]>
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, |
f8c55c66 | 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, |
351f37c0 | 33 | extract_attributes, |
c5e8d7af | 34 | ExtractorError, |
2d30521a | 35 | float_or_none, |
4bb4a188 PH |
36 | get_element_by_attribute, |
37 | get_element_by_id, | |
dd27fd17 | 38 | int_or_none, |
94278f72 | 39 | mimetype2ext, |
4bb4a188 | 40 | orderedSet, |
6310acf5 | 41 | parse_codecs, |
7c80519c | 42 | parse_duration, |
0cb58b02 | 43 | remove_quotes, |
3995d37d | 44 | remove_start, |
cf7e015f | 45 | smuggle_url, |
dbdaaa23 | 46 | str_or_none, |
c93d53f5 | 47 | str_to_int, |
556dbe7f | 48 | try_get, |
c5e8d7af PH |
49 | unescapeHTML, |
50 | unified_strdate, | |
cf7e015f | 51 | unsmuggle_url, |
81c2f20b | 52 | uppercase_escape, |
21c340b8 | 53 | url_or_none, |
6e6bc8da | 54 | urlencode_postdata, |
c5e8d7af PH |
55 | ) |
56 | ||
5f6a1245 | 57 | |
de7f3446 | 58 | class YoutubeBaseInfoExtractor(InfoExtractor): |
b2e8bc1b JMF |
59 | """Provide base functions for Youtube extractors""" |
60 | _LOGIN_URL = 'https://accounts.google.com/ServiceLogin' | |
9303ce3e | 61 | _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge' |
e00eb564 S |
62 | |
63 | _LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup' | |
3995d37d S |
64 | _CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge' |
65 | _TFA_URL = 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}' | |
e00eb564 | 66 | |
b2e8bc1b JMF |
67 | _NETRC_MACHINE = 'youtube' |
68 | # If True it will raise an error if no login info is provided | |
69 | _LOGIN_REQUIRED = False | |
70 | ||
66b48727 | 71 | _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}' |
d0ba5587 | 72 | |
d84b21b4 S |
73 | _YOUTUBE_CLIENT_HEADERS = { |
74 | 'x-youtube-client-name': '1', | |
75 | 'x-youtube-client-version': '1.20200609.04.02', | |
76 | } | |
77 | ||
b2e8bc1b | 78 | def _set_language(self): |
810fb84d | 79 | self._set_cookie( |
ee0b726c | 80 | '.youtube.com', 'PREF', 'f1=50000000&f6=8&hl=en', |
42939b61 | 81 | # YouTube sets the expire time to about two months |
810fb84d | 82 | expire_time=time.time() + 2 * 30 * 24 * 3600) |
b2e8bc1b | 83 | |
25f14e9f S |
84 | def _ids_to_results(self, ids): |
85 | return [ | |
86 | self.url_result(vid_id, 'Youtube', video_id=vid_id) | |
87 | for vid_id in ids] | |
88 | ||
b2e8bc1b | 89 | def _login(self): |
83317f69 | 90 | """ |
91 | Attempt to log in to YouTube. | |
92 | True is returned if successful or skipped. | |
93 | False is returned if login failed. | |
94 | ||
95 | If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised. | |
96 | """ | |
68217024 | 97 | username, password = self._get_login_info() |
b2e8bc1b JMF |
98 | # No authentication to be performed |
99 | if username is None: | |
70d35d16 | 100 | if self._LOGIN_REQUIRED and self._downloader.params.get('cookiefile') is None: |
69ea8ca4 | 101 | raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) |
83317f69 | 102 | return True |
b2e8bc1b | 103 | |
7cc3570e PH |
104 | login_page = self._download_webpage( |
105 | self._LOGIN_URL, None, | |
69ea8ca4 PH |
106 | note='Downloading login page', |
107 | errnote='unable to fetch login page', fatal=False) | |
7cc3570e PH |
108 | if login_page is False: |
109 | return | |
b2e8bc1b | 110 | |
1212e997 | 111 | login_form = self._hidden_inputs(login_page) |
c5e8d7af | 112 | |
e00eb564 S |
113 | def req(url, f_req, note, errnote): |
114 | data = login_form.copy() | |
115 | data.update({ | |
116 | 'pstMsg': 1, | |
117 | 'checkConnection': 'youtube', | |
118 | 'checkedDomains': 'youtube', | |
119 | 'hl': 'en', | |
120 | 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]', | |
3995d37d | 121 | 'f.req': json.dumps(f_req), |
e00eb564 S |
122 | 'flowName': 'GlifWebSignIn', |
123 | 'flowEntry': 'ServiceLogin', | |
baf67a60 S |
124 | # TODO: reverse actual botguard identifier generation algo |
125 | 'bgRequest': '["identifier",""]', | |
041bc3ad | 126 | }) |
e00eb564 S |
127 | return self._download_json( |
128 | url, None, note=note, errnote=errnote, | |
129 | transform_source=lambda s: re.sub(r'^[^[]*', '', s), | |
130 | fatal=False, | |
131 | data=urlencode_postdata(data), headers={ | |
132 | 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8', | |
133 | 'Google-Accounts-XSRF': 1, | |
134 | }) | |
135 | ||
3995d37d S |
136 | def warn(message): |
137 | self._downloader.report_warning(message) | |
138 | ||
139 | lookup_req = [ | |
140 | username, | |
141 | None, [], None, 'US', None, None, 2, False, True, | |
142 | [ | |
143 | None, None, | |
144 | [2, 1, None, 1, | |
145 | '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', | |
146 | None, [], 4], | |
147 | 1, [None, None, []], None, None, None, True | |
148 | ], | |
149 | username, | |
150 | ] | |
151 | ||
e00eb564 | 152 | lookup_results = req( |
3995d37d | 153 | self._LOOKUP_URL, lookup_req, |
e00eb564 S |
154 | 'Looking up account info', 'Unable to look up account info') |
155 | ||
156 | if lookup_results is False: | |
157 | return False | |
041bc3ad | 158 | |
3995d37d S |
159 | user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str) |
160 | if not user_hash: | |
161 | warn('Unable to extract user hash') | |
162 | return False | |
163 | ||
164 | challenge_req = [ | |
