x41yOUIvK2k', | |
1117 | 'ext': 'mp4', | |
1118 | 'title': 'IMG 3456', | |
1119 | 'description': '', | |
1120 | 'upload_date': '20170613', | |
1121 | 'uploader_id': 'ElevageOrVert', | |
1122 | 'uploader': 'ElevageOrVert', | |
1123 | }, | |
1124 | 'params': { | |
1125 | 'skip_download': True, | |
1126 | }, | |
1127 | }, | |
a0566bbf | 1128 | { |
29f7c58a | 1129 | # with '};' inside yt initial data (see [1]) |
1130 | # see [2] for an example with '};' inside ytInitialPlayerResponse | |
1131 | # 1. https://github.com/ytdl-org/youtube-dl/issues/27093 | |
1132 | # 2. https://github.com/ytdl-org/youtube-dl/issues/27216 | |
a0566bbf | 1133 | 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no', |
1134 | 'info_dict': { | |
1135 | 'id': 'CHqg6qOn4no', | |
1136 | 'ext': 'mp4', | |
1137 | 'title': 'Part 77 Sort a list of simple types in c#', | |
1138 | 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc', | |
1139 | 'upload_date': '20130831', | |
1140 | 'uploader_id': 'kudvenkat', | |
1141 | 'uploader': 'kudvenkat', | |
1142 | }, | |
1143 | 'params': { | |
1144 | 'skip_download': True, | |
1145 | }, | |
1146 | }, | |
29f7c58a | 1147 | { |
1148 | # another example of '};' in ytInitialData | |
1149 | 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY', | |
1150 | 'only_matching': True, | |
1151 | }, | |
1152 | { | |
1153 | 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ', | |
1154 | 'only_matching': True, | |
1155 | }, | |
2eb88d95 PH |
1156 | ] |
1157 | ||
e0df6211 PH |
1158 | def __init__(self, *args, **kwargs): |
1159 | super(YoutubeIE, self).__init__(*args, **kwargs) | |
83799698 | 1160 | self._player_cache = {} |
e0df6211 | 1161 | |
c5e8d7af PH |
1162 | def report_video_info_webpage_download(self, video_id): |
1163 | """Report attempt to download video info webpage.""" | |
69ea8ca4 | 1164 | self.to_screen('%s: Downloading video info webpage' % video_id) |
c5e8d7af | 1165 | |
c5e8d7af PH |
1166 | def report_information_extraction(self, video_id): |
1167 | """Report attempt to extract video information.""" | |
69ea8ca4 | 1168 | self.to_screen('%s: Extracting video information' % video_id) |
c5e8d7af PH |
1169 | |
1170 | def report_unavailable_format(self, video_id, format): | |
1171 | """Report extracted video URL.""" | |
69ea8ca4 | 1172 | self.to_screen('%s: Format %s not available' % (video_id, format)) |
c5e8d7af PH |
1173 | |
1174 | def report_rtmp_download(self): | |
1175 | """Indicate the download will use the RTMP protocol.""" | |
69ea8ca4 | 1176 | self.to_screen('RTMP download detected') |
c5e8d7af | 1177 | |
60064c53 PH |
1178 | def _signature_cache_id(self, example_sig): |
1179 | """ Return a string representation of a signature """ | |
78caa52a | 1180 | return '.'.join(compat_str(len(part)) for part in example_sig.split('.')) |
60064c53 | 1181 | |
e40c758c S |
1182 | @classmethod |
1183 | def _extract_player_info(cls, player_url): | |
1184 | for player_re in cls._PLAYER_INFO_RE: | |
1185 | id_m = re.search(player_re, player_url) | |
1186 | if id_m: | |
1187 | break | |
1188 | else: | |
c081b35c | 1189 | raise ExtractorError('Cannot identify player %r' % player_url) |
e40c758c S |
1190 | return id_m.group('ext'), id_m.group('id') |
1191 | ||
1192 | def _extract_signature_function(self, video_id, player_url, example_sig): | |
1193 | player_type, player_id = self._extract_player_info(player_url) | |
e0df6211 | 1194 | |
c4417ddb | 1195 | # Read from filesystem cache |
60064c53 PH |
1196 | func_id = '%s_%s_%s' % ( |
1197 | player_type, player_id, self._signature_cache_id(example_sig)) | |
c4417ddb | 1198 | assert os.path.basename(func_id) == func_id |
a0e07d31 | 1199 | |
69ea8ca4 | 1200 | cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id) |
a0e07d31 | 1201 | if cache_spec is not None: |
78caa52a | 1202 | return lambda s: ''.join(s[i] for i in cache_spec) |
83799698 | 1203 | |
6d1a55a5 PH |
1204 | download_note = ( |
1205 | 'Downloading player %s' % player_url | |
1206 | if self._downloader.params.get('verbose') else | |
1207 | 'Downloading %s player %s' % (player_type, player_id) | |
1208 | ) | |
e0df6211 PH |
1209 | if player_type == 'js': |
1210 | code = self._download_webpage( | |
1211 | player_url, video_id, | |
6d1a55a5 | 1212 | note=download_note, |
69ea8ca4 | 1213 | errnote='Download of %s failed' % player_url) |
83799698 | 1214 | res = self._parse_sig_js(code) |
c4417ddb | 1215 | elif player_type == 'swf': |
e0df6211 PH |
1216 | urlh = self._request_webpage( |
1217 | player_url, video_id, | |
6d1a55a5 | 1218 | note=download_note, |
69ea8ca4 | 1219 | errnote='Download of %s failed' % player_url) |
e0df6211 | 1220 | code = urlh.read() |
83799698 | 1221 | res = self._parse_sig_swf(code) |
e0df6211 PH |
1222 | else: |
1223 | assert False, 'Invalid player type %r' % player_type | |
1224 | ||
785521bf PH |
1225 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
1226 | cache_res = res(test_string) | |
1227 | cache_spec = [ord(c) for c in cache_res] | |
83799698 | 1228 | |
69ea8ca4 | 1229 | self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec) |
83799698 PH |
1230 | return res |
1231 | ||
60064c53 | 1232 | def _print_sig_code(self, func, example_sig): |
edf3e38e PH |
1233 | def gen_sig_code(idxs): |
1234 | def _genslice(start, end, step): | |
78caa52a | 1235 | starts = '' if start == 0 else str(start) |
8bcc8756 | 1236 | ends = (':%d' % (end + step)) if end + step >= 0 else ':' |
69ea8ca4 | 1237 | steps = '' if step == 1 else (':%d' % step) |
78caa52a | 1238 | return 's[%s%s%s]' % (starts, ends, steps) |
edf3e38e PH |
1239 | |
1240 | step = None | |
7af808a5 PH |
1241 | # Quelch pyflakes warnings - start will be set when step is set |
1242 | start = '(Never used)' | |
edf3e38e PH |
1243 | for i, prev in zip(idxs[1:], idxs[:-1]): |
1244 | if step is not None: | |
1245 | if i - prev == step: | |
1246 | continue | |
1247 | yield _genslice(start, prev, step) | |
1248 | step = None | |
1249 | continue | |
1250 | if i - prev in [-1, 1]: | |
1251 | step = i - prev | |
1252 | start = prev | |
1253 | continue | |
1254 | else: | |
78caa52a | 1255 | yield 's[%d]' % prev |
edf3e38e | 1256 | if step is None: |
78caa52a | 1257 | yield 's[%d]' % i |
edf3e38e PH |
1258 | else: |
1259 | yield _genslice(start, i, step) | |
1260 | ||
78caa52a | 1261 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
c705320f | 1262 | cache_res = func(test_string) |
edf3e38e | 1263 | cache_spec = [ord(c) for c in cache_res] |
78caa52a | 1264 | expr_code = ' + '.join(gen_sig_code(cache_spec)) |
60064c53 PH |
1265 | signature_id_tuple = '(%s)' % ( |
1266 | ', '.join(compat_str(len(p)) for p in example_sig.split('.'))) | |
69ea8ca4 | 1267 | code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n' |
78caa52a | 1268 | ' return %s\n') % (signature_id_tuple, expr_code) |
69ea8ca4 | 1269 | self.to_screen('Extracted signature function:\n' + code) |
edf3e38e | 1270 | |
e0df6211 PH |
1271 | def _parse_sig_js(self, jscode): |
1272 | funcname = self._search_regex( | |
abefc03f S |
1273 | (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', |
1274 | r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
e450f6cb | 1275 | r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)', |
31ce6e99 | 1276 | r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)', |
abefc03f S |
1277 | # Obsolete patterns |
1278 | r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
9a47fa35 | 1279 | r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(', |
abefc03f S |
1280 | r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(', |
1281 | r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1282 | r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1283 | r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1284 | r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1285 | r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('), | |
3c90cc8b | 1286 | jscode, 'Initial JS player signature function name', group='sig') |
2b25cb5d PH |
1287 | |
1288 | jsi = JSInterpreter(jscode) | |
1289 | initial_function = jsi.extract_function(funcname) | |
e0df6211 PH |
1290 | return lambda s: initial_function([s]) |
1291 | ||
1292 | def _parse_sig_swf(self, file_contents): | |
54256267 | 1293 | swfi = SWFInterpreter(file_contents) |
78caa52a | 1294 | TARGET_CLASSNAME = 'SignatureDecipher' |
54256267 | 1295 | searched_class = swfi.extract_class(TARGET_CLASSNAME) |
78caa52a | 1296 | initial_function = swfi.extract_function(searched_class, 'decipher') |
e0df6211 PH |
1297 | return lambda s: initial_function([s]) |
1298 | ||
83799698 | 1299 | def _decrypt_signature(self, s, video_id, player_url, age_gate=False): |
257a2501 | 1300 | """Turn the encrypted s field into a working signature""" |
6b37f0be | 1301 | |
c8bf86d5 | 1302 | if player_url is None: |
69ea8ca4 | 1303 | raise ExtractorError('Cannot decrypt signature without player_url') |
920de7a2 | 1304 | |
69ea8ca4 | 1305 | if player_url.startswith('//'): |
78caa52a | 1306 | player_url = 'https:' + player_url |
3c90cc8b S |
1307 | elif not re.match(r'https?://', player_url): |
1308 | player_url = compat_urlparse.urljoin( | |
1309 | 'https://www.youtube.com', player_url) | |
c8bf86d5 | 1310 | try: |
62af3a0e | 1311 | player_id = (player_url, self._signature_cache_id(s)) |
c8bf86d5 PH |
1312 | if player_id not in self._player_cache: |
1313 | func = self._extract_signature_function( | |
60064c53 | 1314 | video_id, player_url, s |
c8bf86d5 PH |
1315 | ) |
1316 | self._player_cache[player_id] = func | |
1317 | func = self._player_cache[player_id] | |
1318 | if self._downloader.params.get('youtube_print_sig_code'): | |
60064c53 | 1319 | self._print_sig_code(func, s) |
c8bf86d5 PH |
1320 | return func(s) |
1321 | except Exception as e: | |
1322 | tb = traceback.format_exc() | |
1323 | raise ExtractorError( | |
78caa52a | 1324 | 'Signature extraction failed: ' + tb, cause=e) |
e0df6211 | 1325 | |
f96f5dda | 1326 | def _get_subtitles(self, video_id, webpage, has_live_chat_replay): |
de7f3446 | 1327 | try: |
60e47a26 | 1328 | subs_doc = self._download_xml( |
38c2e5b8 | 1329 | 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id, |
7fad1c63 JMF |
1330 | video_id, note=False) |
1331 | except ExtractorError as err: | |
9b9c5355 | 1332 | self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err)) |
de7f3446 | 1333 | return {} |
de7f3446 JMF |
1334 | |
1335 | sub_lang_list = {} | |
60e47a26 JMF |
1336 | for track in subs_doc.findall('track'): |
1337 | lang = track.attrib['lang_code'] | |
7e660ac1 LD |
1338 | if lang in sub_lang_list: |
1339 | continue | |
360e1ca5 | 1340 | sub_formats = [] |
23d17e4b | 1341 | for ext in self._SUBTITLE_FORMATS: |
15707c7e | 1342 | params = compat_urllib_parse_urlencode({ |
360e1ca5 JMF |
1343 | 'lang': lang, |
1344 | 'v': video_id, | |
1345 | 'fmt': ext, | |
1346 | 'name': track.attrib['name'].encode('utf-8'), | |
1347 | }) | |
1348 | sub_formats.append({ | |
1349 | 'url': 'https://www.youtube.com/api/timedtext?' + params, | |
1350 | 'ext': ext, | |
1351 | }) | |
1352 | sub_lang_list[lang] = sub_formats | |
9f448fcb | 1353 | if has_live_chat_replay: |
321bf820 | 1354 | sub_lang_list['live_chat'] = [ |
1355 | { | |
1356 | 'video_id': video_id, | |
1357 | 'ext': 'json', | |
1358 | 'protocol': 'youtube_live_chat_replay', | |
1359 | }, | |
9f448fcb | 1360 | ] |
de7f3446 | 1361 | if not sub_lang_list: |
69ea8ca4 | 1362 | self._downloader.report_warning('video doesn\'t have subtitles') |
de7f3446 JMF |
1363 | return {} |
1364 | return sub_lang_list | |
1365 | ||
a72778d3 S |
1366 | def _get_ytplayer_config(self, video_id, webpage): |
1367 | patterns = ( | |
526b3b07 S |
1368 | # User data may contain arbitrary character sequences that may affect |
1369 | # JSON extraction with regex, e.g. when '};' is contained the second | |
1370 | # regex won't capture the whole JSON. Yet working around by trying more | |
1371 | # concrete regex first keeping in mind proper quoted string handling | |
1372 | # to be implemented in future that will replace this workaround (see | |
067aa17e S |
1373 | # https://github.com/ytdl-org/youtube-dl/issues/7468, |
1374 | # https://github.com/ytdl-org/youtube-dl/pull/7599) | |
a72778d3 S |
1375 | r';ytplayer\.config\s*=\s*({.+?});ytplayer', |
1376 | r';ytplayer\.config\s*=\s*({.+?});', | |
1377 | ) | |
1378 | config = self._search_regex( | |
1379 | patterns, webpage, 'ytplayer.config', default=None) | |
1380 | if config: | |
1381 | return self._parse_json( | |
1382 | uppercase_escape(config), video_id, fatal=False) | |
0e49d9a6 | 1383 | |
29f7c58a | 1384 | def _get_automatic_captions(self, video_id, player_response, player_config): |
de7f3446 JMF |
1385 | """We need the webpage for getting the captions url, pass it as an |
1386 | argument to speed up the process.""" | |
69ea8ca4 | 1387 | self.to_screen('%s: Looking for automatic captions' % video_id) |
78caa52a | 1388 | err_msg = 'Couldn\'t find automatic captions for %s' % video_id |
29f7c58a | 1389 | if not (player_response or player_config): |
de7f3446 JMF |
1390 | self._downloader.report_warning(err_msg) |
1391 | return {} | |
de7f3446 | 1392 | try: |
29f7c58a | 1393 | args = player_config.get('args') if player_config else {} |
8bdd16b4 | 1394 | caption_url = args.get('ttsurl') |
1395 | if caption_url: | |
b78b292f S |
1396 | timestamp = args['timestamp'] |
1397 | # We get the available subtitles | |
15707c7e | 1398 | list_params = compat_urllib_parse_urlencode({ |
b78b292f S |
1399 | 'type': 'list', |
1400 | 'tlangs': 1, | |
1401 | 'asrs': 1, | |
1402 | }) | |
1403 | list_url = caption_url + '&' + list_params | |
1404 | caption_list = self._download_xml(list_url, video_id) | |
1405 | original_lang_node = caption_list.find('track') | |
1406 | if original_lang_node is None: | |
1407 | self._downloader.report_warning('Video doesn\'t have automatic captions') | |
1408 | return {} | |
1409 | original_lang = original_lang_node.attrib['lang_code'] | |
1410 | caption_kind = original_lang_node.attrib.get('kind', '') | |
1411 | ||
1412 | sub_lang_list = {} | |
1413 | for lang_node in caption_list.findall('target'): | |
1414 | sub_lang = lang_node.attrib['lang_code'] | |
1415 | sub_formats = [] | |
1416 | for ext in self._SUBTITLE_FORMATS: | |
15707c7e | 1417 | params = compat_urllib_parse_urlencode({ |
b78b292f S |
1418 | 'lang': original_lang, |
1419 | 'tlang': sub_lang, | |
1420 | 'fmt': ext, | |
1421 | 'ts': timestamp, | |
1422 | 'kind': caption_kind, | |
1423 | }) | |
1424 | sub_formats.append({ | |
1425 | 'url': caption_url + '&' + params, | |
1426 | 'ext': ext, | |
1427 | }) | |
1428 | sub_lang_list[sub_lang] = sub_formats | |
1429 | return sub_lang_list | |
1430 | ||
ddbb4c5c S |
1431 | def make_captions(sub_url, sub_langs): |
1432 | parsed_sub_url = compat_urllib_parse_urlparse(sub_url) | |
1433 | caption_qs = compat_parse_qs(parsed_sub_url.query) | |
1434 | captions = {} | |
1435 | for sub_lang in sub_langs: | |
1436 | sub_formats = [] | |
1437 | for ext in self._SUBTITLE_FORMATS: | |
1438 | caption_qs.update({ | |
1439 | 'tlang': [sub_lang], | |
1440 | 'fmt': [ext], | |
1441 | }) | |
1442 | sub_url = compat_urlparse.urlunparse(parsed_sub_url._replace( | |
1443 | query=compat_urllib_parse_urlencode(caption_qs, True))) | |
1444 | sub_formats.append({ | |
1445 | 'url': sub_url, | |
1446 | 'ext': ext, | |
1447 | }) | |
1448 | captions[sub_lang] = sub_formats | |
1449 | return captions | |
1450 | ||
1451 | # New captions format as of 22.06.2017 | |
29f7c58a | 1452 | if player_response: |
1453 | renderer = player_response['captions']['playerCaptionsTracklistRenderer'] | |
1454 | base_url = renderer['captionTracks'][0]['baseUrl'] | |
1455 | sub_lang_list = [] | |
1456 | for lang in renderer['translationLanguages']: | |
1457 | lang_code = lang.get('languageCode') | |
1458 | if lang_code: | |
1459 | sub_lang_list.append(lang_code) | |
1460 | return make_captions(base_url, sub_lang_list) | |
59c5fa91 | 1461 | |
8bdd16b4 | 1462 | # Some videos don't provide ttsurl but rather caption_tracks and |
1463 | # caption_translation_languages (e.g. 20LmZk1hakA) | |
1464 | # Does not used anymore as of 22.06.2017 | |
1465 | caption_tracks = args['caption_tracks'] | |
1466 | caption_translation_languages = args['caption_translation_languages'] | |
1467 | caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0] | |
1468 | sub_lang_list = [] | |