165 | user_hash, | |
166 | None, 1, None, [1, None, None, None, [password, None, True]], | |
167 | [ | |
168 | 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], | |
169 | 1, [None, None, []], None, None, None, True | |
170 | ]] | |
83317f69 | 171 | |
3995d37d S |
172 | challenge_results = req( |
173 | self._CHALLENGE_URL, challenge_req, | |
174 | 'Logging in', 'Unable to log in') | |
83317f69 | 175 | |
3995d37d | 176 | if challenge_results is False: |
e00eb564 | 177 | return |
83317f69 | 178 | |
3995d37d S |
179 | login_res = try_get(challenge_results, lambda x: x[0][5], list) |
180 | if login_res: | |
181 | login_msg = try_get(login_res, lambda x: x[5], compat_str) | |
182 | warn( | |
183 | 'Unable to login: %s' % 'Invalid password' | |
184 | if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg) | |
185 | return False | |
186 | ||
187 | res = try_get(challenge_results, lambda x: x[0][-1], list) | |
188 | if not res: | |
189 | warn('Unable to extract result entry') | |
190 | return False | |
191 | ||
9a6628aa S |
192 | login_challenge = try_get(res, lambda x: x[0][0], list) |
193 | if login_challenge: | |
194 | challenge_str = try_get(login_challenge, lambda x: x[2], compat_str) | |
195 | if challenge_str == 'TWO_STEP_VERIFICATION': | |
3995d37d S |
196 | # SEND_SUCCESS - TFA code has been successfully sent to phone |
197 | # QUOTA_EXCEEDED - reached the limit of TFA codes | |
9a6628aa | 198 | status = try_get(login_challenge, lambda x: x[5], compat_str) |
3995d37d S |
199 | if status == 'QUOTA_EXCEEDED': |
200 | warn('Exceeded the limit of TFA codes, try later') | |
201 | return False | |
202 | ||
203 | tl = try_get(challenge_results, lambda x: x[1][2], compat_str) | |
204 | if not tl: | |
205 | warn('Unable to extract TL') | |
206 | return False | |
207 | ||
208 | tfa_code = self._get_tfa_info('2-step verification code') | |
209 | ||
210 | if not tfa_code: | |
211 | warn( | |
212 | 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>' | |
213 | '(Note that only TOTP (Google Authenticator App) codes work at this time.)') | |
214 | return False | |
215 | ||
216 | tfa_code = remove_start(tfa_code, 'G-') | |
217 | ||
218 | tfa_req = [ | |
219 | user_hash, None, 2, None, | |
220 | [ | |
221 | 9, None, None, None, None, None, None, None, | |
222 | [None, tfa_code, True, 2] | |
223 | ]] | |
224 | ||
225 | tfa_results = req( | |
226 | self._TFA_URL.format(tl), tfa_req, | |
227 | 'Submitting TFA code', 'Unable to submit TFA code') | |
228 | ||
229 | if tfa_results is False: | |
230 | return False | |
231 | ||
232 | tfa_res = try_get(tfa_results, lambda x: x[0][5], list) | |
233 | if tfa_res: | |
234 | tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str) | |
235 | warn( | |
236 | 'Unable to finish TFA: %s' % 'Invalid TFA code' | |
237 | if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg) | |
238 | return False | |
239 | ||
240 | check_cookie_url = try_get( | |
241 | tfa_results, lambda x: x[0][-1][2], compat_str) | |
9a6628aa S |
242 | else: |
243 | CHALLENGES = { | |
244 | 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.", | |
245 | 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.', | |
246 | 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.", | |
247 | } | |
248 | challenge = CHALLENGES.get( | |
249 | challenge_str, | |
250 | '%s returned error %s.' % (self.IE_NAME, challenge_str)) | |
251 | warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge) | |
252 | return False | |
3995d37d S |
253 | else: |
254 | check_cookie_url = try_get(res, lambda x: x[2], compat_str) | |
255 | ||
256 | if not check_cookie_url: | |
257 | warn('Unable to extract CheckCookie URL') | |
258 | return False | |
e00eb564 S |
259 | |
260 | check_cookie_results = self._download_webpage( | |
3995d37d S |
261 | check_cookie_url, None, 'Checking cookie', fatal=False) |
262 | ||
263 | if check_cookie_results is False: | |
264 | return False | |
e00eb564 | 265 | |
3995d37d S |
266 | if 'https://myaccount.google.com/' not in check_cookie_results: |
267 | warn('Unable to log in') | |
b2e8bc1b | 268 | return False |
e00eb564 | 269 | |
b2e8bc1b JMF |
270 | return True |
271 | ||
30226342 | 272 | def _download_webpage_handle(self, *args, **kwargs): |
c1148516 S |
273 | query = kwargs.get('query', {}).copy() |
274 | query['disable_polymer'] = 'true' | |
275 | kwargs['query'] = query | |
30226342 | 276 | return super(YoutubeBaseInfoExtractor, self)._download_webpage_handle( |
8d81f3e3 S |
277 | *args, **compat_kwargs(kwargs)) |
278 | ||
b2e8bc1b JMF |
279 | def _real_initialize(self): |
280 | if self._downloader is None: | |
281 | return | |
42939b61 | 282 | self._set_language() |
b2e8bc1b JMF |
283 | if not self._login(): |
284 | return | |
c5e8d7af | 285 | |
8377574c | 286 | |
8e7aad20 | 287 | class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor): |
061a75ed | 288 | # Extract entries from page with "Load more" button |
648e6a1f S |
289 | def _entries(self, page, playlist_id): |
290 | more_widget_html = content_html = page | |
291 | for page_num in itertools.count(1): | |
061a75ed S |
292 | for entry in self._process_page(content_html): |
293 | yield entry | |
648e6a1f S |
294 | |
295 | mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) | |