1469 | for lang in caption_translation_languages.split(','): | |
1470 | lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang)) | |
1471 | sub_lang = lang_qs.get('lc', [None])[0] | |
1472 | if sub_lang: | |
1473 | sub_lang_list.append(sub_lang) | |
1474 | return make_captions(caption_url, sub_lang_list) | |
de7f3446 JMF |
1475 | # An extractor error can be raise by the download process if there are |
1476 | # no automatic captions but there are subtitles | |
ddbb4c5c | 1477 | except (KeyError, IndexError, ExtractorError): |
de7f3446 JMF |
1478 | self._downloader.report_warning(err_msg) |
1479 | return {} | |
1480 | ||
21c340b8 S |
1481 | def _mark_watched(self, video_id, video_info, player_response): |
1482 | playback_url = url_or_none(try_get( | |
1483 | player_response, | |
1484 | lambda x: x['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get( | |
1485 | video_info, lambda x: x['videostats_playback_base_url'][0])) | |
d77ab8e2 S |
1486 | if not playback_url: |
1487 | return | |
1488 | parsed_playback_url = compat_urlparse.urlparse(playback_url) | |
1489 | qs = compat_urlparse.parse_qs(parsed_playback_url.query) | |
1490 | ||
1491 | # cpn generation algorithm is reverse engineered from base.js. | |
1492 | # In fact it works even with dummy cpn. | |
1493 | CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_' | |
1494 | cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))) | |
1495 | ||
1496 | qs.update({ | |
1497 | 'ver': ['2'], | |
1498 | 'cpn': [cpn], | |
1499 | }) | |
1500 | playback_url = compat_urlparse.urlunparse( | |
15707c7e | 1501 | parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True))) |
d77ab8e2 S |
1502 | |
1503 | self._download_webpage( | |
1504 | playback_url, video_id, 'Marking watched', | |
1505 | 'Unable to mark watched', fatal=False) | |
1506 | ||
66c9fa36 S |
1507 | @staticmethod |
1508 | def _extract_urls(webpage): | |
1509 | # Embedded YouTube player | |
1510 | entries = [ | |
1511 | unescapeHTML(mobj.group('url')) | |
1512 | for mobj in re.finditer(r'''(?x) | |
1513 | (?: | |
1514 | <iframe[^>]+?src=| | |
1515 | data-video-url=| | |
1516 | <embed[^>]+?src=| | |
1517 | embedSWF\(?:\s*| | |
1518 | <object[^>]+data=| | |
1519 | new\s+SWFObject\( | |
1520 | ) | |
1521 | (["\']) | |
1522 | (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/ | |
f2332f18 | 1523 | (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?) |
66c9fa36 S |
1524 | \1''', webpage)] |
1525 | ||
1526 | # lazyYT YouTube embed | |
1527 | entries.extend(list(map( | |
1528 | unescapeHTML, | |
1529 | re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)))) | |
1530 | ||
1531 | # Wordpress "YouTube Video Importer" plugin | |
1532 | matches = re.findall(r'''(?x)<div[^>]+ | |
1533 | class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+ | |
1534 | data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage) | |
1535 | entries.extend(m[-1] for m in matches) | |
1536 | ||
1537 | return entries | |
1538 | ||
1539 | @staticmethod | |
1540 | def _extract_url(webpage): | |
1541 | urls = YoutubeIE._extract_urls(webpage) | |
1542 | return urls[0] if urls else None | |
1543 | ||
97665381 PH |
1544 | @classmethod |
1545 | def extract_id(cls, url): | |
1546 | mobj = re.match(cls._VALID_URL, url, re.VERBOSE) | |
c5e8d7af | 1547 | if mobj is None: |
69ea8ca4 | 1548 | raise ExtractorError('Invalid URL: %s' % url) |
c5e8d7af PH |
1549 | video_id = mobj.group(2) |
1550 | return video_id | |
1551 | ||
84213ea8 S |
1552 | def _extract_chapters_from_json(self, webpage, video_id, duration): |
1553 | if not webpage: | |
1554 | return | |
8bdd16b4 | 1555 | data = self._extract_yt_initial_data(video_id, webpage) |
1556 | if not data or not isinstance(data, dict): | |
84213ea8 S |
1557 | return |
1558 | chapters_list = try_get( | |
8bdd16b4 | 1559 | data, |
84213ea8 S |
1560 | lambda x: x['playerOverlays'] |
1561 | ['playerOverlayRenderer'] | |
1562 | ['decoratedPlayerBarRenderer'] | |
1563 | ['decoratedPlayerBarRenderer'] | |
1564 | ['playerBar'] | |
1565 | ['chapteredPlayerBarRenderer'] | |
1566 | ['chapters'], | |
1567 | list) | |
1568 | if not chapters_list: | |
1569 | return | |
1570 | ||
1571 | def chapter_time(chapter): | |
1572 | return float_or_none( | |
1573 | try_get( | |
1574 | chapter, | |
1575 | lambda x: x['chapterRenderer']['timeRangeStartMillis'], | |
1576 | int), | |
1577 | scale=1000) | |
1578 | chapters = [] | |
1579 | for next_num, chapter in enumerate(chapters_list, start=1): | |
1580 | start_time = chapter_time(chapter) | |
1581 | if start_time is None: | |
1582 | continue | |
1583 | end_time = (chapter_time(chapters_list[next_num]) | |
1584 | if next_num < len(chapters_list) else duration) | |
1585 | if end_time is None: | |
1586 | continue | |
1587 | title = try_get( | |
1588 | chapter, lambda x: x['chapterRenderer']['title']['simpleText'], | |
1589 | compat_str) | |
1590 | chapters.append({ | |
1591 | 'start_time': start_time, | |
1592 | 'end_time': end_time, | |
1593 | 'title': title, | |
1594 | }) | |
1595 | return chapters | |
1596 | ||
9cafc3fd | 1597 | @staticmethod |
84213ea8 | 1598 | def _extract_chapters_from_description(description, duration): |
9cafc3fd S |
1599 | if not description: |
1600 | return None | |
1601 | chapter_lines = re.findall( | |
1602 | r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<br\s*/>)', | |
1603 | description) | |
1604 | if not chapter_lines: | |
1605 | return None | |
1606 | chapters = [] | |
1607 | for next_num, (chapter_line, time_point) in enumerate( | |
1608 | chapter_lines, start=1): | |
1609 | start_time = parse_duration(time_point) | |
1610 | if start_time is None: | |
1611 | continue | |
39d4c1be S |
1612 | if start_time > duration: |
1613 | break | |
9cafc3fd S |
1614 | end_time = (duration if next_num == len(chapter_lines) |
1615 | else parse_duration(chapter_lines[next_num][1])) | |
1616 | if end_time is None: | |
1617 | continue | |
39d4c1be S |
1618 | if end_time > duration: |
1619 | end_time = duration | |
1620 | if start_time > end_time: | |
1621 | break | |
9cafc3fd S |
1622 | chapter_title = re.sub( |
1623 | r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-') | |
1624 | chapter_title = re.sub(r'\s+', ' ', chapter_title) | |
1625 | chapters.append({ | |
1626 | 'start_time': start_time, | |
1627 | 'end_time': end_time, | |
1628 | 'title': chapter_title, | |
1629 | }) | |
1630 | return chapters | |
1631 | ||
84213ea8 S |
1632 | def _extract_chapters(self, webpage, description, video_id, duration): |
1633 | return (self._extract_chapters_from_json(webpage, video_id, duration) | |
1634 | or self._extract_chapters_from_description(description, duration)) | |
1635 | ||
c5e8d7af | 1636 | def _real_extract(self, url): |
cf7e015f S |
1637 | url, smuggled_data = unsmuggle_url(url, {}) |
1638 | ||
7e8c0af0 | 1639 | proto = ( |
78caa52a PH |
1640 | 'http' if self._downloader.params.get('prefer_insecure', False) |
1641 | else 'https') | |
7e8c0af0 | 1642 | |
7c80519c | 1643 | start_time = None |
297a564b | 1644 | end_time = None |
7c80519c JMF |
1645 | parsed_url = compat_urllib_parse_urlparse(url) |
1646 | for component in [parsed_url.fragment, parsed_url.query]: | |
1647 | query = compat_parse_qs(component) | |
297a564b | 1648 | if start_time is None and 't' in query: |
7c80519c | 1649 | start_time = parse_duration(query['t'][0]) |
2929fa0e JMF |
1650 | if start_time is None and 'start' in query: |
1651 | start_time = parse_duration(query['start'][0]) | |
297a564b JMF |
1652 | if end_time is None and 'end' in query: |
1653 | end_time = parse_duration(query['end'][0]) | |
7c80519c | 1654 | |
c5e8d7af PH |
1655 | # Extract original video URL from URL with redirection, like age verification, using next_url parameter |
1656 | mobj = re.search(self._NEXT_URL_RE, url) | |
1657 | if mobj: | |
7fd002c0 | 1658 | url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/') |
97665381 | 1659 | video_id = self.extract_id(url) |
c5e8d7af PH |
1660 | |
1661 | # Get video webpage | |
aa79ac0c | 1662 | url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id |
011e75e6 S |
1663 | video_webpage, urlh = self._download_webpage_handle(url, video_id) |
1664 | ||
1665 | qs = compat_parse_qs(compat_urllib_parse_urlparse(urlh.geturl()).query) | |
1666 | video_id = qs.get('v', [None])[0] or video_id | |
c5e8d7af PH |
1667 | |
1668 | # Attempt to extract SWF player URL | |
e0df6211 | 1669 | mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) |
c5e8d7af PH |
1670 | if mobj is not None: |
1671 | player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) | |
1672 | else: | |
1673 | player_url = None | |
1674 | ||
d8d24a92 S |
1675 | dash_mpds = [] |
1676 | ||
1677 | def add_dash_mpd(video_info): | |
1678 | dash_mpd = video_info.get('dashmpd') | |
1679 | if dash_mpd and dash_mpd[0] not in dash_mpds: | |
1680 | dash_mpds.append(dash_mpd[0]) | |
1681 | ||
561b456e S |
1682 | def add_dash_mpd_pr(pl_response): |
1683 | dash_mpd = url_or_none(try_get( | |
1684 | pl_response, lambda x: x['streamingData']['dashManifestUrl'], | |
1685 | compat_str)) | |
1686 | if dash_mpd and dash_mpd not in dash_mpds: | |
1687 | dash_mpds.append(dash_mpd) | |
1688 | ||
c7121fa7 S |
1689 | is_live = None |
1690 | view_count = None | |
1691 | ||
1692 | def extract_view_count(v_info): | |
1693 | return int_or_none(try_get(v_info, lambda x: x['view_count'][0])) | |
1694 | ||
c2d125d9 S |
1695 | def extract_player_response(player_response, video_id): |
1696 | pl_response = str_or_none(player_response) | |
1697 | if not pl_response: | |
1698 | return | |
1699 | pl_response = self._parse_json(pl_response, video_id, fatal=False) | |
1700 | if isinstance(pl_response, dict): | |
1701 | add_dash_mpd_pr(pl_response) | |
1702 | return pl_response | |
1703 | ||
fb2c9277 U |
1704 | def extract_embedded_config(embed_webpage, video_id): |
1705 | embedded_config = self._search_regex( | |
1706 | r'setConfig\(({.*})\);', | |
1707 | embed_webpage, 'ytInitialData', default=None) | |
1708 | if embedded_config: | |
1709 | return embedded_config | |
1710 | ||
62d80ba1 | 1711 | video_info = {} |
dbdaaa23 | 1712 | player_response = {} |
62d80ba1 | 1713 | ytplayer_config = None |
1714 | embed_webpage = None | |
dbdaaa23 | 1715 | |
c5e8d7af | 1716 | # Get video info |
39e7107d U |
1717 | if (self._og_search_property('restrictions:age', video_webpage, default=None) == '18+' |
1718 | or re.search(r'player-age-gate-content">', video_webpage) is not None): | |
9d9314cb | 1719 | cookie_keys = self._get_cookies('https://www.youtube.com').keys() |
c108eb73 JMF |
1720 | age_gate = True |
1721 | # We simulate the access to the video from www.youtube.com/v/{video_id} | |
1722 | # this can be viewed without login into Youtube | |
beb95e77 CL |
1723 | url = proto + '://www.youtube.com/embed/%s' % video_id |
1724 | embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage') | |
fb2c9277 U |
1725 | ext = extract_embedded_config(embed_webpage, video_id) |
1726 | # playabilityStatus = re.search(r'{\\\"status\\\":\\\"(?P<playabilityStatus>[^\"]+)\\\"', ext) | |
1727 | playable_in_embed = re.search(r'{\\\"playableInEmbed\\\":(?P<playableinEmbed>[^\,]+)', ext) | |
1728 | if not playable_in_embed: | |
1729 | self.to_screen('Could not determine whether playabale in embed for video %s' % video_id) | |
1730 | playable_in_embed = '' | |
1731 | else: | |
1732 | playable_in_embed = playable_in_embed.group('playableinEmbed') | |
1733 | # check if video is only playable on youtube in other words not playable in embed - if so it requires auth (cookies) | |
1734 | # if re.search(r'player-unavailable">', embed_webpage) is not None: | |
1735 | if playable_in_embed == 'false': | |
c73baf23 U |
1736 | ''' |
1737 | # TODO apply this patch when Support for Python 2.6(!) and above drops | |
9d9314cb | 1738 | if ({'VISITOR_INFO1_LIVE', 'HSID', 'SSID', 'SID'} <= cookie_keys |
4bb9c880 | 1739 | or {'VISITOR_INFO1_LIVE', '__Secure-3PSID', 'LOGIN_INFO'} <= cookie_keys): |
c73baf23 U |
1740 | ''' |
1741 | if (set(('VISITOR_INFO1_LIVE', 'HSID', 'SSID', 'SID')) <= set(cookie_keys) | |
1742 | or set(('VISITOR_INFO1_LIVE', '__Secure-3PSID', 'LOGIN_INFO')) <= set(cookie_keys)): | |
4bb9c880 U |
1743 | age_gate = False |
1744 | # Try looking directly into the video webpage | |
1745 | ytplayer_config = self._get_ytplayer_config(video_id, video_webpage) | |
1746 | if ytplayer_config: | |
59c5fa91 PO |
1747 | args = ytplayer_config.get("args") |
1748 | if args is not None: | |
1749 | if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'): | |
1750 | # Convert to the same format returned by compat_parse_qs | |
1751 | video_info = dict((k, [v]) for k, v in args.items()) | |
1752 | add_dash_mpd(video_info) | |
1753 | # Rental video is not rented but preview is available (e.g. | |
1754 | # https://www.youtube.com/watch?v=yYr8q0y5Jfg, | |
1755 | # https://github.com/ytdl-org/youtube-dl/issues/10532) | |
1756 | if not video_info and args.get('ypc_vid'): | |
1757 | return self.url_result( | |
1758 | args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid']) | |
1759 | if args.get('livestream') == '1' or args.get('live_playback') == 1: | |
1760 | is_live = True | |
1761 | if not player_response: | |
1762 | player_response = extract_player_response(args.get('player_response'), video_id) | |
1763 | elif not player_response: | |
1764 | player_response = ytplayer_config | |
4bb9c880 U |
1765 | if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True): |
1766 | add_dash_mpd_pr(player_response) | |
9d9314cb U |
1767 | else: |
1768 | raise ExtractorError('Video is age restricted and only playable on Youtube. Requires cookies!', expected=True) | |
1769 | else: | |
1770 | data = compat_urllib_parse_urlencode({ | |
1771 | 'video_id': video_id, | |
1772 | 'eurl': 'https://youtube.googleapis.com/v/' + video_id, | |
1773 | 'sts': self._search_regex( | |
1774 | r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''), | |
1775 | }) | |
1776 | video_info_url = proto + '://www.youtube.com/get_video_info?' + data | |
1777 | try: | |
1778 | video_info_webpage = self._download_webpage( | |
1779 | video_info_url, video_id, | |
1780 | note='Refetching age-gated info webpage', | |
1781 | errnote='unable to download video info webpage') | |
1782 | except ExtractorError: | |
1783 | video_info_webpage = None | |
1784 | if video_info_webpage: | |
1785 | video_info = compat_parse_qs(video_info_webpage) | |
1786 | pl_response = video_info.get('player_response', [None])[0] | |
1787 | player_response = extract_player_response(pl_response, video_id) | |
1788 | add_dash_mpd(video_info) | |
1789 | view_count = extract_view_count(video_info) | |
c108eb73 JMF |
1790 | else: |
1791 | age_gate = False | |
d8d24a92 | 1792 | # Try looking directly into the video webpage |
a72778d3 | 1793 | ytplayer_config = self._get_ytplayer_config(video_id, video_webpage) |
8bdd16b4 | 1794 | if ytplayer_config: |
1795 | args = ytplayer_config.get('args', {}) | |
4c76aa06 | 1796 | if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'): |
d8d24a92 S |
1797 | # Convert to the same format returned by compat_parse_qs |
1798 | video_info = dict((k, [v]) for k, v in args.items()) | |
1799 | add_dash_mpd(video_info) | |
6496ccb4 S |
1800 | # Rental video is not rented but preview is available (e.g. |
1801 | # https://www.youtube.com/watch?v=yYr8q0y5Jfg, | |
067aa17e | 1802 | # https://github.com/ytdl-org/youtube-dl/issues/10532) |
6496ccb4 S |
1803 | if not video_info and args.get('ypc_vid'): |
1804 | return self.url_result( | |
1805 | args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid']) | |
2fe1ff85 JMF |
1806 | if args.get('livestream') == '1' or args.get('live_playback') == 1: |
1807 | is_live = True | |
dbdaaa23 | 1808 | if not player_response: |
c2d125d9 | 1809 | player_response = extract_player_response(args.get('player_response'), video_id) |
0a3cf9ad | 1810 | if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True): |
561b456e | 1811 | add_dash_mpd_pr(player_response) |
bbb7c3f7 | 1812 | |
8bdd16b4 | 1813 | if not video_info and not player_response: |
1814 | player_response = extract_player_response( | |
1815 | self._search_regex( | |
29f7c58a | 1816 | (r'%s\s*%s' % (self._YT_INITIAL_PLAYER_RESPONSE_RE, self._YT_INITIAL_BOUNDARY_RE), |
1817 | self._YT_INITIAL_PLAYER_RESPONSE_RE), video_webpage, | |
8bdd16b4 | 1818 | 'initial player response', default='{}'), |
1819 | video_id) | |
1820 | ||
bbb7c3f7 | 1821 | def extract_unavailable_message(): |
0add33ab S |
1822 | messages = [] |
1823 | for tag, kind in (('h1', 'message'), ('div', 'submessage')): | |
1824 | msg = self._html_search_regex( | |
1825 | r'(?s)<{tag}[^>]+id=["\']unavailable-{kind}["\'][^>]*>(.+?)</{tag}>'.format(tag=tag, kind=kind), | |
1826 | video_webpage, 'unavailable %s' % kind, default=None) | |
1827 | if msg: | |
1828 | messages.append(msg) | |
1829 | if messages: | |
1830 | return '\n'.join(messages) | |
bbb7c3f7 | 1831 | |
f93abcf1 | 1832 | if not video_info and not player_response: |
15be3eb5 RA |
1833 | unavailable_message = extract_unavailable_message() |
1834 | if not unavailable_message: | |
1835 | unavailable_message = 'Unable to extract video data' | |
1836 | raise ExtractorError( | |
1837 | 'YouTube said: %s' % unavailable_message, expected=True, video_id=video_id) | |
1838 | ||
f93abcf1 S |
1839 | if not isinstance(video_info, dict): |
1840 | video_info = {} | |
1841 | ||
5ac23244 | 1842 | playable_in_embed = try_get( |
1843 | player_response, lambda x: x['playabilityStatus']['playableInEmbed']) | |
1844 | ||
dbdaaa23 S |
1845 | video_details = try_get( |
1846 | player_response, lambda x: x['videoDetails'], dict) or {} | |
1847 | ||
37357d21 S |
1848 | microformat = try_get( |
1849 | player_response, lambda x: x['microformat']['playerMicroformatRenderer'], dict) or {} | |
1850 | ||
8dbf751a RA |
1851 | video_title = video_info.get('title', [None])[0] or video_details.get('title') |
1852 | if not video_title: | |
cf7e015f S |
1853 | self._downloader.report_warning('Unable to extract video title') |
1854 | video_title = '_' | |
1855 | ||
9cafc3fd | 1856 | description_original = video_description = get_element_by_id("eow-description", video_webpage) |
cf7e015f | 1857 | if video_description: |
fa4bc6e7 RA |
1858 | |
1859 | def replace_url(m): | |
1860 | redir_url = compat_urlparse.urljoin(url, m.group(1)) | |
1861 | parsed_redir_url = compat_urllib_parse_urlparse(redir_url) | |
1862 | if re.search(r'^(?:www\.)?(?:youtube(?:-nocookie)?\.com|youtu\.be)$', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect': | |
1863 | qs = compat_parse_qs(parsed_redir_url.query) | |
1864 | q = qs.get('q') | |
1865 | if q and q[0]: | |
1866 | return q[0] | |
1867 | return redir_url | |
1868 | ||
9cafc3fd | 1869 | description_original = video_description = re.sub(r'''(?x) |
cf7e015f | 1870 | <a\s+ |
25cb7a0e | 1871 | (?:[a-zA-Z-]+="[^"]*"\s+)*? |
23f13e97 | 1872 | (?:title|href)="([^"]+)"\s+ |
25cb7a0e | 1873 | (?:[a-zA-Z-]+="[^"]*"\s+)*? |
525cedb9 | 1874 | class="[^"]*"[^>]*> |
23f13e97 | 1875 | [^<]+\.{3}\s* |
cf7e015f | 1876 | </a> |
fa4bc6e7 | 1877 | ''', replace_url, video_description) |
cf7e015f S |
1878 | video_description = clean_html(video_description) |
1879 | else: | |
ea74e00b DP |
1880 | video_description = video_details.get('shortDescription') |
1881 | if video_description is None: | |
1882 | video_description = self._html_search_meta('description', video_webpage) | |
cf7e015f | 1883 | |
8fe10494 | 1884 | if not smuggled_data.get('force_singlefeed', False): |
5e1eddb9 | 1885 | if not self._downloader.params.get('noplaylist'): |
8fe10494 S |
1886 | multifeed_metadata_list = try_get( |
1887 | player_response, | |
1888 | lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'], | |
1889 | compat_str) or try_get( | |
1890 | video_info, lambda x: x['multifeed_metadata_list'][0], compat_str) | |
1891 | if multifeed_metadata_list: | |
1892 | entries = [] | |
1893 | feed_ids = [] | |
1894 | for feed in multifeed_metadata_list.split(','): | |
1895 | # Unquote should take place before split on comma (,) since textual | |
1896 | # fields may contain comma as well (see | |
067aa17e | 1897 | # https://github.com/ytdl-org/youtube-dl/issues/8536) |
8fe10494 | 1898 | feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed)) |
6b09401b S |
1899 | |
1900 | def feed_entry(name): | |
1901 | return try_get(feed_data, lambda x: x[name][0], compat_str) | |
1902 | ||
1903 | feed_id = feed_entry('id') | |
1904 | if not feed_id: | |
1905 | continue | |
1906 | feed_title = feed_entry('title') | |
1907 | title = video_title | |
1908 | if feed_title: | |
1909 | title += ' (%s)' % feed_title | |
8fe10494 S |
1910 | entries.append({ |
1911 | '_type': 'url_transparent', | |
1912 | 'ie_key': 'Youtube', | |
1913 | 'url': smuggle_url( | |
1914 | '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]), | |
1915 | {'force_singlefeed': True}), | |
6b09401b | 1916 | 'title': title, |
8fe10494 | 1917 | }) |
6b09401b | 1918 | feed_ids.append(feed_id) |
8fe10494 S |
1919 | self.to_screen( |
1920 | 'Downloading multifeed video (%s) - add --no-playlist to just download video %s' | |
1921 | % (', '.join(feed_ids), video_id)) | |
1922 | return self.playlist_result(entries, video_id, video_title, video_description) | |
1923 | else: | |
1924 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
cf7e015f | 1925 | |
c7121fa7 | 1926 | if view_count is None: |
1c9c8de2 | 1927 | view_count = extract_view_count(video_info) |
dbdaaa23 S |
1928 | if view_count is None and video_details: |
1929 | view_count = int_or_none(video_details.get('viewCount')) | |
7b16239a S |
1930 | if view_count is None and microformat: |
1931 | view_count = int_or_none(microformat.get('viewCount')) | |
1d699755 | 1932 | |
27019dbb | 1933 | if is_live is None: |
898238e9 | 1934 | is_live = bool_or_none(video_details.get('isLive')) |
27019dbb | 1935 | |
321bf820 | 1936 | has_live_chat_replay = False |
f0f76a33 | 1937 | if not is_live: |
82e3f6eb | 1938 | yt_initial_data = self._extract_yt_initial_data(video_id, video_webpage) |
321bf820 | 1939 | try: |
1940 | yt_initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation'] | |
1941 | has_live_chat_replay = True | |
f0f76a33 | 1942 | except (KeyError, IndexError, TypeError): |
321bf820 | 1943 | pass |
1944 | ||
c5e8d7af PH |
1945 | # Check for "rental" videos |
1946 | if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: | |
067aa17e | 1947 | raise ExtractorError('"rental" videos not supported. See https://github.com/ytdl-org/youtube-dl/issues/359 for more information.', expected=True) |
c5e8d7af | 1948 | |
c63ca0ee S |
1949 | def _extract_filesize(media_url): |
1950 | return int_or_none(self._search_regex( | |
1951 | r'\bclen[=/](\d+)', media_url, 'filesize', default=None)) | |
1952 | ||
bf1317d2 S |
1953 | streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list) or [] |
1954 | streaming_formats.extend(try_get(player_response, lambda x: x['streamingData']['adaptiveFormats'], list) or []) | |
1955 | ||
c5e8d7af PH |
1956 | if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): |
1957 | self.report_rtmp_download() | |
dd27fd17 PH |
1958 | formats = [{ |
1959 | 'format_id': '_rtmp', | |
1960 | 'protocol': 'rtmp', | |
1961 | 'url': video_info['conn'][0], | |
1962 | 'player_url': player_url, | |
1963 | }] | |
bf1317d2 | 1964 | elif not is_live and (streaming_formats or len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1): |
5f6a1245 | 1965 | encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0] |
00fe14fc | 1966 | if 'rtmpe%3Dyes' in encoded_url_map: |
067aa17e | 1967 | raise ExtractorError('rtmpe downloads are not supported, see https://github.com/ytdl-org/youtube-dl/issues/343 for more information.', expected=True) |
bf1317d2 | 1968 | formats = [] |
3318832e | 1969 | formats_spec = {} |
82156fdb | 1970 | fmt_list = video_info.get('fmt_list', [''])[0] |
1971 | if fmt_list: | |
1972 | for fmt in fmt_list.split(','): | |
1973 | spec = fmt.split('/') | |
3318832e | 1974 | if len(spec) > 1: |
1975 | width_height = spec[1].split('x') | |
1976 | if len(width_height) == 2: | |
1977 | formats_spec[spec[0]] = { | |
1978 | 'resolution': spec[1], | |
1979 | 'width': int_or_none(width_height[0]), | |
1980 | 'height': int_or_none(width_height[1]), | |
1981 | } | |
bf1317d2 S |
1982 | for fmt in streaming_formats: |
1983 | itag = str_or_none(fmt.get('itag')) | |
1984 | if not itag: | |
201e9eaa | 1985 | continue |
bf1317d2 S |
1986 | quality = fmt.get('quality') |
1987 | quality_label = fmt.get('qualityLabel') or quality | |
1988 | formats_spec[itag] = { | |
1989 | 'asr': int_or_none(fmt.get('audioSampleRate')), | |
1990 | 'filesize': int_or_none(fmt.get('contentLength')), | |
1991 | 'format_note': quality_label, | |
1992 | 'fps': int_or_none(fmt.get('fps')), | |
1993 | 'height': int_or_none(fmt.get('height')), | |
bf1317d2 S |
1994 | # bitrate for itag 43 is always 2147483647 |
1995 | 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None, | |
1996 | 'width': int_or_none(fmt.get('width')), | |
1997 | } | |
1998 | ||
1999 | for fmt in streaming_formats: | |
00eb865b | 2000 | if fmt.get('drmFamilies') or fmt.get('drm_families'): |
bf1317d2 S |
2001 | continue |
2002 | url = url_or_none(fmt.get('url')) | |
2003 | ||
2004 | if not url: | |
fa3db383 | 2005 | cipher = fmt.get('cipher') or fmt.get('signatureCipher') |
bf1317d2 S |
2006 | if not cipher: |
2007 | continue | |
2008 | url_data = compat_parse_qs(cipher) | |
2009 | url = url_or_none(try_get(url_data, lambda x: x['url'][0], compat_str)) | |
2010 | if not url: | |
2011 | continue | |
2012 | else: | |
2013 | cipher = None | |
2014 | url_data = compat_parse_qs(compat_urllib_parse_urlparse(url).query) | |
2015 | ||
2f483bc1 S |
2016 | stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0])) |
2017 | # Unsupported FORMAT_STREAM_TYPE_OTF | |
2018 | if stream_type == 3: | |
2019 | continue | |
6449cd80 | 2020 | |
bf1317d2 S |
2021 | format_id = fmt.get('itag') or url_data['itag'][0] |
2022 | if not format_id: | |
2023 | continue | |
2024 | format_id = compat_str(format_id) | |
a49eccdf | 2025 | |
bf1317d2 S |
2026 | if cipher: |
2027 | if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True): | |
8bdd16b4 | 2028 | ASSETS_RE = ( |
2029 | r'<script[^>]+\bsrc=("[^"]+")[^>]+\bname=["\']player_ias/base', | |
2030 | r'"jsUrl"\s*:\s*("[^"]+")', | |
2031 | r'"assets":.+?"js":\s*("[^"]+")') | |
bf1317d2 S |
2032 | jsplayer_url_json = self._search_regex( |
2033 | ASSETS_RE, | |
2034 | embed_webpage if age_gate else video_webpage, | |
2035 | 'JS player URL (1)', default=None) | |
2036 | if not jsplayer_url_json and not age_gate: | |
2037 | # We need the embed website after all | |
2038 | if embed_webpage is None: | |
2039 | embed_url = proto + '://www.youtube.com/embed/%s' % video_id | |
2040 | embed_webpage = self._download_webpage( | |
2041 | embed_url, video_id, 'Downloading embed webpage') | |
2042 | jsplayer_url_json = self._search_regex( | |
2043 | ASSETS_RE, embed_webpage, 'JS player URL') | |
2044 | ||
2045 | player_url = json.loads(jsplayer_url_json) | |
cf010131 | 2046 | if player_url is None: |
bf1317d2 S |
2047 | player_url_json = self._search_regex( |
2048 | r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")', | |
2049 | video_webpage, 'age gate player URL') | |
2050 | player_url = json.loads(player_url_json) | |
2051 | ||
2052 | if 'sig' in url_data: | |
2053 | url += '&signature=' + url_data['sig'][0] | |
2054 | elif 's' in url_data: | |
2055 | encrypted_sig = url_data['s'][0] | |
2056 | ||
2057 | if self._downloader.params.get('verbose'): | |
2058 | if player_url is None: | |
bf1317d2 | 2059 | player_desc = 'unknown' |
cf010131 | 2060 | else: |
e40c758c S |
2061 | player_type, player_version = self._extract_player_info(player_url) |
2062 | player_desc = '%s player %s' % ('flash' if player_type == 'swf' else 'html5', player_version) | |
bf1317d2 S |
2063 | parts_sizes = self._signature_cache_id(encrypted_sig) |
2064 | self.to_screen('{%s} signature length %s, %s' % | |
2065 | (format_id, parts_sizes, player_desc)) | |
2066 | ||
2067 | signature = self._decrypt_signature( | |
2068 | encrypted_sig, video_id, player_url, age_gate) | |
2069 | sp = try_get(url_data, lambda x: x['sp'][0], compat_str) or 'signature' | |
2070 | url += '&%s=%s' % (sp, signature) | |
201e9eaa PH |
2071 | if 'ratebypass' not in url: |
2072 | url += '&ratebypass=yes' | |
c9afb51c | 2073 | |
94278f72 YCH |
2074 | dct = { |
2075 | 'format_id': format_id, | |
2076 | 'url': url, | |
2077 | 'player_url': player_url, | |
2078 | } | |
2079 | if format_id in self._formats: | |
2080 | dct.update(self._formats[format_id]) | |
3318832e | 2081 | if format_id in formats_spec: |
2082 | dct.update(formats_spec[format_id]) | |
94278f72 | 2083 | |
aabc2be6 | 2084 | # Some itags are not included in DASH manifest thus corresponding formats will |
067aa17e | 2085 | # lack metadata (see https://github.com/ytdl-org/youtube-dl/pull/5993). |
aabc2be6 S |
2086 | # Trying to extract metadata from url_encoded_fmt_stream_map entry. |
2087 | mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0]) | |
2088 | width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None) | |
94278f72 | 2089 | |
bf1317d2 S |
2090 | if width is None: |
2091 | width = int_or_none(fmt.get('width')) | |
2092 | if height is None: | |
2093 | height = int_or_none(fmt.get('height')) | |
2094 | ||
c63ca0ee S |
2095 | filesize = int_or_none(url_data.get( |
2096 | 'clen', [None])[0]) or _extract_filesize(url) | |
2097 | ||
bf1317d2 S |
2098 | quality = url_data.get('quality', [None])[0] or fmt.get('quality') |
2099 | quality_label = url_data.get('quality_label', [None])[0] or fmt.get('qualityLabel') | |
2100 | ||
4878759f S |
2101 | tbr = (float_or_none(url_data.get('bitrate', [None])[0], 1000) |
2102 | or float_or_none(fmt.get('bitrate'), 1000)) if format_id != '43' else None | |
bf1317d2 | 2103 | fps = int_or_none(url_data.get('fps', [None])[0]) or int_or_none(fmt.get('fps')) |
54fc90aa | 2104 | |
94278f72 | 2105 | more_fields = { |
c63ca0ee | 2106 | 'filesize': filesize, |
bf1317d2 | 2107 | 'tbr': tbr, |
c9afb51c AH |
2108 | 'width': width, |
2109 | 'height': height, | |
bf1317d2 S |
2110 | 'fps': fps, |
2111 | 'format_note': quality_label or quality, | |
c9afb51c | 2112 | } |
94278f72 YCH |
2113 | for key, value in more_fields.items(): |
2114 | if value: | |
2115 | dct[key] = value | |
bf1317d2 | 2116 | type_ = url_data.get('type', [None])[0] or fmt.get('mimeType') |
aabc2be6 S |
2117 | if type_: |
2118 | type_split = type_.split(';') | |
2119 | kind_ext = type_split[0].split('/') | |
2120 | if len(kind_ext) == 2: | |
94278f72 YCH |
2121 | kind, _ = kind_ext |
2122 | dct['ext'] = mimetype2ext(type_split[0]) | |
aabc2be6 S |
2123 | if kind in ('audio', 'video'): |
2124 | codecs = None | |
2125 | for mobj in re.finditer( | |
2126 | r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_): | |
2127 | if mobj.group('key') == 'codecs': | |
2128 | codecs = mobj.group('val') | |
2129 | break | |
2130 | if codecs: | |
6310acf5 | 2131 | dct.update(parse_codecs(codecs)) |
e4a60912 S |
2132 | if dct.get('acodec') == 'none' or dct.get('vcodec') == 'none': |
2133 | dct['downloader_options'] = { | |
2134 | # Youtube throttles chunks >~10M | |
2135 | 'http_chunk_size': 10485760, | |
2136 | } | |
aabc2be6 | 2137 | formats.append(dct) |
c5e8d7af | 2138 | else: |
c3e54389 S |
2139 | manifest_url = ( |
2140 | url_or_none(try_get( | |
2141 | player_response, | |
2142 | lambda x: x['streamingData']['hlsManifestUrl'], | |
3089bc74 S |
2143 | compat_str)) |
2144 | or url_or_none(try_get( | |
c3e54389 S |
2145 | video_info, lambda x: x['hlsvp'][0], compat_str))) |
2146 | if manifest_url: | |
2147 | formats = [] | |
2148 | m3u8_formats = self._extract_m3u8_formats( | |
2149 | manifest_url, video_id, 'mp4', fatal=False) | |
2150 | for a_format in m3u8_formats: | |
2151 | itag = self._search_regex( | |
2152 | r'/itag/(\d+)/', a_format['url'], 'itag', default=None) | |
2153 | if itag: | |
2154 | a_format['format_id'] = itag | |
2155 | if itag in self._formats: | |
2156 | dct = self._formats[itag].copy() | |
2157 | dct.update(a_format) | |
2158 | a_format = dct | |
2159 | a_format['player_url'] = player_url | |
2160 | # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming | |
2161 | a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True' | |
78895bd3 U |
2162 | if self._downloader.params.get('youtube_include_hls_manifest', True): |
2163 | formats.append(a_format) | |
c3e54389 | 2164 | else: |
13577349 | 2165 | error_message = extract_unavailable_message() |
a0566bbf | 2166 | if not error_message: |