296 | if not mobj: | |
297 | break | |
298 | ||
f8c55c66 S |
299 | count = 0 |
300 | retries = 3 | |
301 | while count <= retries: | |
302 | try: | |
303 | # Downloading page may result in intermittent 5xx HTTP error | |
304 | # that is usually worked around with a retry | |
305 | more = self._download_json( | |
07af16b9 | 306 | 'https://www.youtube.com/%s' % mobj.group('more'), playlist_id, |
f8c55c66 S |
307 | 'Downloading page #%s%s' |
308 | % (page_num, ' (retry #%d)' % count if count else ''), | |
d84b21b4 S |
309 | transform_source=uppercase_escape, |
310 | headers=self._YOUTUBE_CLIENT_HEADERS) | |
f8c55c66 S |
311 | break |
312 | except ExtractorError as e: | |
313 | if isinstance(e.cause, compat_HTTPError) and e.cause.code in (500, 503): | |
314 | count += 1 | |
315 | if count <= retries: | |
316 | continue | |
317 | raise | |
318 | ||
648e6a1f S |
319 | content_html = more['content_html'] |
320 | if not content_html.strip(): | |
321 | # Some webpages show a "Load more" button but they don't | |
322 | # have more videos | |
323 | break | |
324 | more_widget_html = more['load_more_widget_html'] | |
325 | ||
061a75ed S |
326 | |
327 | class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): | |
328 | def _process_page(self, content): | |
329 | for video_id, video_title in self.extract_videos_from_page(content): | |
330 | yield self.url_result(video_id, 'Youtube', video_id, video_title) | |
331 | ||
351f37c0 S |
332 | def extract_videos_from_page_impl(self, video_re, page, ids_in_page, titles_in_page): |
333 | for mobj in re.finditer(video_re, page): | |
648e6a1f S |
334 | # The link with index 0 is not the first video of the playlist (not sure if still actual) |
335 | if 'index' in mobj.groupdict() and mobj.group('id') == '0': | |
336 | continue | |
337 | video_id = mobj.group('id') | |
351f37c0 S |
338 | video_title = unescapeHTML( |
339 | mobj.group('title')) if 'title' in mobj.groupdict() else None | |
648e6a1f S |
340 | if video_title: |
341 | video_title = video_title.strip() | |
351f37c0 S |
342 | if video_title == '► Play all': |
343 | video_title = None | |
648e6a1f S |
344 | try: |
345 | idx = ids_in_page.index(video_id) | |
346 | if video_title and not titles_in_page[idx]: | |
347 | titles_in_page[idx] = video_title | |
348 | except ValueError: | |
349 | ids_in_page.append(video_id) | |
350 | titles_in_page.append(video_title) | |
351f37c0 S |
351 | |
352 | def extract_videos_from_page(self, page): | |
353 | ids_in_page = [] | |
354 | titles_in_page = [] | |
355 | self.extract_videos_from_page_impl( | |
356 | self._VIDEO_RE, page, ids_in_page, titles_in_page) | |
648e6a1f S |
357 | return zip(ids_in_page, titles_in_page) |
358 | ||
359 | ||
061a75ed S |
360 | class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): |
361 | def _process_page(self, content): | |
6dee688e S |
362 | for playlist_id in orderedSet(re.findall( |
363 | r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"', | |
364 | content)): | |
061a75ed S |
365 | yield self.url_result( |
366 | 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist') | |
367 | ||
0c148415 S |
368 | def _real_extract(self, url): |
369 | playlist_id = self._match_id(url) | |
370 | webpage = self._download_webpage(url, playlist_id) | |
0c148415 | 371 | title = self._og_search_title(webpage, fatal=False) |
061a75ed | 372 | return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title) |
0c148415 S |
373 | |
374 | ||
360e1ca5 | 375 | class YoutubeIE(YoutubeBaseInfoExtractor): |
78caa52a | 376 | IE_DESC = 'YouTube.com' |
cb7dfeea | 377 | _VALID_URL = r"""(?x)^ |
c5e8d7af | 378 | ( |
edb53e2d | 379 | (?:https?://|//) # http(s):// or protocol-independent URL |
66b48727 | 380 | (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com/| |
484aaeb2 | 381 | (?:www\.)?deturl\.com/www\.youtube\.com/| |
e70dc1d1 | 382 | (?:www\.)?pwnyoutube\.com/| |
8b561bfc | 383 | (?:www\.)?hooktube\.com/| |
f7000f3a | 384 | (?:www\.)?yourepeat\.com/| |
e69ae5b9 | 385 | tube\.majestyc\.net/| |
ba036333 | 386 | # Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances |
77d95677 | 387 | (?:(?:www|dev)\.)?invidio\.us/| |
ba036333 | 388 | (?:(?:www|no)\.)?invidiou\.sh/| |
389 | (?:(?:www|fi|de)\.)?invidious\.snopyta\.org/| | |
8ae113ca | 390 | (?:www\.)?invidious\.kabi\.tk/| |
ba036333 | 391 | (?:www\.)?invidious\.13ad\.de/| |
791d2e81 | 392 | (?:www\.)?invidious\.mastodon\.host/| |
494d664e | 393 | (?:www\.)?invidious\.nixnet\.xyz/| |
666d808e | 394 | (?:www\.)?invidious\.drycat\.fr/| |
ba036333 | 395 | (?:www\.)?tube\.poal\.co/| |
8ae113ca | 396 | (?:www\.)?vid\.wxzm\.sx/| |
384bf91f | 397 | (?:www\.)?yewtu\.be/| |
494d664e | 398 | (?:www\.)?yt\.elukerio\.org/| |
894b3826 | 399 | (?:www\.)?yt\.lelux\.fi/| |
1db5ab6b | 400 | (?:www\.)?invidious\.ggc-project\.de/| |
401 | (?:www\.)?yt\.maisputain\.ovh/| | |
402 | (?:www\.)?invidious\.13ad\.de/| | |
403 | (?:www\.)?invidious\.toot\.koeln/| | |
404 | (?:www\.)?invidious\.fdn\.fr/| | |
405 | (?:www\.)?watch\.nettohikari\.com/| | |
bff90fc5 | 406 | (?:www\.)?kgg2m7yk5aybusll\.onion/| |
407 | (?:www\.)?qklhadlycap4cnod\.onion/| | |
408 | (?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion/| | |
409 | (?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion/| | |