2167 | reason_list = try_get( | |
2168 | player_response, | |
2169 | lambda x: x['playabilityStatus']['errorScreen']['playerErrorMessageRenderer']['subreason']['runs'], | |
2170 | list) or [] | |
2171 | for reason in reason_list: | |
2172 | if not isinstance(reason, dict): | |
2173 | continue | |
2174 | reason_text = try_get(reason, lambda x: x['text'], compat_str) | |
2175 | if reason_text: | |
2176 | if not error_message: | |
2177 | error_message = '' | |
2178 | error_message += reason_text | |
2179 | if error_message: | |
2180 | error_message = clean_html(error_message) | |
c3e54389 | 2181 | if not error_message: |
13577349 S |
2182 | error_message = clean_html(try_get( |
2183 | player_response, lambda x: x['playabilityStatus']['reason'], | |
2184 | compat_str)) | |
2185 | if not error_message: | |
2186 | error_message = clean_html( | |
2187 | try_get(video_info, lambda x: x['reason'][0], compat_str)) | |
c3e54389 S |
2188 | if error_message: |
2189 | raise ExtractorError(error_message, expected=True) | |
2190 | raise ExtractorError('no conn, hlsvp, hlsManifestUrl or url_encoded_fmt_stream_map information found in video info') | |
c5e8d7af | 2191 | |
7e72694b | 2192 | # uploader |
dbdaaa23 S |
2193 | video_uploader = try_get( |
2194 | video_info, lambda x: x['author'][0], | |
2195 | compat_str) or str_or_none(video_details.get('author')) | |
7e72694b S |
2196 | if video_uploader: |
2197 | video_uploader = compat_urllib_parse_unquote_plus(video_uploader) | |
2198 | else: | |
2199 | self._downloader.report_warning('unable to extract uploader name') | |
2200 | ||
2201 | # uploader_id | |
2202 | video_uploader_id = None | |
2203 | video_uploader_url = None | |
2204 | mobj = re.search( | |
2205 | r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">', | |
2206 | video_webpage) | |
2207 | if mobj is not None: | |
2208 | video_uploader_id = mobj.group('uploader_id') | |
2209 | video_uploader_url = mobj.group('uploader_url') | |
a6211d23 S |
2210 | else: |
2211 | owner_profile_url = url_or_none(microformat.get('ownerProfileUrl')) | |
2212 | if owner_profile_url: | |
2213 | video_uploader_id = self._search_regex( | |
2214 | r'(?:user|channel)/([^/]+)', owner_profile_url, 'uploader id', | |
2215 | default=None) | |
2216 | video_uploader_url = owner_profile_url | |
7e72694b | 2217 | |
b45a9e69 | 2218 | channel_id = ( |
3089bc74 S |
2219 | str_or_none(video_details.get('channelId')) |
2220 | or self._html_search_meta( | |
2221 | 'channelId', video_webpage, 'channel id', default=None) | |
2222 | or self._search_regex( | |
b45a9e69 | 2223 | r'data-channel-external-id=(["\'])(?P<id>(?:(?!\1).)+)\1', |
2224 | video_webpage, 'channel id', default=None, group='id')) | |
dd4c4492 S |
2225 | channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None |
2226 | ||
b477fc13 S |
2227 | thumbnails = [] |
2228 | thumbnails_list = try_get( | |
2229 | video_details, lambda x: x['thumbnail']['thumbnails'], list) or [] | |
2230 | for t in thumbnails_list: | |
2231 | if not isinstance(t, dict): | |
2232 | continue | |
2233 | thumbnail_url = url_or_none(t.get('url')) | |
2234 | if not thumbnail_url: | |
2235 | continue | |
2236 | thumbnails.append({ | |
2237 | 'url': thumbnail_url, | |
2238 | 'width': int_or_none(t.get('width')), | |
2239 | 'height': int_or_none(t.get('height')), | |
2240 | }) | |
2241 | ||
2242 | if not thumbnails: | |
7e72694b | 2243 | video_thumbnail = None |
b477fc13 S |
2244 | # We try first to get a high quality image: |
2245 | m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">', | |
2246 | video_webpage, re.DOTALL) | |
2247 | if m_thumb is not None: | |
2248 | video_thumbnail = m_thumb.group(1) | |
2249 | thumbnail_url = try_get(video_info, lambda x: x['thumbnail_url'][0], compat_str) | |
2250 | if thumbnail_url: | |
2251 | video_thumbnail = compat_urllib_parse_unquote_plus(thumbnail_url) | |
2252 | if video_thumbnail: | |
2253 | thumbnails.append({'url': video_thumbnail}) | |
7e72694b S |
2254 | |
2255 | # upload date | |
2256 | upload_date = self._html_search_meta( | |
2257 | 'datePublished', video_webpage, 'upload date', default=None) | |
2258 | if not upload_date: | |
2259 | upload_date = self._search_regex( | |
2260 | [r'(?s)id="eow-date.*?>(.*?)</span>', | |
2261 | r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'], | |
2262 | video_webpage, 'upload date', default=None) | |
37357d21 S |
2263 | if not upload_date: |
2264 | upload_date = microformat.get('publishDate') or microformat.get('uploadDate') | |
7e72694b S |
2265 | upload_date = unified_strdate(upload_date) |
2266 | ||
2267 | video_license = self._html_search_regex( | |
2268 | r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li', | |
2269 | video_webpage, 'license', default=None) | |
2270 | ||
2271 | m_music = re.search( | |
2272 | r'''(?x) | |
2273 | <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s* | |
2274 | <ul[^>]*>\s* | |
2275 | <li>(?P<title>.+?) | |
2276 | by (?P<creator>.+?) | |
2277 | (?: | |
2278 | \(.+?\)| | |
2279 | <a[^>]* | |
2280 | (?: | |
2281 | \bhref=["\']/red[^>]*>| # drop possible | |
2282 | >\s*Listen ad-free with YouTube Red # YouTube Red ad | |
2283 | ) | |
2284 | .*? | |
2285 | )?</li | |
2286 | ''', | |
2287 | video_webpage) | |
2288 | if m_music: | |
2289 | video_alt_title = remove_quotes(unescapeHTML(m_music.group('title'))) | |
2290 | video_creator = clean_html(m_music.group('creator')) | |
2291 | else: | |
2292 | video_alt_title = video_creator = None | |
2293 | ||
2294 | def extract_meta(field): | |
2295 | return self._html_search_regex( | |
2296 | r'<h4[^>]+class="title"[^>]*>\s*%s\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li>\s*' % field, | |
2297 | video_webpage, field, default=None) | |
2298 | ||
2299 | track = extract_meta('Song') | |
2300 | artist = extract_meta('Artist') | |
92bc97d3 | 2301 | album = extract_meta('Album') |
822b9d9c RA |
2302 | |
2303 | # Youtube Music Auto-generated description | |
92bc97d3 | 2304 | release_date = release_year = None |
822b9d9c | 2305 | if video_description: |
38d70284 | 2306 | mobj = re.search(r'(?s)(?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+(?P<album>[^\n]+)(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?(?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?(.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?.+\nAuto-generated by YouTube\.\s*$', video_description) |
822b9d9c RA |
2307 | if mobj: |
2308 | if not track: | |
2309 | track = mobj.group('track').strip() | |
2310 | if not artist: | |
2311 | artist = mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')) | |
92bc97d3 RA |
2312 | if not album: |
2313 | album = mobj.group('album'.strip()) | |
822b9d9c RA |
2314 | release_year = mobj.group('release_year') |
2315 | release_date = mobj.group('release_date') | |
2316 | if release_date: | |
2317 | release_date = release_date.replace('-', '') | |
2318 | if not release_year: | |
2319 | release_year = int(release_date[:4]) | |
2320 | if release_year: | |
2321 | release_year = int(release_year) | |
7e72694b | 2322 | |
38d70284 | 2323 | yt_initial_data = self._extract_yt_initial_data(video_id, video_webpage) |
2324 | contents = try_get(yt_initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or [] | |
2325 | for content in contents: | |
2326 | rows = try_get(content, lambda x: x['videoSecondaryInfoRenderer']['metadataRowContainer']['metadataRowContainerRenderer']['rows'], list) or [] | |
2327 | multiple_songs = False | |
2328 | for row in rows: | |
2329 | if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True: | |
2330 | multiple_songs = True | |
2331 | break | |
2332 | for row in rows: | |
2333 | mrr = row.get('metadataRowRenderer') or {} | |
2334 | mrr_title = try_get( | |
2335 | mrr, lambda x: x['title']['simpleText'], compat_str) | |
2336 | mrr_contents = try_get( | |
2337 | mrr, lambda x: x['contents'][0], dict) or {} | |
2338 | mrr_contents_text = try_get(mrr_contents, [lambda x: x['simpleText'], lambda x: x['runs'][0]['text']], compat_str) | |
2339 | if not (mrr_title and mrr_contents_text): | |
2340 | continue | |
2341 | if mrr_title == 'License': | |
2342 | video_license = mrr_contents_text | |
2343 | elif not multiple_songs: | |
2344 | if mrr_title == 'Album': | |
2345 | album = mrr_contents_text | |
2346 | elif mrr_title == 'Artist': | |
2347 | artist = mrr_contents_text | |
2348 | elif mrr_title == 'Song': | |
2349 | track = mrr_contents_text | |
9322f116 | 2350 | |
7e72694b S |
2351 | m_episode = re.search( |
2352 | r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>', | |
2353 | video_webpage) | |
2354 | if m_episode: | |
c2dd2dc0 | 2355 | series = unescapeHTML(m_episode.group('series')) |
7e72694b S |
2356 | season_number = int(m_episode.group('season')) |
2357 | episode_number = int(m_episode.group('episode')) | |
2358 | else: | |
2359 | series = season_number = episode_number = None | |
2360 | ||
2361 | m_cat_container = self._search_regex( | |
2362 | r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>', | |
2363 | video_webpage, 'categories', default=None) | |
dbeafce5 | 2364 | category = None |
7e72694b S |
2365 | if m_cat_container: |
2366 | category = self._html_search_regex( | |
2367 | r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category', | |
2368 | default=None) | |
dbeafce5 S |
2369 | if not category: |
2370 | category = try_get( | |
2371 | microformat, lambda x: x['category'], compat_str) | |
2372 | video_categories = None if category is None else [category] | |
7e72694b S |
2373 | |
2374 | video_tags = [ | |
2375 | unescapeHTML(m.group('content')) | |
2376 | for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)] | |
dbeafce5 S |
2377 | if not video_tags: |
2378 | video_tags = try_get(video_details, lambda x: x['keywords'], list) | |
7e72694b S |
2379 | |
2380 | def _extract_count(count_name): | |
2381 | return str_to_int(self._search_regex( | |
a0566bbf | 2382 | (r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>' % re.escape(count_name), |
2383 | r'["\']label["\']\s*:\s*["\']([\d,.]+)\s+%ss["\']' % re.escape(count_name)), | |
7e72694b S |
2384 | video_webpage, count_name, default=None)) |
2385 | ||
2386 | like_count = _extract_count('like') | |
2387 | dislike_count = _extract_count('dislike') | |
2388 | ||
dbdaaa23 S |
2389 | if view_count is None: |
2390 | view_count = str_to_int(self._search_regex( | |
2391 | r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage, | |
2392 | 'view count', default=None)) | |
2393 | ||
bf3c9326 S |
2394 | average_rating = ( |
2395 | float_or_none(video_details.get('averageRating')) | |
2396 | or try_get(video_info, lambda x: float_or_none(x['avg_rating'][0]))) | |
2397 | ||
7e72694b | 2398 | # subtitles |
321bf820 | 2399 | video_subtitles = self.extract_subtitles( |
2400 | video_id, video_webpage, has_live_chat_replay) | |
29f7c58a | 2401 | automatic_captions = self.extract_automatic_captions(video_id, player_response, ytplayer_config) |
7e72694b S |
2402 | |
2403 | video_duration = try_get( | |
2404 | video_info, lambda x: int_or_none(x['length_seconds'][0])) | |
dbdaaa23 S |
2405 | if not video_duration: |
2406 | video_duration = int_or_none(video_details.get('lengthSeconds')) | |
7e72694b S |
2407 | if not video_duration: |
2408 | video_duration = parse_duration(self._html_search_meta( | |
2409 | 'duration', video_webpage, 'video duration')) | |
2410 | ||
b84071c0 JP |
2411 | # Get Subscriber Count of channel |
2412 | subscriber_count = parse_count(self._search_regex( | |
2413 | r'"text":"([\d\.]+\w?) subscribers"', | |
2414 | video_webpage, | |
2415 | 'subscriber count', | |
2416 | default=None | |
2417 | )) | |
2418 | ||
06167fbb | 2419 | # get xsrf for annotations or comments |
2420 | get_annotations = self._downloader.params.get('writeannotations', False) | |
2421 | get_comments = self._downloader.params.get('getcomments', False) | |
2422 | if get_annotations or get_comments: | |
29f7c58a | 2423 | xsrf_token = None |
2424 | ytcfg = self._extract_ytcfg(video_id, video_webpage) | |
2425 | if ytcfg: | |
2426 | xsrf_token = try_get(ytcfg, lambda x: x['XSRF_TOKEN'], compat_str) | |
2427 | if not xsrf_token: | |
2428 | xsrf_token = self._search_regex( | |
2429 | r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P<xsrf_token>(?:(?!\2).)+)\2', | |
2430 | video_webpage, 'xsrf token', group='xsrf_token', fatal=False) | |
06167fbb | 2431 | |
2432 | # annotations | |
2433 | video_annotations = None | |
2434 | if get_annotations: | |
64b6a4e9 RA |
2435 | invideo_url = try_get( |
2436 | player_response, lambda x: x['annotations'][0]['playerAnnotationsUrlsRenderer']['invideoUrl'], compat_str) | |
2437 | if xsrf_token and invideo_url: | |
29f7c58a | 2438 | xsrf_field_name = None |
2439 | if ytcfg: | |
2440 | xsrf_field_name = try_get(ytcfg, lambda x: x['XSRF_FIELD_NAME'], compat_str) | |
2441 | if not xsrf_field_name: | |
2442 | xsrf_field_name = self._search_regex( | |
2443 | r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P<xsrf_field_name>\w+)\2', | |
2444 | video_webpage, 'xsrf field name', | |
2445 | group='xsrf_field_name', default='session_token') | |
64b6a4e9 RA |
2446 | video_annotations = self._download_webpage( |
2447 | self._proto_relative_url(invideo_url), | |
2448 | video_id, note='Downloading annotations', | |
2449 | errnote='Unable to download video annotations', fatal=False, | |
2450 | data=urlencode_postdata({xsrf_field_name: xsrf_token})) | |
7e72694b | 2451 | |
84213ea8 | 2452 | chapters = self._extract_chapters(video_webpage, description_original, video_id, video_duration) |
7e72694b | 2453 | |
06167fbb | 2454 | # Get comments |
2455 | # TODO: Refactor and move to seperate function | |
2456 | if get_comments: | |
2457 | expected_video_comment_count = 0 | |
2458 | video_comments = [] | |
2459 | ||
2460 | def find_value(html, key, num_chars=2, separator='"'): | |
2461 | pos_begin = html.find(key) + len(key) + num_chars | |
2462 | pos_end = html.find(separator, pos_begin) | |
2463 | return html[pos_begin: pos_end] | |
2464 | ||
2465 | def search_dict(partial, key): | |
2466 | if isinstance(partial, dict): | |
2467 | for k, v in partial.items(): | |
2468 | if k == key: | |
2469 | yield v | |
2470 | else: | |
2471 | for o in search_dict(v, key): | |
2472 | yield o | |
2473 | elif isinstance(partial, list): | |
2474 | for i in partial: | |
2475 | for o in search_dict(i, key): | |
2476 | yield o | |
2477 | ||
2478 | try: | |
2479 | ncd = next(search_dict(yt_initial_data, 'nextContinuationData')) | |
8d0ea5f9 | 2480 | continuations = [ncd['continuation']] |
06167fbb | 2481 | # Handle videos where comments have been disabled entirely |
2482 | except StopIteration: | |
2483 | continuations = [] | |
2484 | ||
8d0ea5f9 | 2485 | def get_continuation(continuation, session_token, replies=False): |
06167fbb | 2486 | query = { |
66c935fb | 2487 | 'pbj': 1, |
2488 | 'ctoken': continuation, | |
06167fbb | 2489 | } |
2490 | if replies: | |
2491 | query['action_get_comment_replies'] = 1 | |
2492 | else: | |
2493 | query['action_get_comments'] = 1 | |
2494 | ||
2495 | while True: | |
2496 | content, handle = self._download_webpage_handle( | |
2497 | 'https://www.youtube.com/comment_service_ajax', | |
2498 | video_id, | |
2499 | note=False, | |
2500 | expected_status=[413], | |
2501 | data=urlencode_postdata({ | |
2502 | 'session_token': session_token | |
2503 | }), | |
2504 | query=query, | |
2505 | headers={ | |
2506 | 'Accept': '*/*', | |
2507 | 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:76.0) Gecko/20100101 Firefox/76.0', | |
2508 | 'X-YouTube-Client-Name': '1', | |
2509 | 'X-YouTube-Client-Version': '2.20201202.06.01' | |
2510 | } | |
2511 | ) | |
2512 | ||
2513 | response_code = handle.getcode() | |
2514 | if (response_code == 200): | |
2515 | return self._parse_json(content, video_id) | |
8d0ea5f9 | 2516 | if (response_code == 413): |
06167fbb | 2517 | return None |
2518 | raise ExtractorError('Unexpected HTTP error code: %s' % response_code) | |
2519 | ||
2520 | first_continuation = True | |
2521 | while continuations: | |
2522 | continuation, itct = continuations.pop() | |
8d0ea5f9 | 2523 | comment_response = get_continuation(continuation, xsrf_token) |
06167fbb | 2524 | if not comment_response: |
2525 | continue | |
2526 | if list(search_dict(comment_response, 'externalErrorMessage')): | |
2527 | raise ExtractorError('Error returned from server: ' + next(search_dict(comment_response, 'externalErrorMessage'))) | |
2528 | ||
8d0ea5f9 B |
2529 | if 'continuationContents' not in comment_response['response']: |
2530 | # Something is wrong here. Youtube won't accept this continuation token for some reason and responds with a user satisfaction dialog (error?) | |
2531 | continue | |
2532 | # not sure if this actually helps | |
2533 | if 'xsrf_token' in comment_response: | |
2534 | xsrf_token = comment_response['xsrf_token'] | |
2535 | ||
06167fbb | 2536 | item_section = comment_response['response']['continuationContents']['itemSectionContinuation'] |
2537 | if first_continuation: | |
2538 | expected_video_comment_count = int(item_section['header']['commentsHeaderRenderer']['countText']['runs'][0]['text'].replace(' Comments', '').replace('1 Comment', '1').replace(',', '')) | |
2539 | first_continuation = False | |
2540 | if 'contents' not in item_section: | |
2541 | # continuation returned no comments? | |
2542 | # set an empty array as to not break the for loop | |
2543 | item_section['contents'] = [] | |
2544 | ||
2545 | for meta_comment in item_section['contents']: | |
2546 | comment = meta_comment['commentThreadRenderer']['comment']['commentRenderer'] | |
2547 | video_comments.append({ | |
2548 | 'id': comment['commentId'], | |
2549 | 'text': ''.join([c['text'] for c in comment['contentText']['runs']]), | |
8d0ea5f9 | 2550 | 'time_text': ''.join([c['text'] for c in comment['publishedTimeText']['runs']]), |
06167fbb | 2551 | 'author': comment.get('authorText', {}).get('simpleText', ''), |
2552 | 'votes': comment.get('voteCount', {}).get('simpleText', '0'), | |
2553 | 'author_thumbnail': comment['authorThumbnail']['thumbnails'][-1]['url'], | |
2554 | 'parent': 'root' | |
2555 | }) | |
2556 | if 'replies' not in meta_comment['commentThreadRenderer']: | |
2557 | continue | |
2558 | ||
8d0ea5f9 B |
2559 | reply_continuations = [rcn['nextContinuationData']['continuation'] for rcn in meta_comment['commentThreadRenderer']['replies']['commentRepliesRenderer']['continuations']] |
2560 | while reply_continuations: | |
06167fbb | 2561 | time.sleep(1) |
8d0ea5f9 B |
2562 | continuation = reply_continuations.pop() |
2563 | replies_data = get_continuation(continuation, xsrf_token, True) | |
06167fbb | 2564 | if not replies_data or 'continuationContents' not in replies_data[1]['response']: |
8d0ea5f9 | 2565 | continue |
06167fbb | 2566 | |
2567 | if self._downloader.params.get('verbose', False): | |
2568 | self.to_screen('[debug] Comments downloaded (chain %s) %s of ~%s' % (comment['commentId'], len(video_comments), expected_video_comment_count)) | |
2569 | reply_comment_meta = replies_data[1]['response']['continuationContents']['commentRepliesContinuation'] | |
2570 | for reply_meta in replies_data[1]['response']['continuationContents']['commentRepliesContinuation']['contents']: | |
2571 | reply_comment = reply_meta['commentRenderer'] | |
2572 | video_comments.append({ | |
2573 | 'id': reply_comment['commentId'], | |
2574 | 'text': ''.join([c['text'] for c in reply_comment['contentText']['runs']]), | |
8d0ea5f9 | 2575 | 'time_text': ''.join([c['text'] for c in reply_comment['publishedTimeText']['runs']]), |
06167fbb | 2576 | 'author': reply_comment.get('authorText', {}).get('simpleText', ''), |
2577 | 'votes': reply_comment.get('voteCount', {}).get('simpleText', '0'), | |
2578 | 'author_thumbnail': reply_comment['authorThumbnail']['thumbnails'][-1]['url'], | |
2579 | 'parent': comment['commentId'] | |
2580 | }) | |
2581 | if 'continuations' not in reply_comment_meta or len(reply_comment_meta['continuations']) == 0: | |
8d0ea5f9 | 2582 | continue |
06167fbb | 2583 | |
8d0ea5f9 | 2584 | reply_continuations += [rcn['nextContinuationData']['continuation'] for rcn in reply_comment_meta['continuations']] |
06167fbb | 2585 | |
2586 | self.to_screen('Comments downloaded %s of ~%s' % (len(video_comments), expected_video_comment_count)) | |
2587 | ||
2588 | if 'continuations' in item_section: | |
8d0ea5f9 | 2589 | continuations += [ncd['nextContinuationData']['continuation'] for ncd in item_section['continuations']] |
06167fbb | 2590 | time.sleep(1) |
2591 | ||
2592 | self.to_screen('Total comments downloaded %s of ~%s' % (len(video_comments), expected_video_comment_count)) | |
2593 | else: | |
2594 | expected_video_comment_count = None | |
2595 | video_comments = None | |
2596 | ||
dd27fd17 | 2597 | # Look for the DASH manifest |
203fb43f | 2598 | if self._downloader.params.get('youtube_include_dash_manifest', True): |
77c6fb5b | 2599 | dash_mpd_fatal = True |
8ff648e4 | 2600 | for mpd_url in dash_mpds: |
d8d24a92 | 2601 | dash_formats = {} |
774e208f | 2602 | try: |
05d0d131 YCH |
2603 | def decrypt_sig(mobj): |
2604 | s = mobj.group(1) | |
2605 | dec_s = self._decrypt_signature(s, video_id, player_url, age_gate) | |
2606 | return '/signature/%s' % dec_s | |
2607 | ||
8ff648e4 | 2608 | mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url) |
2d2fa82d | 2609 | |
8ff648e4 | 2610 | for df in self._extract_mpd_formats( |
2611 | mpd_url, video_id, fatal=dash_mpd_fatal, | |
2612 | formats_dict=self._formats): | |
c63ca0ee S |
2613 | if not df.get('filesize'): |
2614 | df['filesize'] = _extract_filesize(df['url']) | |
d8d24a92 S |
2615 | # Do not overwrite DASH format found in some previous DASH manifest |
2616 | if df['format_id'] not in dash_formats: | |
2617 | dash_formats[df['format_id']] = df | |
77c6fb5b S |
2618 | # Additional DASH manifests may end up in HTTP Error 403 therefore |
2619 | # allow them to fail without bug report message if we already have | |
2620 | # some DASH manifest succeeded. This is temporary workaround to reduce | |
2621 | # burst of bug reports until we figure out the reason and whether it | |
2622 | # can be fixed at all. | |
2623 | dash_mpd_fatal = False | |
774e208f PH |
2624 | except (ExtractorError, KeyError) as e: |
2625 | self.report_warning( | |
2626 | 'Skipping DASH manifest: %r' % e, video_id) | |
d8d24a92 | 2627 | if dash_formats: |
04b3b3df JMF |
2628 | # Remove the formats we found through non-DASH, they |
2629 | # contain less info and it can be wrong, because we use | |
2630 | # fixed values (for example the resolution). See | |
067aa17e | 2631 | # https://github.com/ytdl-org/youtube-dl/issues/5774 for an |
04b3b3df | 2632 | # example. |
d80265cc | 2633 | formats = [f for f in formats if f['format_id'] not in dash_formats.keys()] |
d8d24a92 | 2634 | formats.extend(dash_formats.values()) |
d80044c2 | 2635 | |
6271f1ca PH |
2636 | # Check for malformed aspect ratio |
2637 | stretched_m = re.search( | |
2638 | r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">', | |
2639 | video_webpage) | |
2640 | if stretched_m: | |
313dfc45 LL |
2641 | w = float(stretched_m.group('w')) |
2642 | h = float(stretched_m.group('h')) | |
5faf9fed S |
2643 | # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0). |
2644 | # We will only process correct ratios. | |
313dfc45 | 2645 | if w > 0 and h > 0: |
41f24c32 | 2646 | ratio = w / h |
313dfc45 LL |
2647 | for f in formats: |
2648 | if f.get('vcodec') != 'none': | |
2649 | f['stretched_ratio'] = ratio | |
6271f1ca | 2650 | |
026fbedc | 2651 | if not formats: |
43ebf77d S |
2652 | if 'reason' in video_info: |
2653 | if 'The uploader has not made this video available in your country.' in video_info['reason']: | |
2654 | regions_allowed = self._html_search_meta( | |
2655 | 'regionsAllowed', video_webpage, default=None) | |
2656 | countries = regions_allowed.split(',') if regions_allowed else None | |
2657 | self.raise_geo_restricted( | |
2658 | msg=video_info['reason'][0], countries=countries) | |
2659 | reason = video_info['reason'][0] | |
2660 | if 'Invalid parameters' in reason: | |
2661 | unavailable_message = extract_unavailable_message() | |
2662 | if unavailable_message: | |
2663 | reason = unavailable_message | |
2664 | raise ExtractorError( | |
2665 | 'YouTube said: %s' % reason, | |
2666 | expected=True, video_id=video_id) | |
2667 | if video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos']): | |
2668 | raise ExtractorError('This video is DRM protected.', expected=True) | |
0d297518 | 2669 | |
4bcc7bd1 | 2670 | self._sort_formats(formats) |
4ea3be0a | 2671 | |
21c340b8 | 2672 | self.mark_watched(video_id, video_info, player_response) |
d77ab8e2 | 2673 | |
4ea3be0a | 2674 | return { |
8bcc8756 JW |
2675 | 'id': video_id, |
2676 | 'uploader': video_uploader, | |
2677 | 'uploader_id': video_uploader_id, | |
fd050249 | 2678 | 'uploader_url': video_uploader_url, |
b60419c5 | 2679 | 'channel': video_uploader, |
dd4c4492 S |
2680 | 'channel_id': channel_id, |
2681 | 'channel_url': channel_url, | |
8bcc8756 | 2682 | 'upload_date': upload_date, |
7caf9830 | 2683 | 'license': video_license, |
936784b2 | 2684 | 'creator': video_creator or artist, |
8bcc8756 | 2685 | 'title': video_title, |
936784b2 | 2686 | 'alt_title': video_alt_title or track, |
b477fc13 | 2687 | 'thumbnails': thumbnails, |
8bcc8756 JW |
2688 | 'description': video_description, |
2689 | 'categories': video_categories, | |
000b6b5a | 2690 | 'tags': video_tags, |
8bcc8756 | 2691 | 'subtitles': video_subtitles, |
360e1ca5 | 2692 | 'automatic_captions': automatic_captions, |
8bcc8756 JW |
2693 | 'duration': video_duration, |
2694 | 'age_limit': 18 if age_gate else 0, | |
2695 | 'annotations': video_annotations, | |
9cafc3fd | 2696 | 'chapters': chapters, |
7e8c0af0 | 2697 | 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id, |
8bcc8756 | 2698 | 'view_count': view_count, |
4ea3be0a | 2699 | 'like_count': like_count, |
2700 | 'dislike_count': dislike_count, | |
bf3c9326 | 2701 | 'average_rating': average_rating, |
8bcc8756 | 2702 | 'formats': formats, |
2fe1ff85 | 2703 | 'is_live': is_live, |
7c80519c | 2704 | 'start_time': start_time, |
297a564b | 2705 | 'end_time': end_time, |
12afdc2a S |
2706 | 'series': series, |
2707 | 'season_number': season_number, | |
2708 | 'episode_number': episode_number, | |
936784b2 S |
2709 | 'track': track, |
2710 | 'artist': artist, | |
5caabd3c | 2711 | 'album': album, |
2712 | 'release_date': release_date, | |
2713 | 'release_year': release_year, | |
b84071c0 | 2714 | 'subscriber_count': subscriber_count, |
5ac23244 | 2715 | 'playable_in_embed': playable_in_embed, |
06167fbb | 2716 | 'comments': video_comments, |
2717 | 'comment_count': expected_video_comment_count, | |
4ea3be0a | 2718 | } |
c5e8d7af | 2719 | |
5f6a1245 | 2720 | |
8bdd16b4 | 2721 | class YoutubeTabIE(YoutubeBaseInfoExtractor): |
2722 | IE_DESC = 'YouTube.com tab' | |
70d5c17b | 2723 | _VALID_URL = r'''(?x) |
2724 | https?:// | |
2725 | (?:\w+\.)? | |
2726 | (?: | |
2727 | youtube(?:kids)?\.com| | |
2728 | invidio\.us | |
2729 | )/ | |
2730 | (?: | |
2731 | (?:channel|c|user)/| | |
2732 | (?P<not_channel> | |
3d3dddc9 | 2733 | feed/| |
70d5c17b | 2734 | (?:playlist|watch)\?.*?\blist= |
2735 | )| | |
29f7c58a | 2736 | (?!(?:%s)\b) # Direct URLs |
70d5c17b | 2737 | ) |
2738 | (?P<id>[^/?\#&]+) | |
2739 | ''' % YoutubeBaseInfoExtractor._RESERVED_NAMES | |
8bdd16b4 | 2740 | IE_NAME = 'youtube:tab' |
2741 | ||
81127aa5 | 2742 | _TESTS = [{ |
8bdd16b4 | 2743 | # playlists, multipage |
2744 | 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid', | |
2745 | 'playlist_mincount': 94, | |
2746 | 'info_dict': { | |
2747 | 'id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
2748 | 'title': 'Игорь Клейнер - Playlists', | |
2749 | 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2', | |
2750 | }, | |
2751 | }, { | |
2752 | # playlists, multipage, different order | |
2753 | 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd', | |
2754 | 'playlist_mincount': 94, | |
2755 | 'info_dict': { | |
2756 | 'id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
2757 | 'title': 'Игорь Клейнер - Playlists', | |
2758 | 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2', | |
2759 | }, | |
2760 | }, { | |
2761 | # playlists, singlepage | |
2762 | 'url': 'https://www.youtube.com/user/ThirstForScience/playlists', | |
2763 | 'playlist_mincount': 4, | |
2764 | 'info_dict': { | |
2765 | 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ', | |
2766 | 'title': 'ThirstForScience - Playlists', | |
2767 | 'description': 'md5:609399d937ea957b0f53cbffb747a14c', | |
2768 | } | |
2769 | }, { | |
2770 | 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists', | |
2771 | 'only_matching': True, | |
2772 | }, { | |
2773 | # basic, single video playlist | |
0e30a7b9 | 2774 | 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', |
81127aa5 | 2775 | 'info_dict': { |
0e30a7b9 | 2776 | 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', |
2777 | 'uploader': 'Sergey M.', | |
2778 | 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', | |
3867038a | 2779 | 'title': 'youtube-dl public playlist', |
81127aa5 | 2780 | }, |
0e30a7b9 | 2781 | 'playlist_count': 1, |
9291475f | 2782 | }, { |
8bdd16b4 | 2783 | # empty playlist |
0e30a7b9 | 2784 | 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', |
9291475f | 2785 | 'info_dict': { |
0e30a7b9 | 2786 | 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', |
2787 | 'uploader': 'Sergey M.', | |
2788 | 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', | |
3867038a | 2789 | 'title': 'youtube-dl empty playlist', |
9291475f PH |
2790 | }, |
2791 | 'playlist_count': 0, | |
2792 | }, { | |
8bdd16b4 | 2793 | # Home tab |
2794 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured', | |
9291475f | 2795 | 'info_dict': { |
8bdd16b4 | 2796 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', |
2797 | 'title': 'lex will - Home', | |
2798 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
9291475f | 2799 | }, |
8bdd16b4 | 2800 | 'playlist_mincount': 2, |
9291475f | 2801 | }, { |
8bdd16b4 | 2802 | # Videos tab |
2803 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos', | |
9291475f | 2804 | 'info_dict': { |
8bdd16b4 | 2805 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', |
2806 | 'title': 'lex will - Videos', | |
2807 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
9291475f | 2808 | }, |
8bdd16b4 | 2809 | 'playlist_mincount': 975, |
9291475f | 2810 | }, { |
8bdd16b4 | 2811 | # Videos tab, sorted by popular |
2812 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid', | |
9291475f | 2813 | 'info_dict': { |
8bdd16b4 | 2814 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', |
2815 | 'title': 'lex will - Videos', | |
2816 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
9291475f | 2817 | }, |
8bdd16b4 | 2818 | 'playlist_mincount': 199, |
9291475f | 2819 | }, { |
8bdd16b4 | 2820 | # Playlists tab |
2821 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists', | |
9291475f | 2822 | 'info_dict': { |
8bdd16b4 | 2823 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', |
2824 | 'title': 'lex will - Playlists', | |
2825 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
9291475f | 2826 | }, |
8bdd16b4 | 2827 | 'playlist_mincount': 17, |
ac7553d0 | 2828 | }, { |
8bdd16b4 | 2829 | # Community tab |
2830 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community', | |
ac7553d0 | 2831 | 'info_dict': { |
8bdd16b4 | 2832 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', |
2833 | 'title': 'lex will - Community', | |
2834 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
2835 | }, | |
2836 | 'playlist_mincount': 18, | |
87dadd45 | 2837 | }, { |
8bdd16b4 | 2838 | # Channels tab |
2839 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels', | |
87dadd45 | 2840 | 'info_dict': { |
8bdd16b4 | 2841 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', |
2842 | 'title': 'lex will - Channels', | |
2843 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
2844 | }, | |
2845 | 'playlist_mincount': 138, | |
6b08cdf6 | 2846 | }, { |
a0566bbf | 2847 | 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA', |
8bdd16b4 | 2848 | 'only_matching': True, |
2849 | }, { | |
a0566bbf | 2850 | 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', |
8bdd16b4 | 2851 | 'only_matching': True, |
2852 | }, { | |
a0566bbf | 2853 | 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', |
8bdd16b4 | 2854 | 'only_matching': True, |
2855 | }, { | |
2856 | 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', | |
2857 | 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