410 | (?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion/| | |
411 | (?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion/| | |
33c1c7d8 | 412 | (?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p/| |
1db5ab6b | 413 | (?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion/| |
e69ae5b9 | 414 | youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains |
c5e8d7af PH |
415 | (?:.*?\#/)? # handle anchor (#/) redirect urls |
416 | (?: # the various things that can precede the ID: | |
ac7553d0 | 417 | (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/ |
c5e8d7af | 418 | |(?: # or the v= param in all its forms |
f7000f3a | 419 | (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) |
c5e8d7af | 420 | (?:\?|\#!?) # the params delimiter ? or # or #! |
040ac686 | 421 | (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY) |
c5e8d7af PH |
422 | v= |
423 | ) | |
f4b05232 | 424 | )) |
cbaed4bb S |
425 | |(?: |
426 | youtu\.be| # just youtu.be/xxxx | |
6d4fc66b S |
427 | vid\.plus| # or vid.plus/xxxx |
428 | zwearz\.com/watch| # or zwearz.com/watch/xxxx | |
cbaed4bb | 429 | )/ |
edb53e2d | 430 | |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId= |
f4b05232 | 431 | ) |
c5e8d7af | 432 | )? # all until now is optional -> you can pass the naked ID |
8963d9c2 | 433 | ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID |
d0ba5587 S |
434 | (?!.*?\blist= |
435 | (?: | |
436 | %(playlist_id)s| # combined list/video URLs are handled by the playlist IE | |
437 | WL # WL are handled by the watch later IE | |
438 | ) | |
439 | ) | |
c5e8d7af | 440 | (?(1).+)? # if we found the ID, everything can follow |
d0ba5587 | 441 | $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE} |
c5e8d7af | 442 | _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' |
e40c758c S |
443 | _PLAYER_INFO_RE = ( |
444 | r'/(?P<id>[a-zA-Z0-9_-]{8,})/player_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?/base\.(?P<ext>[a-z]+)$', | |
445 | r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.(?P<ext>[a-z]+)$', | |
446 | ) | |
2c62dc26 | 447 | _formats = { |
c2d3cb4c | 448 | '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, |
449 | '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, | |
450 | '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}, | |
451 | '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}, | |
452 | '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}, | |
453 | '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
454 | '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
455 | '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
3834d3e3 | 456 | # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well |
c2d3cb4c | 457 | '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}, |
458 | '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
459 | '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
460 | '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
461 | '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
462 | '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, | |
e1a0bfdf | 463 | '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, |
c2d3cb4c | 464 | '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, |
465 | '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
e1a0bfdf | 466 | |
467 | ||
468 | # 3D videos | |
c2d3cb4c | 469 | '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, |
470 | '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, | |
471 | '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
472 | '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
e1a0bfdf | 473 | '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}, |
474 | '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
475 | '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
836a086c | 476 | |
96fb5605 | 477 | # Apple HTTP Live Streaming |
11f12195 | 478 | '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, |
c2d3cb4c | 479 | '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, |
480 | '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
481 | '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
482 | '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
483 | '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
e1a0bfdf | 484 | '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, |
485 | '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}, | |
2c62dc26 PH |
486 | |
487 | # DASH mp4 video | |
d23028a8 S |
488 | '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}, |
489 | '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
490 | '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
491 | '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
492 | '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
067aa17e | 493 | '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559) |
d23028a8 S |
494 | '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}, |
495 | '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
496 | '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
497 | '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
498 | '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
499 | '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