2858 | 'info_dict': { | |
2859 | 'title': '29C3: Not my department', | |
2860 | 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
2861 | 'uploader': 'Christiaan008', | |
2862 | 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg', | |
2863 | }, | |
2864 | 'playlist_count': 96, | |
2865 | }, { | |
2866 | 'note': 'Large playlist', | |
2867 | 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', | |
6b08cdf6 | 2868 | 'info_dict': { |
8bdd16b4 | 2869 | 'title': 'Uploads from Cauchemar', |
2870 | 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', | |
2871 | 'uploader': 'Cauchemar', | |
2872 | 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q', | |
13a75688 | 2873 | }, |
8bdd16b4 | 2874 | 'playlist_mincount': 1123, |
2875 | }, { | |
2876 | # even larger playlist, 8832 videos | |
2877 | 'url': 'http://www.youtube.com/user/NASAgovVideo/videos', | |
2878 | 'only_matching': True, | |
4b7df0d3 JMF |
2879 | }, { |
2880 | 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', | |
2881 | 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', | |
2882 | 'info_dict': { | |
acf757f4 PH |
2883 | 'title': 'Uploads from Interstellar Movie', |
2884 | 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', | |
13a75688 | 2885 | 'uploader': 'Interstellar Movie', |
8bdd16b4 | 2886 | 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA', |
4b7df0d3 | 2887 | }, |
481cc733 | 2888 | 'playlist_mincount': 21, |
8bdd16b4 | 2889 | }, { |
2890 | # https://github.com/ytdl-org/youtube-dl/issues/21844 | |
2891 | 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', | |
2892 | 'info_dict': { | |
2893 | 'title': 'Data Analysis with Dr Mike Pound', | |
2894 | 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', | |
2895 | 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA', | |
2896 | 'uploader': 'Computerphile', | |
2897 | }, | |
2898 | 'playlist_mincount': 11, | |
2899 | }, { | |
a0566bbf | 2900 | 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', |
8bdd16b4 | 2901 | 'only_matching': True, |
dacb3a86 S |
2902 | }, { |
2903 | # Playlist URL that does not actually serve a playlist | |
2904 | 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4', | |
2905 | 'info_dict': { | |
2906 | 'id': 'FqZTN594JQw', | |
2907 | 'ext': 'webm', | |
2908 | 'title': "Smiley's People 01 detective, Adventure Series, Action", | |
2909 | 'uploader': 'STREEM', | |
2910 | 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng', | |
ec85ded8 | 2911 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng', |
dacb3a86 S |
2912 | 'upload_date': '20150526', |
2913 | 'license': 'Standard YouTube License', | |
2914 | 'description': 'md5:507cdcb5a49ac0da37a920ece610be80', | |
2915 | 'categories': ['People & Blogs'], | |
2916 | 'tags': list, | |
dbdaaa23 | 2917 | 'view_count': int, |
dacb3a86 S |
2918 | 'like_count': int, |
2919 | 'dislike_count': int, | |
2920 | }, | |
2921 | 'params': { | |
2922 | 'skip_download': True, | |
2923 | }, | |
13a75688 | 2924 | 'skip': 'This video is not available.', |
dacb3a86 | 2925 | 'add_ie': [YoutubeIE.ie_key()], |
481cc733 | 2926 | }, { |
8bdd16b4 | 2927 | 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g', |
c0345b82 | 2928 | 'only_matching': True, |
66b48727 | 2929 | }, { |
8bdd16b4 | 2930 | 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM', |
66b48727 | 2931 | 'only_matching': True, |
a0566bbf | 2932 | }, { |
2933 | 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live', | |
2934 | 'info_dict': { | |
2935 | 'id': '9Auq9mYxFEE', | |
2936 | 'ext': 'mp4', | |
2937 | 'title': 'Watch Sky News live', | |
2938 | 'uploader': 'Sky News', | |
2939 | 'uploader_id': 'skynews', | |
2940 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews', | |
2941 | 'upload_date': '20191102', | |
2942 | 'description': 'md5:78de4e1c2359d0ea3ed829678e38b662', | |
2943 | 'categories': ['News & Politics'], | |
2944 | 'tags': list, | |
2945 | 'like_count': int, | |
2946 | 'dislike_count': int, | |
2947 | }, | |
2948 | 'params': { | |
2949 | 'skip_download': True, | |
2950 | }, | |
2951 | }, { | |
2952 | 'url': 'https://www.youtube.com/user/TheYoungTurks/live', | |
2953 | 'info_dict': { | |
2954 | 'id': 'a48o2S1cPoo', | |
2955 | 'ext': 'mp4', | |
2956 | 'title': 'The Young Turks - Live Main Show', | |
2957 | 'uploader': 'The Young Turks', | |
2958 | 'uploader_id': 'TheYoungTurks', | |
2959 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks', | |
2960 | 'upload_date': '20150715', | |
2961 | 'license': 'Standard YouTube License', | |
2962 | 'description': 'md5:438179573adcdff3c97ebb1ee632b891', | |
2963 | 'categories': ['News & Politics'], | |
2964 | 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'], | |
2965 | 'like_count': int, | |
2966 | 'dislike_count': int, | |
2967 | }, | |
2968 | 'params': { | |
2969 | 'skip_download': True, | |
2970 | }, | |
2971 | 'only_matching': True, | |
2972 | }, { | |
2973 | 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live', | |
2974 | 'only_matching': True, | |
2975 | }, { | |
2976 | 'url': 'https://www.youtube.com/c/CommanderVideoHq/live', | |
2977 | 'only_matching': True, | |
3d3dddc9 | 2978 | }, { |
2979 | 'url': 'https://www.youtube.com/feed/trending', | |
2980 | 'only_matching': True, | |
2981 | }, { | |
2982 | # needs auth | |
2983 | 'url': 'https://www.youtube.com/feed/library', | |
2984 | 'only_matching': True, | |
2985 | }, { | |
2986 | # needs auth | |
2987 | 'url': 'https://www.youtube.com/feed/history', | |
2988 | 'only_matching': True, | |
2989 | }, { | |
2990 | # needs auth | |
2991 | 'url': 'https://www.youtube.com/feed/subscriptions', | |
2992 | 'only_matching': True, | |
2993 | }, { | |
2994 | # needs auth | |
2995 | 'url': 'https://www.youtube.com/feed/watch_later', | |
2996 | 'only_matching': True, | |
2997 | }, { | |
2998 | # no longer available? | |
2999 | 'url': 'https://www.youtube.com/feed/recommended', | |
3000 | 'only_matching': True, | |
29f7c58a | 3001 | }, { |
3002 | # inline playlist with not always working continuations | |
3003 | 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C', | |
3004 | 'only_matching': True, | |
3005 | }, { | |
3006 | 'url': 'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8', | |
3007 | 'only_matching': True, | |
3008 | }, { | |
3009 | 'url': 'https://www.youtube.com/course', | |
3010 | 'only_matching': True, | |
3011 | }, { | |
3012 | 'url': 'https://www.youtube.com/zsecurity', | |
3013 | 'only_matching': True, | |
3014 | }, { | |
3015 | 'url': 'http://www.youtube.com/NASAgovVideo/videos', | |
3016 | 'only_matching': True, | |
3017 | }, { | |
3018 | 'url': 'https://www.youtube.com/TheYoungTurks/live', | |
3019 | 'only_matching': True, | |
3020 | }] | |
3021 | ||
3022 | @classmethod | |
3023 | def suitable(cls, url): | |
3024 | return False if YoutubeIE.suitable(url) else super( | |
3025 | YoutubeTabIE, cls).suitable(url) | |
8bdd16b4 | 3026 | |
3027 | def _extract_channel_id(self, webpage): | |
3028 | channel_id = self._html_search_meta( | |
3029 | 'channelId', webpage, 'channel id', default=None) | |
3030 | if channel_id: | |
3031 | return channel_id | |
3032 | channel_url = self._html_search_meta( | |
3033 | ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url', | |
3034 | 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad', | |
3035 | 'twitter:app:url:googleplay'), webpage, 'channel url') | |
3036 | return self._search_regex( | |
3037 | r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+', | |
3038 | channel_url, 'channel id') | |
15f6397c | 3039 | |
8bdd16b4 | 3040 | @staticmethod |
3041 | def _extract_grid_item_renderer(item): | |
3042 | for item_kind in ('Playlist', 'Video', 'Channel'): | |
3043 | renderer = item.get('grid%sRenderer' % item_kind) | |
3044 | if renderer: | |
3045 | return renderer | |
3046 | ||
8bdd16b4 | 3047 | def _grid_entries(self, grid_renderer): |
3048 | for item in grid_renderer['items']: | |
3049 | if not isinstance(item, dict): | |
39b62db1 | 3050 | continue |
8bdd16b4 | 3051 | renderer = self._extract_grid_item_renderer(item) |
3052 | if not isinstance(renderer, dict): | |
3053 | continue | |
3054 | title = try_get( | |
3055 | renderer, lambda x: x['title']['runs'][0]['text'], compat_str) | |
3056 | # playlist | |
3057 | playlist_id = renderer.get('playlistId') | |
3058 | if playlist_id: | |
3059 | yield self.url_result( | |
3060 | 'https://www.youtube.com/playlist?list=%s' % playlist_id, | |
3061 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id, | |
3062 | video_title=title) | |
3063 | # video | |
3064 | video_id = renderer.get('videoId') | |
3065 | if video_id: | |
3066 | yield self._extract_video(renderer) | |
3067 | # channel | |
3068 | channel_id = renderer.get('channelId') | |
3069 | if channel_id: | |
3070 | title = try_get( | |
3071 | renderer, lambda x: x['title']['simpleText'], compat_str) | |
3072 | yield self.url_result( | |
3073 | 'https://www.youtube.com/channel/%s' % channel_id, | |
3074 | ie=YoutubeTabIE.ie_key(), video_title=title) | |
3075 | ||
3d3dddc9 | 3076 | def _shelf_entries_from_content(self, shelf_renderer): |
3077 | content = shelf_renderer.get('content') | |
3078 | if not isinstance(content, dict): | |
8bdd16b4 | 3079 | return |
3d3dddc9 | 3080 | renderer = content.get('gridRenderer') |
3081 | if renderer: | |
3082 | # TODO: add support for nested playlists so each shelf is processed | |
3083 | # as separate playlist | |
3084 | # TODO: this includes only first N items | |
3085 | for entry in self._grid_entries(renderer): | |
3086 | yield entry | |
3087 | renderer = content.get('horizontalListRenderer') | |
3088 | if renderer: | |
3089 | # TODO | |
3090 | pass | |
8bdd16b4 | 3091 | |
29f7c58a | 3092 | def _shelf_entries(self, shelf_renderer, skip_channels=False): |
8bdd16b4 | 3093 | ep = try_get( |
3094 | shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'], | |
3095 | compat_str) | |
3096 | shelf_url = urljoin('https://www.youtube.com', ep) | |
3d3dddc9 | 3097 | if shelf_url: |
29f7c58a | 3098 | # Skipping links to another channels, note that checking for |
3099 | # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL | |
3100 | # will not work | |
3101 | if skip_channels and '/channels?' in shelf_url: | |
3102 | return | |
3d3dddc9 | 3103 | title = try_get( |
3104 | shelf_renderer, lambda x: x['title']['runs'][0]['text'], compat_str) | |
3105 | yield self.url_result(shelf_url, video_title=title) | |
3106 | # Shelf may not contain shelf URL, fallback to extraction from content | |
3107 | for entry in self._shelf_entries_from_content(shelf_renderer): | |
3108 | yield entry | |
c5e8d7af | 3109 | |
8bdd16b4 | 3110 | def _playlist_entries(self, video_list_renderer): |
3111 | for content in video_list_renderer['contents']: | |
3112 | if not isinstance(content, dict): | |
3113 | continue | |
3114 | renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer') | |
3115 | if not isinstance(renderer, dict): | |
3116 | continue | |
3117 | video_id = renderer.get('videoId') | |
3118 | if not video_id: | |
3119 | continue | |
3120 | yield self._extract_video(renderer) | |
07aeced6 | 3121 | |
3d3dddc9 | 3122 | r""" # Not needed in the new implementation |
3462ffa8 | 3123 | def _itemSection_entries(self, item_sect_renderer): |
3124 | for content in item_sect_renderer['contents']: | |
3125 | if not isinstance(content, dict): | |
3126 | continue | |
3127 | renderer = content.get('videoRenderer', {}) | |
3128 | if not isinstance(renderer, dict): | |
3129 | continue | |
3130 | video_id = renderer.get('videoId') | |
3131 | if not video_id: | |
3132 | continue | |
3133 | yield self._extract_video(renderer) | |
3d3dddc9 | 3134 | """ |
3462ffa8 | 3135 | |
3136 | def _rich_entries(self, rich_grid_renderer): | |
3137 | renderer = try_get( | |
70d5c17b | 3138 | rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {} |
3462ffa8 | 3139 | video_id = renderer.get('videoId') |
3140 | if not video_id: | |
3141 | return | |
3142 | yield self._extract_video(renderer) | |
3143 | ||
8bdd16b4 | 3144 | def _video_entry(self, video_renderer): |
3145 | video_id = video_renderer.get('videoId') | |
3146 | if video_id: | |
3147 | return self._extract_video(video_renderer) | |
dacb3a86 | 3148 | |
8bdd16b4 | 3149 | def _post_thread_entries(self, post_thread_renderer): |
3150 | post_renderer = try_get( | |
3151 | post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict) | |
3152 | if not post_renderer: | |
3153 | return | |
3154 | # video attachment | |
3155 | video_renderer = try_get( | |
3156 | post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) | |
3157 | video_id = None | |
3158 | if video_renderer: | |
3159 | entry = self._video_entry(video_renderer) | |
3160 | if entry: | |
3161 | yield entry | |
3162 | # inline video links | |
3163 | runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or [] | |
3164 | for run in runs: | |
3165 | if not isinstance(run, dict): | |
3166 | continue | |
3167 | ep_url = try_get( | |
3168 | run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str) | |
3169 | if not ep_url: | |
3170 | continue | |
3171 | if not YoutubeIE.suitable(ep_url): | |
3172 | continue | |
3173 | ep_video_id = YoutubeIE._match_id(ep_url) | |
3174 | if video_id == ep_video_id: | |
3175 | continue | |
3176 | yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=video_id) | |
dacb3a86 | 3177 | |
8bdd16b4 | 3178 | def _post_thread_continuation_entries(self, post_thread_continuation): |
3179 | contents = post_thread_continuation.get('contents') | |
3180 | if not isinstance(contents, list): | |
3181 | return | |
3182 | for content in contents: | |
3183 | renderer = content.get('backstagePostThreadRenderer') | |
3184 | if not isinstance(renderer, dict): | |
3185 | continue | |
3186 | for entry in self._post_thread_entries(renderer): | |
3187 | yield entry | |
07aeced6 | 3188 | |
29f7c58a | 3189 | @staticmethod |
3190 | def _build_continuation_query(continuation, ctp=None): | |
3191 | query = { | |
3192 | 'ctoken': continuation, | |
3193 | 'continuation': continuation, | |
3194 | } | |
3195 | if ctp: | |
3196 | query['itct'] = ctp | |
3197 | return query | |
3198 | ||
8bdd16b4 | 3199 | @staticmethod |
3200 | def _extract_next_continuation_data(renderer): | |
3201 | next_continuation = try_get( | |
3202 | renderer, lambda x: x['continuations'][0]['nextContinuationData'], dict) | |
3203 | if not next_continuation: | |
3204 | return | |
3205 | continuation = next_continuation.get('continuation') | |
3206 | if not continuation: | |
3207 | return | |
3208 | ctp = next_continuation.get('clickTrackingParams') | |
29f7c58a | 3209 | return YoutubeTabIE._build_continuation_query(continuation, ctp) |
c5e8d7af | 3210 | |
8bdd16b4 | 3211 | @classmethod |
3212 | def _extract_continuation(cls, renderer): | |
3213 | next_continuation = cls._extract_next_continuation_data(renderer) | |
3214 | if next_continuation: | |
3215 | return next_continuation | |
3216 | contents = renderer.get('contents') | |
3217 | if not isinstance(contents, list): | |
3218 | return | |
3219 | for content in contents: | |
3220 | if not isinstance(content, dict): | |
3221 | continue | |
3222 | continuation_ep = try_get( | |
3223 | content, lambda x: x['continuationItemRenderer']['continuationEndpoint'], | |
3224 | dict) | |
3225 | if not continuation_ep: | |
3226 | continue | |
3227 | continuation = try_get( | |
3228 | continuation_ep, lambda x: x['continuationCommand']['token'], compat_str) | |
3229 | if not continuation: | |
3230 | continue | |
3231 | ctp = continuation_ep.get('clickTrackingParams') | |
29f7c58a | 3232 | return YoutubeTabIE._build_continuation_query(continuation, ctp) |
448830ce | 3233 | |
8bdd16b4 | 3234 | def _entries(self, tab, identity_token): |
3462ffa8 | 3235 | |
70d5c17b | 3236 | def extract_entries(parent_renderer): # this needs to called again for continuation to work with feeds |
3237 | contents = try_get(parent_renderer, lambda x: x['contents'], list) or [] | |
3238 | for content in contents: | |
3239 | if not isinstance(content, dict): | |
8bdd16b4 | 3240 | continue |
70d5c17b | 3241 | is_renderer = try_get(content, lambda x: x['itemSectionRenderer'], dict) |
3462ffa8 | 3242 | if not is_renderer: |
70d5c17b | 3243 | renderer = content.get('richItemRenderer') |
3462ffa8 | 3244 | if renderer: |
3245 | for entry in self._rich_entries(renderer): | |