836a086c | 500 | |
f6f1fc92 | 501 | # Dash mp4 audio |
d23028a8 S |
502 | '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}, |
503 | '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}, | |
504 | '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}, | |
505 | '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
506 | '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
507 | '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}, | |
508 | '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}, | |
836a086c AZ |
509 | |
510 | # Dash webm | |
d23028a8 S |
511 | '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, |
512 | '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
513 | '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
514 | '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
515 | '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
516 | '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
517 | '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}, | |
518 | '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
519 | '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
520 | '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
521 | '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
522 | '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
523 | '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
524 | '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
525 | '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
4c6b4764 | 526 | # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug) |
d23028a8 S |
527 | '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, |
528 | '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
529 | '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
530 | '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
531 | '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
532 | '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
2c62dc26 PH |
533 | |
534 | # Dash webm audio | |
d23028a8 S |
535 | '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}, |
536 | '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}, | |
ce6b9a2d | 537 | |
0857baad | 538 | # Dash webm audio with opus inside |
d23028a8 S |
539 | '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}, |
540 | '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}, | |
541 | '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}, | |
0857baad | 542 | |
ce6b9a2d PH |
543 | # RTMP (unnamed) |
544 | '_rtmp': {'protocol': 'rtmp'}, | |
b85eae0f S |
545 | |
546 | # av01 video only formats sometimes served with "unknown" codecs | |
547 | '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}, | |
548 | '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}, | |
549 | '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}, | |
550 | '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}, | |
c5e8d7af | 551 | } |
19041a38 | 552 | _SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt') |
836a086c | 553 | |
fd5c4aab S |
554 | _GEO_BYPASS = False |
555 | ||
78caa52a | 556 | IE_NAME = 'youtube' |
2eb88d95 PH |
557 | _TESTS = [ |
558 | { | |
2d3d2997 | 559 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9', |
4bc3a23e PH |
560 | 'info_dict': { |
561 | 'id': 'BaW_jenozKc', | |
562 | 'ext': 'mp4', | |
563 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
564 | 'uploader': 'Philipp Hagemeister', | |
565 | 'uploader_id': 'phihag', | |
ec85ded8 | 566 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', |
dd4c4492 S |
567 | 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', |
568 | 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', | |
4bc3a23e PH |
569 | 'upload_date': '20121002', |
570 | '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 .', | |
571 | 'categories': ['Science & Technology'], | |
000b6b5a | 572 | 'tags': ['youtube-dl'], |
556dbe7f | 573 | 'duration': 10, |
dbdaaa23 | 574 | 'view_count': int, |
3e7c1224 PH |
575 | 'like_count': int, |
576 | 'dislike_count': int, | |
7c80519c | 577 | 'start_time': 1, |
297a564b | 578 | 'end_time': 9, |
2eb88d95 | 579 | } |
0e853ca4 | 580 | }, |
0e853ca4 | 581 | { |
2d3d2997 | 582 | 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY', |
4bc3a23e PH |
583 | 'note': 'Test generic use_cipher_signature video (#897)', |
584 | 'info_dict': { | |
585 | 'id': 'UxxajLWwzqY', | |
586 | 'ext': 'mp4', | |
587 | 'upload_date': '20120506', | |
588 | 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]', | |
0cb58b02 | 589 | 'alt_title': 'I Love It (feat. Charli XCX)', |
5429d6a9 | 590 | 'description': 'md5:19a2f98d9032b9311e686ed039564f63', |
000b6b5a S |
591 | 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli', |
592 | 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop', | |
593 | 'iconic ep', 'iconic', 'love', 'it'], | |
556dbe7f | 594 | 'duration': 180, |
4bc3a23e PH |
595 | 'uploader': 'Icona Pop', |
596 | 'uploader_id': 'IconaPop', | |
ec85ded8 | 597 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop', |
0cb58b02 | 598 | 'creator': 'Icona Pop', |
936784b2 S |
599 | 'track': 'I Love It (feat. Charli XCX)', |
600 | 'artist': 'Icona Pop', | |
2eb88d95 | 601 | } |
c108eb73 JMF |
602 | }, |
603 | { | |
4bc3a23e PH |
604 | 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ', |
605 | 'note': 'Test VEVO video with age protection (#956)', | |
606 | 'info_dict': { | |
607 | 'id': '07FYdnEawAQ', | |
608 | 'ext': 'mp4', | |
609 | 'upload_date': '20130703', | |
4fe54c12 | 610 | 'title': 'Justin Timberlake - Tunnel Vision (Official Music Video) (Explicit)', |
0cb58b02 | 611 | 'alt_title': 'Tunnel Vision', |
4fe54c12 | 612 | 'description': 'md5:07dab3356cde4199048e4c7cd93471e1', |
556dbe7f | 613 | 'duration': 419, |
4bc3a23e PH |
614 | 'uploader': 'justintimberlakeVEVO', |
615 | 'uploader_id': 'justintimberlakeVEVO', | |
ec85ded8 | 616 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO', |
0cb58b02 | 617 | 'creator': 'Justin Timberlake', |
7e72694b | 618 | 'track': 'Tunnel Vision', |
936784b2 | 619 | 'artist': 'Justin Timberlake', |
34952f09 | 620 | 'age_limit': 18, |
c108eb73 JMF |
621 | } |
622 | }, | |
fccd3771 | 623 | { |
4bc3a23e PH |
624 | 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ', |
625 | 'note': 'Embed-only video (#1746)', | |
626 | 'info_dict': { | |
627 | 'id': 'yZIXLfi8CZQ', | |
628 | 'ext': 'mp4', | |
629 | 'upload_date': '20120608', | |
630 | 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012', | |
631 | 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7', | |
632 | 'uploader': 'SET India', | |
94bfcd23 | 633 | 'uploader_id': 'setindia', |
ec85ded8 | 634 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia', |
94bfcd23 | 635 | 'age_limit': 18, |
fccd3771 PH |
636 | } |
637 | }, | |
11b56058 | 638 | { |
2d3d2997 | 639 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY', |
11b56058 PM |
640 | 'note': 'Use the first video ID in the URL', |
641 | 'info_dict': { | |
642 | 'id': 'BaW_jenozKc', | |
643 | 'ext': 'mp4', | |
644 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
645 | 'uploader': 'Philipp Hagemeister', | |
646 | 'uploader_id': 'phihag', | |
ec85ded8 | 647 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', |
11b56058 PM |
648 | 'upload_date': '20121002', |
649 | '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 .', | |
650 | 'categories': ['Science & Technology'], | |
651 | 'tags': ['youtube-dl'], | |
556dbe7f | 652 | 'duration': 10, |
dbdaaa23 | 653 | 'view_count': int, |
11b56058 PM |
654 | 'like_count': int, |
655 | 'dislike_count': int, | |
34a7de29 S |
656 | }, |
657 | 'params': { | |
658 | 'skip_download': True, | |
659 | }, | |
11b56058 | 660 | }, |
dd27fd17 | 661 | { |
2d3d2997 | 662 | 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I', |
4bc3a23e PH |
663 | 'note': '256k DASH audio (format 141) via DASH manifest', |
664 | 'info_dict': { | |
665 | 'id': 'a9LDPn-MO4I', | |
666 | 'ext': 'm4a', | |
667 | 'upload_date': '20121002', | |
668 | 'uploader_id': '8KVIDEO', | |
ec85ded8 | 669 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO', |
4bc3a23e PH |
670 | 'description': '', |
671 | 'uploader': '8KVIDEO', | |
672 | 'title': 'UHDTV TEST 8K VIDEO.mp4' | |
4919603f | 673 | }, |
4bc3a23e PH |
674 | 'params': { |
675 | 'youtube_include_dash_manifest': True, | |
676 | 'format': '141', | |
4919603f | 677 | }, |
de3c7fe0 | 678 | 'skip': 'format 141 not served anymore', |
dd27fd17 | 679 | }, |
3489b7d2 JMF |
680 | # DASH manifest with encrypted signature |
681 | { | |
78caa52a PH |
682 | 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA', |
683 | 'info_dict': { | |
684 | 'id': 'IB3lcPjvWLA', | |
685 | 'ext': 'm4a', | |
4fe54c12 S |
686 | 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson', |
687 | 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf', | |
556dbe7f | 688 | 'duration': 244, |
78caa52a PH |
689 | 'uploader': 'AfrojackVEVO', |
690 | 'uploader_id': 'AfrojackVEVO', | |
691 | 'upload_date': '20131011', | |
3489b7d2 | 692 | }, |
4bc3a23e | 693 | 'params': { |
78caa52a | 694 | 'youtube_include_dash_manifest': True, |
de3c7fe0 | 695 | 'format': '141/bestaudio[ext=m4a]', |
3489b7d2 JMF |
696 | }, |
697 | }, | |
aaeb86f6 S |
698 | # JS player signature function name containing $ |
699 | { | |
700 | 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM', | |
701 | 'info_dict': { | |
702 | 'id': 'nfWlot6h_JM', | |
703 | 'ext': 'm4a', | |
704 | 'title': 'Taylor Swift - Shake It Off', | |
5429d6a9 | 705 | 'description': 'md5:307195cd21ff7fa352270fe884570ef0', |
556dbe7f | 706 | 'duration': 242, |
aaeb86f6 S |
707 | 'uploader': 'TaylorSwiftVEVO', |
708 | 'uploader_id': 'TaylorSwiftVEVO', | |
709 | 'upload_date': '20140818', | |
710 | }, | |
711 | 'params': { | |
712 | 'youtube_include_dash_manifest': True, | |
de3c7fe0 | 713 | 'format': '141/bestaudio[ext=m4a]', |
aaeb86f6 S |
714 | }, |
715 | }, | |
aa79ac0c PH |
716 | # Controversy video |
717 | { | |
718 | 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8', | |
719 | 'info_dict': { | |
720 | 'id': 'T4XJQO3qol8', | |
721 | 'ext': 'mp4', | |
556dbe7f | 722 | 'duration': 219, |
aa79ac0c | 723 | 'upload_date': '20100909', |
4fe54c12 | 724 | 'uploader': 'Amazing Atheist', |
aa79ac0c | 725 | 'uploader_id': 'TheAmazingAtheist', |
ec85ded8 | 726 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist', |
aa79ac0c PH |
727 | 'title': 'Burning Everyone\'s Koran', |
728 | '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', | |
729 | } | |