3246 | yield entry | |
3247 | continuation_list[0] = self._extract_continuation(parent_renderer) | |
8bdd16b4 | 3248 | continue |
3462ffa8 | 3249 | isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or [] |
3250 | for isr_content in isr_contents: | |
3251 | if not isinstance(isr_content, dict): | |
3252 | continue | |
3253 | renderer = isr_content.get('playlistVideoListRenderer') | |
3254 | if renderer: | |
3255 | for entry in self._playlist_entries(renderer): | |
3256 | yield entry | |
3257 | continuation_list[0] = self._extract_continuation(renderer) | |
3258 | continue | |
3259 | renderer = isr_content.get('gridRenderer') | |
3260 | if renderer: | |
3261 | for entry in self._grid_entries(renderer): | |
3262 | yield entry | |
3263 | continuation_list[0] = self._extract_continuation(renderer) | |
3264 | continue | |
3265 | renderer = isr_content.get('shelfRenderer') | |
3266 | if renderer: | |
29f7c58a | 3267 | is_channels_tab = tab.get('title') == 'Channels' |
3268 | for entry in self._shelf_entries(renderer, not is_channels_tab): | |
3462ffa8 | 3269 | yield entry |
3462ffa8 | 3270 | continue |
3271 | renderer = isr_content.get('backstagePostThreadRenderer') | |
3272 | if renderer: | |
3273 | for entry in self._post_thread_entries(renderer): | |
3274 | yield entry | |
3275 | continuation_list[0] = self._extract_continuation(renderer) | |
3276 | continue | |
3277 | renderer = isr_content.get('videoRenderer') | |
3278 | if renderer: | |
3279 | entry = self._video_entry(renderer) | |
3280 | if entry: | |
3281 | yield entry | |
70d5c17b | 3282 | |
3462ffa8 | 3283 | if not continuation_list[0]: |
3284 | continuation_list[0] = self._extract_continuation(is_renderer) | |
70d5c17b | 3285 | |
3286 | if not continuation_list[0]: | |
3287 | continuation_list[0] = self._extract_continuation(parent_renderer) | |
3462ffa8 | 3288 | |
3289 | continuation_list = [None] # Python 2 doesnot support nonlocal | |
29f7c58a | 3290 | tab_content = try_get(tab, lambda x: x['content'], dict) |
3291 | if not tab_content: | |
3292 | return | |
3462ffa8 | 3293 | parent_renderer = ( |
29f7c58a | 3294 | try_get(tab_content, lambda x: x['sectionListRenderer'], dict) |
3295 | or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {}) | |
70d5c17b | 3296 | for entry in extract_entries(parent_renderer): |
3297 | yield entry | |
3462ffa8 | 3298 | continuation = continuation_list[0] |
8bdd16b4 | 3299 | |
3300 | headers = { | |
3301 | 'x-youtube-client-name': '1', | |
3302 | 'x-youtube-client-version': '2.20201112.04.01', | |
3303 | } | |
3304 | if identity_token: | |
3305 | headers['x-youtube-identity-token'] = identity_token | |
ebf1b291 | 3306 | |
8bdd16b4 | 3307 | for page_num in itertools.count(1): |
3308 | if not continuation: | |
3309 | break | |
29f7c58a | 3310 | count = 0 |
3311 | retries = 3 | |
3312 | while count <= retries: | |
3313 | try: | |
3314 | # Downloading page may result in intermittent 5xx HTTP error | |
3315 | # that is usually worked around with a retry | |
3316 | browse = self._download_json( | |
3317 | 'https://www.youtube.com/browse_ajax', None, | |
3318 | 'Downloading page %d%s' | |
3319 | % (page_num, ' (retry #%d)' % count if count else ''), | |
3320 | headers=headers, query=continuation) | |
3321 | break | |
3322 | except ExtractorError as e: | |
3323 | if isinstance(e.cause, compat_HTTPError) and e.cause.code in (500, 503): | |
3324 | count += 1 | |
3325 | if count <= retries: | |
3326 | continue | |
3327 | raise | |
8bdd16b4 | 3328 | if not browse: |
3329 | break | |
3330 | response = try_get(browse, lambda x: x[1]['response'], dict) | |
3331 | if not response: | |
3332 | break | |
ebf1b291 | 3333 | |
8bdd16b4 | 3334 | continuation_contents = try_get( |
3335 | response, lambda x: x['continuationContents'], dict) | |
3336 | if continuation_contents: | |
3337 | continuation_renderer = continuation_contents.get('playlistVideoListContinuation') | |
3338 | if continuation_renderer: | |
3339 | for entry in self._playlist_entries(continuation_renderer): | |
3340 | yield entry | |
3341 | continuation = self._extract_continuation(continuation_renderer) | |
3342 | continue | |
3343 | continuation_renderer = continuation_contents.get('gridContinuation') | |
3344 | if continuation_renderer: | |
3345 | for entry in self._grid_entries(continuation_renderer): | |
3346 | yield entry | |
3347 | continuation = self._extract_continuation(continuation_renderer) | |
3348 | continue | |
3349 | continuation_renderer = continuation_contents.get('itemSectionContinuation') | |
3350 | if continuation_renderer: | |
3351 | for entry in self._post_thread_continuation_entries(continuation_renderer): | |
3352 | yield entry | |
3353 | continuation = self._extract_continuation(continuation_renderer) | |
3354 | continue | |
70d5c17b | 3355 | continuation_renderer = continuation_contents.get('sectionListContinuation') # for feeds |
3462ffa8 | 3356 | if continuation_renderer: |
3357 | continuation_list = [None] | |
3358 | for entry in extract_entries(continuation_renderer): | |
3359 | yield entry | |
3360 | continuation = continuation_list[0] | |
3361 | continue | |
c5e8d7af | 3362 | |
8bdd16b4 | 3363 | continuation_items = try_get( |
3364 | response, lambda x: x['onResponseReceivedActions'][0]['appendContinuationItemsAction']['continuationItems'], list) | |
3365 | if continuation_items: | |
3366 | continuation_item = continuation_items[0] | |
3367 | if not isinstance(continuation_item, dict): | |
3368 | continue | |
70d5c17b | 3369 | renderer = continuation_item.get('playlistVideoRenderer') or continuation_item.get('itemSectionRenderer') |
8bdd16b4 | 3370 | if renderer: |
3371 | video_list_renderer = {'contents': continuation_items} | |
3372 | for entry in self._playlist_entries(video_list_renderer): | |
3373 | yield entry | |
3374 | continuation = self._extract_continuation(video_list_renderer) | |
3375 | continue | |
8bdd16b4 | 3376 | break |
9558dcec | 3377 | |
8bdd16b4 | 3378 | @staticmethod |
3379 | def _extract_selected_tab(tabs): | |
3380 | for tab in tabs: | |
3381 | if try_get(tab, lambda x: x['tabRenderer']['selected'], bool): | |
3382 | return tab['tabRenderer'] | |
2b3c2546 | 3383 | else: |
8bdd16b4 | 3384 | raise ExtractorError('Unable to find selected tab') |
b82f815f | 3385 | |
8bdd16b4 | 3386 | @staticmethod |
3387 | def _extract_uploader(data): | |
3388 | uploader = {} | |
3389 | sidebar_renderer = try_get( | |
3390 | data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) | |
3391 | if sidebar_renderer: | |
3392 | for item in sidebar_renderer: | |
3393 | if not isinstance(item, dict): | |
3394 | continue | |
3395 | renderer = item.get('playlistSidebarSecondaryInfoRenderer') | |
3396 | if not isinstance(renderer, dict): | |
3397 | continue | |
3398 | owner = try_get( | |
3399 | renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict) | |
3400 | if owner: | |
3401 | uploader['uploader'] = owner.get('text') | |
3402 | uploader['uploader_id'] = try_get( | |
3403 | owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str) | |
3404 | uploader['uploader_url'] = urljoin( | |
3405 | 'https://www.youtube.com/', | |
3406 | try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str)) | |
9c3fe2ef | 3407 | return {k: v for k, v in uploader.items() if v is not None} |
8bdd16b4 | 3408 | |
3409 | def _extract_from_tabs(self, item_id, webpage, data, tabs, identity_token): | |
b60419c5 | 3410 | playlist_id = title = description = channel_url = channel_name = channel_id = None |
3411 | thumbnails_list = tags = [] | |
3412 | ||
8bdd16b4 | 3413 | selected_tab = self._extract_selected_tab(tabs) |
3414 | renderer = try_get( | |
3415 | data, lambda x: x['metadata']['channelMetadataRenderer'], dict) | |
3416 | if renderer: | |
b60419c5 | 3417 | channel_name = renderer.get('title') |
3418 | channel_url = renderer.get('channelUrl') | |
3419 | channel_id = renderer.get('externalId') | |
64c0d954 | 3420 | |
64c0d954 | 3421 | if not renderer: |
3422 | renderer = try_get( | |
3423 | data, lambda x: x['metadata']['playlistMetadataRenderer'], dict) | |
8bdd16b4 | 3424 | if renderer: |
3425 | title = renderer.get('title') | |
64c0d954 | 3426 | description = renderer.get('description') |
b60419c5 | 3427 | playlist_id = channel_id |
3428 | tags = renderer.get('keywords', '').split() | |
3429 | thumbnails_list = ( | |
3430 | try_get(renderer, lambda x: x['avatar']['thumbnails'], list) | |
3431 | or data['sidebar']['playlistSidebarRenderer']['items'][0]['playlistSidebarPrimaryInfoRenderer']['thumbnailRenderer']['playlistVideoThumbnailRenderer']['thumbnail']['thumbnails'] | |
3432 | or []) | |
3433 | ||
3434 | thumbnails = [] | |
3435 | for t in thumbnails_list: | |
3436 | if not isinstance(t, dict): | |
3437 | continue | |
3438 | thumbnail_url = url_or_none(t.get('url')) | |
3439 | if not thumbnail_url: | |
3440 | continue | |
3441 | thumbnails.append({ | |
3442 | 'url': thumbnail_url, | |
3443 | 'width': int_or_none(t.get('width')), | |
3444 | 'height': int_or_none(t.get('height')), | |
3445 | }) | |
64c0d954 | 3446 | |
3462ffa8 | 3447 | if playlist_id is None: |
70d5c17b | 3448 | playlist_id = item_id |
3449 | if title is None: | |
b60419c5 | 3450 | title = playlist_id |
3451 | title += format_field(selected_tab, 'title', ' - %s') | |
3452 | ||
3453 | metadata = { | |
3454 | 'playlist_id': playlist_id, | |
3455 | 'playlist_title': title, | |
3456 | 'playlist_description': description, | |
3457 | 'uploader': channel_name, | |
3458 | 'uploader_id': channel_id, | |
3459 | 'uploader_url': channel_url, | |
3460 | 'thumbnails': thumbnails, | |
3461 | 'tags': tags, | |
3462 | } | |
3463 | if not channel_id: | |
3464 | metadata.update(self._extract_uploader(data)) | |
3465 | metadata.update({ | |
3466 | 'channel': metadata['uploader'], | |
3467 | 'channel_id': metadata['uploader_id'], | |
3468 | 'channel_url': metadata['uploader_url']}) | |
3469 | return self.playlist_result( | |
29f7c58a | 3470 | self._entries(selected_tab, identity_token), |
b60419c5 | 3471 | **metadata) |
73c4ac2c | 3472 | |
29f7c58a | 3473 | def _extract_from_playlist(self, item_id, url, data, playlist): |
8bdd16b4 | 3474 | title = playlist.get('title') or try_get( |
3475 | data, lambda x: x['titleText']['simpleText'], compat_str) | |
3476 | playlist_id = playlist.get('playlistId') or item_id | |
29f7c58a | 3477 | # Inline playlist rendition continuation does not always work |
3478 | # at Youtube side, so delegating regular tab-based playlist URL | |
3479 | # processing whenever possible. | |
3480 | playlist_url = urljoin(url, try_get( | |
3481 | playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'], | |
3482 | compat_str)) | |
3483 | if playlist_url and playlist_url != url: | |
3484 | return self.url_result( | |
3485 | playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id, | |
3486 | video_title=title) | |
8bdd16b4 | 3487 | return self.playlist_result( |
3488 | self._playlist_entries(playlist), playlist_id=playlist_id, | |
3489 | playlist_title=title) | |
c5e8d7af | 3490 | |
29f7c58a | 3491 | @staticmethod |
3492 | def _extract_alerts(data): | |
02ced43c | 3493 | for alert_dict in try_get(data, lambda x: x['alerts'], list) or []: |
29f7c58a | 3494 | if not isinstance(alert_dict, dict): |
3495 | continue | |
02ced43c | 3496 | for renderer in alert_dict: |
3497 | alert = alert_dict[renderer] | |
3498 | alert_type = alert.get('type') | |
3499 | if not alert_type: | |
3500 | continue | |
3501 | message = try_get(alert, lambda x: x['text']['simpleText'], compat_str) | |
3502 | if message: | |
3503 | yield alert_type, message | |
3504 | for run in try_get(alert, lambda x: x['text']['runs'], list) or []: | |
3505 | message = try_get(run, lambda x: x['text'], compat_str) | |
3506 | if message: | |
3507 | yield alert_type, message | |
3508 | ||
29f7c58a | 3509 | def _extract_identity_token(self, webpage, item_id): |
3510 | ytcfg = self._extract_ytcfg(item_id, webpage) | |
3511 | if ytcfg: | |
3512 | token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str) | |
3513 | if token: | |
3514 | return token | |
3515 | return self._search_regex( | |
3516 | r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage, | |
3517 | 'identity token', default=None) | |
3518 | ||
8bdd16b4 | 3519 | def _real_extract(self, url): |
3520 | item_id = self._match_id(url) | |
3521 | url = compat_urlparse.urlunparse( | |
3522 | compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com')) | |
036fcf3a | 3523 | is_home = re.match(r'(?P<pre>%s)(?P<post>/?(?![^#?]).*$)' % self._VALID_URL, url) |
70d5c17b | 3524 | if is_home is not None and is_home.group('not_channel') is None and item_id != 'feed': |
036fcf3a | 3525 | self._downloader.report_warning( |
3526 | 'A channel/user page was given. All the channel\'s videos will be downloaded. ' | |
c76eb41b | 3527 | 'To download only the videos in the home page, add a "/featured" to the URL') |
036fcf3a | 3528 | url = '%s/videos%s' % (is_home.group('pre'), is_home.group('post') or '') |
3529 | ||
8bdd16b4 | 3530 | # Handle both video/playlist URLs |
3531 | qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) | |
3532 | video_id = qs.get('v', [None])[0] | |
3533 | playlist_id = qs.get('list', [None])[0] | |
f0c532a4 | 3534 | |
29f7c58a | 3535 | 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: |
f0c532a4 | 3536 | if playlist_id: |
3537 | self._downloader.report_warning('%s is not a valid Youtube URL. Trying to download playlist %s' % (url, playlist_id)) | |
3538 | url = 'https://www.youtube.com/playlist?list=%s' % playlist_id | |
3539 | # return self.url_result(playlist_id, ie=YoutubePlaylistIE.ie_key()) | |
3540 | else: | |
3541 | raise ExtractorError('Unable to recognize tab page') | |
8bdd16b4 | 3542 | if video_id and playlist_id: |
3543 | if self._downloader.params.get('noplaylist'): | |
3544 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
3545 | return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id) | |
3546 | self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) | |
2fa90513 | 3547 | |
8bdd16b4 | 3548 | webpage = self._download_webpage(url, item_id) |
29f7c58a | 3549 | identity_token = self._extract_identity_token(webpage, item_id) |
8bdd16b4 | 3550 | data = self._extract_yt_initial_data(item_id, webpage) |
6b8eb0c0 | 3551 | err_msg = None |
02ced43c | 3552 | for alert_type, alert_message in self._extract_alerts(data): |
6b8eb0c0 | 3553 | if alert_type.lower() == 'error': |
3554 | if err_msg: | |
3555 | self._downloader.report_warning('YouTube said: %s - %s' % ('ERROR', err_msg)) | |
3556 | err_msg = alert_message | |
3557 | else: | |
3558 | self._downloader.report_warning('YouTube said: %s - %s' % (alert_type, alert_message)) | |
3559 | if err_msg: | |
3560 | raise ExtractorError('YouTube said: %s' % err_msg, expected=True) | |
8bdd16b4 | 3561 | tabs = try_get( |
3562 | data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list) | |
3563 | if tabs: | |
3564 | return self._extract_from_tabs(item_id, webpage, data, tabs, identity_token) | |
3565 | playlist = try_get( | |
3566 | data, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict) | |
3567 | if playlist: | |
29f7c58a | 3568 | return self._extract_from_playlist(item_id, url, data, playlist) |
a0566bbf | 3569 | # Fallback to video extraction if no playlist alike page is recognized. |
3570 | # First check for the current video then try the v attribute of URL query. | |
3571 | video_id = try_get( | |
3572 | data, lambda x: x['currentVideoEndpoint']['watchEndpoint']['videoId'], | |
3573 | compat_str) or video_id | |
8bdd16b4 | 3574 | if video_id: |
3575 | return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id) | |
3576 | # Failed to recognize | |
3577 | raise ExtractorError('Unable to recognize tab page') | |
c5e8d7af | 3578 | |
c5e8d7af | 3579 | |
8bdd16b4 | 3580 | class YoutubePlaylistIE(InfoExtractor): |
3581 | IE_DESC = 'YouTube.com playlists' | |
3582 | _VALID_URL = r'''(?x)(?: | |
3583 | (?:https?://)? | |
3584 | (?:\w+\.)? | |
3585 | (?: | |
3586 | (?: | |
3587 | youtube(?:kids)?\.com| | |
29f7c58a | 3588 | invidio\.us |
8bdd16b4 | 3589 | ) |
3590 | /.*?\?.*?\blist= | |
3591 | )? | |
3592 | (?P<id>%(playlist_id)s) | |
3593 | )''' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE} | |
3594 | IE_NAME = 'youtube:playlist' | |
cdc628a4 | 3595 | _TESTS = [{ |
8bdd16b4 | 3596 | 'note': 'issue #673', |