c522adb1 JMF |
730 | }, |
731 | # Normal age-gate video (No vevo, embed allowed) | |
732 | { | |
2d3d2997 | 733 | 'url': 'https://youtube.com/watch?v=HtVdAasjOgU', |
c522adb1 JMF |
734 | 'info_dict': { |
735 | 'id': 'HtVdAasjOgU', | |
736 | 'ext': 'mp4', | |
737 | 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer', | |
ec85ded8 | 738 | 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}', |
556dbe7f | 739 | 'duration': 142, |
c522adb1 JMF |
740 | 'uploader': 'The Witcher', |
741 | 'uploader_id': 'WitcherGame', | |
ec85ded8 | 742 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame', |
c522adb1 | 743 | 'upload_date': '20140605', |
34952f09 | 744 | 'age_limit': 18, |
c522adb1 JMF |
745 | }, |
746 | }, | |
fccae2b9 S |
747 | # Age-gate video with encrypted signature |
748 | { | |
2d3d2997 | 749 | 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU', |
fccae2b9 S |
750 | 'info_dict': { |
751 | 'id': '6kLq3WMV1nU', | |
4fe54c12 | 752 | 'ext': 'mp4', |
fccae2b9 S |
753 | 'title': 'Dedication To My Ex (Miss That) (Lyric Video)', |
754 | 'description': 'md5:33765bb339e1b47e7e72b5490139bb41', | |
eb6793ba | 755 | 'duration': 246, |
fccae2b9 S |
756 | 'uploader': 'LloydVEVO', |
757 | 'uploader_id': 'LloydVEVO', | |
ec85ded8 | 758 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO', |
fccae2b9 | 759 | 'upload_date': '20110629', |
34952f09 | 760 | 'age_limit': 18, |
fccae2b9 S |
761 | }, |
762 | }, | |
067aa17e | 763 | # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421) |
7d02dcfa | 764 | # YouTube Red ad is not captured for creator |
774e208f PH |
765 | { |
766 | 'url': '__2ABJjxzNo', | |
767 | 'info_dict': { | |
768 | 'id': '__2ABJjxzNo', | |
769 | 'ext': 'mp4', | |
556dbe7f | 770 | 'duration': 266, |
774e208f PH |
771 | 'upload_date': '20100430', |
772 | 'uploader_id': 'deadmau5', | |
ec85ded8 | 773 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5', |
5429d6a9 | 774 | 'creator': 'Dada Life, deadmau5', |
774e208f PH |
775 | 'description': 'md5:12c56784b8032162bb936a5f76d55360', |
776 | 'uploader': 'deadmau5', | |
777 | 'title': 'Deadmau5 - Some Chords (HD)', | |
5429d6a9 | 778 | 'alt_title': 'This Machine Kills Some Chords', |
774e208f PH |
779 | }, |
780 | 'expected_warnings': [ | |
781 | 'DASH manifest missing', | |
782 | ] | |
e52a40ab | 783 | }, |
067aa17e | 784 | # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431) |
e52a40ab PH |
785 | { |
786 | 'url': 'lqQg6PlCWgI', | |
787 | 'info_dict': { | |
788 | 'id': 'lqQg6PlCWgI', | |
789 | 'ext': 'mp4', | |
556dbe7f | 790 | 'duration': 6085, |
90227264 | 791 | 'upload_date': '20150827', |
cbe2bd91 | 792 | 'uploader_id': 'olympic', |
ec85ded8 | 793 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic', |
cbe2bd91 | 794 | 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', |
be49068d | 795 | 'uploader': 'Olympic', |
cbe2bd91 PH |
796 | 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', |
797 | }, | |
798 | 'params': { | |
799 | 'skip_download': 'requires avconv', | |
e52a40ab | 800 | } |
cbe2bd91 | 801 | }, |
6271f1ca PH |
802 | # Non-square pixels |
803 | { | |
804 | 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0', | |
805 | 'info_dict': { | |
806 | 'id': '_b-2C3KPAM0', | |
807 | 'ext': 'mp4', | |
808 | 'stretched_ratio': 16 / 9., | |
556dbe7f | 809 | 'duration': 85, |
6271f1ca PH |
810 | 'upload_date': '20110310', |
811 | 'uploader_id': 'AllenMeow', | |
ec85ded8 | 812 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow', |
6271f1ca | 813 | '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 | 814 | 'uploader': '孫ᄋᄅ', |
6271f1ca PH |
815 | 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', |
816 | }, | |
06b491eb S |
817 | }, |
818 | # url_encoded_fmt_stream_map is empty string | |
819 | { | |
820 | 'url': 'qEJwOuvDf7I', | |
821 | 'info_dict': { | |
822 | 'id': 'qEJwOuvDf7I', | |
f57b7835 | 823 | 'ext': 'webm', |
06b491eb S |
824 | 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге', |
825 | 'description': '', | |
826 | 'upload_date': '20150404', | |
827 | 'uploader_id': 'spbelect', | |
828 | 'uploader': 'Наблюдатели Петербурга', | |
829 | }, | |
830 | 'params': { | |
831 | 'skip_download': 'requires avconv', | |
e323cf3f S |
832 | }, |
833 | 'skip': 'This live event has ended.', | |
06b491eb | 834 | }, |
067aa17e | 835 | # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097) |
da77d856 S |
836 | { |
837 | 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y', | |
838 | 'info_dict': { | |
839 | 'id': 'FIl7x6_3R5Y', | |
eb6793ba | 840 | 'ext': 'webm', |
da77d856 S |
841 | 'title': 'md5:7b81415841e02ecd4313668cde88737a', |
842 | 'description': 'md5:116377fd2963b81ec4ce64b542173306', | |
556dbe7f | 843 | 'duration': 220, |
da77d856 S |
844 | 'upload_date': '20150625', |
845 | 'uploader_id': 'dorappi2000', | |
ec85ded8 | 846 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000', |
da77d856 | 847 | 'uploader': 'dorappi2000', |
eb6793ba | 848 | 'formats': 'mincount:31', |
da77d856 | 849 | }, |
eb6793ba | 850 | 'skip': 'not actual anymore', |
2ee8f5d8 | 851 | }, |
8a1a26ce YCH |
852 | # DASH manifest with segment_list |
853 | { | |
854 | 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8', | |
855 | 'md5': '8ce563a1d667b599d21064e982ab9e31', | |