3597 | 'url': 'PLBB231211A4F62143', | |
cdc628a4 | 3598 | 'info_dict': { |
8bdd16b4 | 3599 | 'title': '[OLD]Team Fortress 2 (Class-based LP)', |
3600 | 'id': 'PLBB231211A4F62143', | |
3601 | 'uploader': 'Wickydoo', | |
3602 | 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q', | |
3603 | }, | |
3604 | 'playlist_mincount': 29, | |
3605 | }, { | |
3606 | 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
3607 | 'info_dict': { | |
3608 | 'title': 'YDL_safe_search', | |
3609 | 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
3610 | }, | |
3611 | 'playlist_count': 2, | |
3612 | 'skip': 'This playlist is private', | |
9558dcec | 3613 | }, { |
8bdd16b4 | 3614 | 'note': 'embedded', |
3615 | 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', | |
3616 | 'playlist_count': 4, | |
9558dcec | 3617 | 'info_dict': { |
8bdd16b4 | 3618 | 'title': 'JODA15', |
3619 | 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', | |
3620 | 'uploader': 'milan', | |
3621 | 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw', | |
9558dcec | 3622 | } |
cdc628a4 | 3623 | }, { |
8bdd16b4 | 3624 | 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', |
3625 | 'playlist_mincount': 982, | |
3626 | 'info_dict': { | |
3627 | 'title': '2018 Chinese New Singles (11/6 updated)', | |
3628 | 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', | |
3629 | 'uploader': 'LBK', | |
3630 | 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA', | |
3631 | } | |
daa0df9e | 3632 | }, { |
29f7c58a | 3633 | 'url': 'TLGGrESM50VT6acwMjAyMjAxNw', |
3634 | 'only_matching': True, | |
3635 | }, { | |
3636 | # music album playlist | |
3637 | 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM', | |
3638 | 'only_matching': True, | |
3639 | }] | |
3640 | ||
3641 | @classmethod | |
3642 | def suitable(cls, url): | |
3643 | return False if YoutubeTabIE.suitable(url) else super( | |
3644 | YoutubePlaylistIE, cls).suitable(url) | |
3645 | ||
3646 | def _real_extract(self, url): | |
3647 | playlist_id = self._match_id(url) | |
3648 | qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) | |
3649 | if not qs: | |
3650 | qs = {'list': playlist_id} | |
3651 | return self.url_result( | |
3652 | update_url_query('https://www.youtube.com/playlist', qs), | |
3653 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
3654 | ||
3655 | ||
3656 | class YoutubeYtBeIE(InfoExtractor): | |
c76eb41b | 3657 | IE_DESC = 'youtu.be' |
29f7c58a | 3658 | _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} |
3659 | _TESTS = [{ | |
8bdd16b4 | 3660 | 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5', |
3661 | 'info_dict': { | |
3662 | 'id': 'yeWKywCrFtk', | |
3663 | 'ext': 'mp4', | |
3664 | 'title': 'Small Scale Baler and Braiding Rugs', | |
3665 | 'uploader': 'Backus-Page House Museum', | |
3666 | 'uploader_id': 'backuspagemuseum', | |
3667 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum', | |
3668 | 'upload_date': '20161008', | |
3669 | 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a', | |
3670 | 'categories': ['Nonprofits & Activism'], | |
3671 | 'tags': list, | |
3672 | 'like_count': int, | |
3673 | 'dislike_count': int, | |
3674 | }, | |
3675 | 'params': { | |
3676 | 'noplaylist': True, | |
3677 | 'skip_download': True, | |
3678 | }, | |
39e7107d | 3679 | }, { |
8bdd16b4 | 3680 | 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21', |
39e7107d | 3681 | 'only_matching': True, |
cdc628a4 PH |
3682 | }] |
3683 | ||
8bdd16b4 | 3684 | def _real_extract(self, url): |
29f7c58a | 3685 | mobj = re.match(self._VALID_URL, url) |
3686 | video_id = mobj.group('id') | |
3687 | playlist_id = mobj.group('playlist_id') | |
8bdd16b4 | 3688 | return self.url_result( |
29f7c58a | 3689 | update_url_query('https://www.youtube.com/watch', { |
3690 | 'v': video_id, | |
3691 | 'list': playlist_id, | |
3692 | 'feature': 'youtu.be', | |
3693 | }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
8bdd16b4 | 3694 | |
3695 | ||
3696 | class YoutubeYtUserIE(InfoExtractor): | |
c76eb41b | 3697 | IE_DESC = 'YouTube.com user videos, URL or "ytuser" keyword' |
8bdd16b4 | 3698 | _VALID_URL = r'ytuser:(?P<id>.+)' |
3699 | _TESTS = [{ | |
3700 | 'url': 'ytuser:phihag', | |
3701 | 'only_matching': True, | |
3702 | }] | |
3703 | ||
3704 | def _real_extract(self, url): | |
3705 | user_id = self._match_id(url) | |
3706 | return self.url_result( | |
3707 | 'https://www.youtube.com/user/%s' % user_id, | |
3708 | ie=YoutubeTabIE.ie_key(), video_id=user_id) | |
9558dcec | 3709 | |
b05654f0 | 3710 | |
3d3dddc9 | 3711 | class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): |
70d5c17b | 3712 | IE_NAME = 'youtube:favorites' |
3713 | IE_DESC = 'YouTube.com liked videos, ":ytfav" for short (requires authentication)' | |
3714 | _VALID_URL = r':ytfav(?:ou?rite)?s?' | |
3715 | _LOGIN_REQUIRED = True | |
3716 | _TESTS = [{ | |
3717 | 'url': ':ytfav', | |
3718 | 'only_matching': True, | |
3719 | }, { | |
3720 | 'url': ':ytfavorites', | |
3721 | 'only_matching': True, | |
3722 | }] | |
3723 | ||
3724 | def _real_extract(self, url): | |
3725 | return self.url_result( | |
3726 | 'https://www.youtube.com/playlist?list=LL', | |
3727 | ie=YoutubeTabIE.ie_key()) | |
3728 | ||
3729 | ||
8bdd16b4 | 3730 | class YoutubeSearchIE(SearchInfoExtractor, YoutubeBaseInfoExtractor): |
78caa52a | 3731 | IE_DESC = 'YouTube.com searches' |
b4c08069 JMF |
3732 | # there doesn't appear to be a real limit, for example if you search for |
3733 | # 'python' you get more than 8.000.000 results | |
3734 | _MAX_RESULTS = float('inf') | |
78caa52a | 3735 | IE_NAME = 'youtube:search' |
b05654f0 | 3736 | _SEARCH_KEY = 'ytsearch' |
6c894ea1 | 3737 | _SEARCH_PARAMS = None |
9dd8e46a | 3738 | _TESTS = [] |
b05654f0 | 3739 | |
6c894ea1 U |
3740 | def _entries(self, query, n): |
3741 | data = { | |
3742 | 'context': { | |
3743 | 'client': { | |
3744 | 'clientName': 'WEB', | |
3745 | 'clientVersion': '2.20201021.03.00', | |
3746 | } | |
3747 | }, | |
3748 | 'query': query, | |
a22b2fd1 | 3749 | } |
6c894ea1 U |
3750 | if self._SEARCH_PARAMS: |
3751 | data['params'] = self._SEARCH_PARAMS | |
3752 | total = 0 | |
3753 | for page_num in itertools.count(1): | |
3754 | search = self._download_json( | |
3755 | 'https://www.youtube.com/youtubei/v1/search?key=AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', | |
3756 | video_id='query "%s"' % query, | |
3757 | note='Downloading page %s' % page_num, | |
3758 | errnote='Unable to download API page', fatal=False, | |
3759 | data=json.dumps(data).encode('utf8'), | |
3760 | headers={'content-type': 'application/json'}) | |
3761 | if not search: | |
b4c08069 | 3762 | break |
6c894ea1 U |
3763 | slr_contents = try_get( |
3764 | search, | |
3765 | (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'], | |
3766 | lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']), | |
3767 | list) | |
3768 | if not slr_contents: | |
a22b2fd1 | 3769 | break |
0366ae87 | 3770 | |
0366ae87 M |
3771 | # Youtube sometimes adds promoted content to searches, |
3772 | # changing the index location of videos and token. | |
3773 | # So we search through all entries till we find them. | |
30a074c2 | 3774 | continuation_token = None |
3775 | for slr_content in slr_contents: | |
3776 | isr_contents = try_get( | |
3777 | slr_content, | |
3778 | lambda x: x['itemSectionRenderer']['contents'], | |
3779 | list) | |
9da76d30 | 3780 | if not isr_contents: |
30a074c2 | 3781 | continue |
3782 | for content in isr_contents: | |
3783 | if not isinstance(content, dict): | |
3784 | continue | |
3785 | video = content.get('videoRenderer') | |
3786 | if not isinstance(video, dict): | |
3787 | continue | |
3788 | video_id = video.get('videoId') | |
3789 | if not video_id: | |
3790 | continue | |
3791 | ||
3792 | yield self._extract_video(video) | |
3793 | total += 1 | |
3794 | if total == n: | |
3795 | return | |
0366ae87 M |
3796 | |
3797 | if continuation_token is None: | |
3798 | continuation_token = try_get( | |
30a074c2 | 3799 | slr_content, |
3800 | lambda x: x['continuationItemRenderer']['continuationEndpoint']['continuationCommand']['token'], | |
0366ae87 | 3801 | compat_str) |
0366ae87 | 3802 | |
0366ae87 | 3803 | if not continuation_token: |
6c894ea1 | 3804 | break |
0366ae87 | 3805 | data['continuation'] = continuation_token |
b05654f0 | 3806 | |
6c894ea1 U |
3807 | def _get_n_results(self, query, n): |
3808 | """Get a specified number of results for a query""" | |
3809 | return self.playlist_result(self._entries(query, n), query) | |
75dff0ee | 3810 | |
c9ae7b95 | 3811 | |
a3dd9248 | 3812 | class YoutubeSearchDateIE(YoutubeSearchIE): |
cb7fb546 | 3813 | IE_NAME = YoutubeSearchIE.IE_NAME + ':date' |
a3dd9248 | 3814 | _SEARCH_KEY = 'ytsearchdate' |
c76eb41b | 3815 | IE_DESC = 'YouTube.com searches, newest videos first, "ytsearchdate" keyword' |
6c894ea1 | 3816 | _SEARCH_PARAMS = 'CAI%3D' |
75dff0ee | 3817 | |
c9ae7b95 | 3818 | |
386e1dd9 | 3819 | class YoutubeSearchURLIE(YoutubeSearchIE): |
c76eb41b | 3820 | IE_DESC = 'YouTube.com searches, "ytsearch" keyword' |
386e1dd9 | 3821 | IE_NAME = YoutubeSearchIE.IE_NAME + '_url' |
3822 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)' | |
ef2f3c7f | 3823 | # _MAX_RESULTS = 100 |
3462ffa8 | 3824 | _TESTS = [{ |
3825 | 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', | |
3826 | 'playlist_mincount': 5, | |
3827 | 'info_dict': { | |
3828 | 'title': 'youtube-dl test video', | |
3829 | } | |
3830 | }, { | |
3831 | 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB', | |
3832 | 'only_matching': True, | |
3833 | }] | |
3834 | ||
386e1dd9 | 3835 | @classmethod |
3836 | def _make_valid_url(cls): | |
3837 | return cls._VALID_URL | |
3838 | ||
3462ffa8 | 3839 | def _real_extract(self, url): |
386e1dd9 | 3840 | qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query) |
3841 | query = (qs.get('search_query') or qs.get('q'))[0] | |
3842 | self._SEARCH_PARAMS = qs.get('sp', ('',))[0] | |
3843 | return self._get_n_results(query, self._MAX_RESULTS) | |
3462ffa8 | 3844 | |
3845 | ||
3846 | class YoutubeFeedsInfoExtractor(YoutubeTabIE): | |
d7ae0639 | 3847 | """ |
25f14e9f | 3848 | Base class for feed extractors |
3d3dddc9 | 3849 | Subclasses must define the _FEED_NAME property. |
d7ae0639 | 3850 | """ |
b2e8bc1b | 3851 | _LOGIN_REQUIRED = True |
3462ffa8 | 3852 | # _MAX_PAGES = 5 |
ef2f3c7f | 3853 | _TESTS = [] |
d7ae0639 JMF |
3854 | |
3855 | @property | |
3856 | def IE_NAME(self): | |
78caa52a | 3857 | return 'youtube:%s' % self._FEED_NAME |
04cc9617 | 3858 | |
81f0259b | 3859 | def _real_initialize(self): |
b2e8bc1b | 3860 | self._login() |
81f0259b | 3861 | |
3853309f | 3862 | def _real_extract(self, url): |
3d3dddc9 | 3863 | return self.url_result( |
3864 | 'https://www.youtube.com/feed/%s' % self._FEED_NAME, | |
3865 | ie=YoutubeTabIE.ie_key()) | |
25f14e9f S |
3866 | |
3867 | ||
ef2f3c7f | 3868 | class YoutubeWatchLaterIE(InfoExtractor): |
3869 | IE_NAME = 'youtube:watchlater' | |
70d5c17b | 3870 | IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)' |
3d3dddc9 | 3871 | _VALID_URL = r':ytwatchlater' |
bc7a9cd8 | 3872 | _TESTS = [{ |
8bdd16b4 | 3873 | 'url': ':ytwatchlater', |
bc7a9cd8 S |
3874 | 'only_matching': True, |
3875 | }] | |
25f14e9f S |
3876 | |
3877 | def _real_extract(self, url): | |
ef2f3c7f | 3878 | return self.url_result( |
3879 | 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key()) | |
3462ffa8 | 3880 | |
3881 | ||
25f14e9f S |
3882 | class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): |
3883 | IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)' | |
3d3dddc9 | 3884 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?' |
25f14e9f | 3885 | _FEED_NAME = 'recommended' |
3d3dddc9 | 3886 | _TESTS = [{ |
3887 | 'url': ':ytrec', | |
3888 | 'only_matching': True, | |
3889 | }, { | |
3890 | 'url': ':ytrecommended', | |
3891 | 'only_matching': True, | |
3892 | }, { | |
3893 | 'url': 'https://youtube.com', | |
3894 | 'only_matching': True, | |
3895 | }] | |
1ed5b5c9 | 3896 | |
1ed5b5c9 | 3897 | |
25f14e9f | 3898 | class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): |
70d5c17b | 3899 | IE_DESC = 'YouTube.com subscriptions feed, ":ytsubs" for short (requires authentication)' |
3d3dddc9 | 3900 | _VALID_URL = r':ytsub(?:scription)?s?' |
25f14e9f | 3901 | _FEED_NAME = 'subscriptions' |
3d3dddc9 | 3902 | _TESTS = [{ |
3903 | 'url': ':ytsubs', | |
3904 | 'only_matching': True, | |
3905 | }, { | |
3906 | 'url': ':ytsubscriptions', | |
3907 | 'only_matching': True, | |
3908 | }] | |
1ed5b5c9 | 3909 | |
1ed5b5c9 | 3910 | |
25f14e9f S |
3911 | class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): |
3912 | IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)' | |
3d3dddc9 | 3913 | _VALID_URL = r':ythistory' |
25f14e9f | 3914 | _FEED_NAME = 'history' |
3d3dddc9 | 3915 | _TESTS = [{ |
3916 | 'url': ':ythistory', | |
3917 | 'only_matching': True, | |
3918 | }] | |
1ed5b5c9 JMF |
3919 | |
3920 | ||
15870e90 PH |
3921 | class YoutubeTruncatedURLIE(InfoExtractor): |
3922 | IE_NAME = 'youtube:truncated_url' | |
3923 | IE_DESC = False # Do not list | |
975d35db | 3924 | _VALID_URL = r'''(?x) |
b95aab84 PH |
3925 | (?:https?://)? |
3926 | (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/ | |
3927 | (?:watch\?(?: | |
c4808c60 | 3928 | feature=[a-z_]+| |
b95aab84 PH |
3929 | annotation_id=annotation_[^&]+| |
3930 | x-yt-cl=[0-9]+| | |
c1708b89 | 3931 | hl=[^&]*| |
287be8c6 | 3932 | t=[0-9]+ |
b95aab84 PH |
3933 | )? |
3934 | | | |
3935 | attribution_link\?a=[^&]+ | |
3936 | ) | |
3937 | $ | |
975d35db | 3938 | ''' |
15870e90 | 3939 | |
c4808c60 | 3940 | _TESTS = [{ |
2d3d2997 | 3941 | 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041', |
c4808c60 | 3942 | 'only_matching': True, |
dc2fc736 | 3943 | }, { |
2d3d2997 | 3944 | 'url': 'https://www.youtube.com/watch?', |
dc2fc736 | 3945 | 'only_matching': True, |
b95aab84 PH |
3946 | }, { |
3947 | 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534', | |
3948 | 'only_matching': True, | |
3949 | }, { | |
3950 | 'url': 'https://www.youtube.com/watch?feature=foo', | |
3951 | 'only_matching': True, | |
c1708b89 PH |
3952 | }, { |
3953 | 'url': 'https://www.youtube.com/watch?hl=en-GB', | |
3954 | 'only_matching': True, | |
287be8c6 PH |
3955 | }, { |
3956 | 'url': 'https://www.youtube.com/watch?t=2372', | |
3957 | 'only_matching': True, | |
c4808c60 PH |
3958 | }] |
3959 | ||
15870e90 PH |
3960 | def _real_extract(self, url): |
3961 | raise ExtractorError( | |
78caa52a PH |
3962 | 'Did you forget to quote the URL? Remember that & is a meta ' |
3963 | 'character in most shells, so you want to put the URL in quotes, ' | |
3867038a | 3964 | 'like youtube-dl ' |
2d3d2997 | 3965 | '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' |
3867038a | 3966 | ' or simply youtube-dl BaW_jenozKc .', |
15870e90 | 3967 | expected=True) |
772fd5cc PH |
3968 | |
3969 | ||
3970 | class YoutubeTruncatedIDIE(InfoExtractor): | |
3971 | IE_NAME = 'youtube:truncated_id' | |
3972 | IE_DESC = False # Do not list | |
b95aab84 | 3973 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$' |
772fd5cc PH |
3974 | |
3975 | _TESTS = [{ | |
3976 | 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob', | |
3977 | 'only_matching': True, | |
3978 | }] | |
3979 | ||
3980 | def _real_extract(self, url): | |
3981 | video_id = self._match_id(url) | |
3982 | raise ExtractorError( | |
3983 | 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url), | |
3984 | expected=True) | |
8bdd16b4 | 3985 | |
3986 | ||
3462ffa8 | 3987 | # Do Youtube show urls even exist anymore? I couldn't find any |
3988 | r''' | |
3989 | class YoutubeShowIE(YoutubeTabIE): | |
8bdd16b4 | 3990 | IE_DESC = 'YouTube.com (multi-season) shows' |
3991 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)' | |
3992 | IE_NAME = 'youtube:show' | |
3993 | _TESTS = [{ | |
3994 | 'url': 'https://www.youtube.com/show/airdisasters', | |
3995 | 'playlist_mincount': 5, | |
3996 | 'info_dict': { | |
3997 | 'id': 'airdisasters', | |
3998 | 'title': 'Air Disasters', | |
3999 | } | |
4000 | }] | |
4001 | ||
4002 | def _real_extract(self, url): | |
4003 | playlist_id = self._match_id(url) | |
4004 | return super(YoutubeShowIE, self)._real_extract( | |
4005 | 'https://www.youtube.com/show/%s/playlists' % playlist_id) | |
3462ffa8 | 4006 | ''' |