856 | 'info_dict': { | |
857 | 'id': 'CsmdDsKjzN8', | |
858 | 'ext': 'mp4', | |
17ee98e1 | 859 | 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510 |
8a1a26ce YCH |
860 | 'uploader': 'Airtek', |
861 | 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.', | |
862 | 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ', | |
863 | 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015', | |
864 | }, | |
865 | 'params': { | |
866 | 'youtube_include_dash_manifest': True, | |
867 | 'format': '135', # bestvideo | |
be49068d S |
868 | }, |
869 | 'skip': 'This live event has ended.', | |
2ee8f5d8 | 870 | }, |
cf7e015f S |
871 | { |
872 | # Multifeed videos (multiple cameras), URL is for Main Camera | |
873 | 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs', | |
874 | 'info_dict': { | |
875 | 'id': 'jqWvoWXjCVs', | |
876 | 'title': 'teamPGP: Rocket League Noob Stream', | |
877 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
878 | }, | |
879 | 'playlist': [{ | |
880 | 'info_dict': { | |
881 | 'id': 'jqWvoWXjCVs', | |
882 | 'ext': 'mp4', | |
883 | 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)', | |
884 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
556dbe7f | 885 | 'duration': 7335, |
cf7e015f S |
886 | 'upload_date': '20150721', |
887 | 'uploader': 'Beer Games Beer', | |
888 | 'uploader_id': 'beergamesbeer', | |
ec85ded8 | 889 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', |
7caf9830 | 890 | 'license': 'Standard YouTube License', |
cf7e015f S |
891 | }, |
892 | }, { | |
893 | 'info_dict': { | |
894 | 'id': '6h8e8xoXJzg', | |
895 | 'ext': 'mp4', | |
896 | 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)', | |
897 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
556dbe7f | 898 | 'duration': 7337, |
cf7e015f S |
899 | 'upload_date': '20150721', |
900 | 'uploader': 'Beer Games Beer', | |
901 | 'uploader_id': 'beergamesbeer', | |
ec85ded8 | 902 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', |
7caf9830 | 903 | 'license': 'Standard YouTube License', |
cf7e015f S |
904 | }, |
905 | }, { | |
906 | 'info_dict': { | |
907 | 'id': 'PUOgX5z9xZw', | |
908 | 'ext': 'mp4', | |
909 | 'title': 'teamPGP: Rocket League Noob Stream (grizzle)', | |
910 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
556dbe7f | 911 | 'duration': 7337, |
cf7e015f S |
912 | 'upload_date': '20150721', |
913 | 'uploader': 'Beer Games Beer', | |
914 | 'uploader_id': 'beergamesbeer', | |
ec85ded8 | 915 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', |
7caf9830 | 916 | 'license': 'Standard YouTube License', |
cf7e015f S |
917 | }, |
918 | }, { | |
919 | 'info_dict': { | |
920 | 'id': 'teuwxikvS5k', | |
921 | 'ext': 'mp4', | |
922 | 'title': 'teamPGP: Rocket League Noob Stream (zim)', | |
923 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
556dbe7f | 924 | 'duration': 7334, |
cf7e015f S |
925 | 'upload_date': '20150721', |
926 | 'uploader': 'Beer Games Beer', | |
927 | 'uploader_id': 'beergamesbeer', | |
ec85ded8 | 928 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', |
7caf9830 | 929 | 'license': 'Standard YouTube License', |
cf7e015f S |
930 | }, |
931 | }], | |
932 | 'params': { | |
933 | 'skip_download': True, | |
934 | }, | |
4fe54c12 | 935 | 'skip': 'This video is not available.', |
cbaed4bb | 936 | }, |
f9f49d87 | 937 | { |
067aa17e | 938 | # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536) |
f9f49d87 S |
939 | 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo', |
940 | 'info_dict': { | |
941 | 'id': 'gVfLd0zydlo', | |
942 | 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30', | |
943 | }, | |
944 | 'playlist_count': 2, | |
be49068d | 945 | 'skip': 'Not multifeed anymore', |
f9f49d87 | 946 | }, |
cbaed4bb | 947 | { |
2d3d2997 | 948 | 'url': 'https://vid.plus/FlRa-iH7PGw', |
cbaed4bb | 949 | 'only_matching': True, |
0e49d9a6 | 950 | }, |
6d4fc66b | 951 | { |
2d3d2997 | 952 | 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html', |
6d4fc66b S |
953 | 'only_matching': True, |
954 | }, | |
0e49d9a6 | 955 | { |
067aa17e | 956 | # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468) |
a8776b10 | 957 | # Also tests cut-off URL expansion in video description (see |
067aa17e S |
958 | # https://github.com/ytdl-org/youtube-dl/issues/1892, |
959 | # https://github.com/ytdl-org/youtube-dl/issues/8164) | |
0e49d9a6 LL |
960 | 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg', |
961 | 'info_dict': { | |
962 | 'id': 'lsguqyKfVQg', | |
963 | 'ext': 'mp4', | |
964 | 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21', | |
eb6793ba | 965 | 'alt_title': 'Dark Walk - Position Music', |
0e49d9a6 | 966 | 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a', |
556dbe7f | 967 | 'duration': 133, |
0e49d9a6 LL |
968 | 'upload_date': '20151119', |
969 | 'uploader_id': 'IronSoulElf', | |
ec85ded8 | 970 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf', |
0e49d9a6 | 971 | 'uploader': 'IronSoulElf', |
eb6793ba S |
972 | 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan', |
973 | 'track': 'Dark Walk - Position Music', | |
974 | 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan', | |
92bc97d3 | 975 | 'album': 'Position Music - Production Music Vol. 143 - Dark Walk', |
0e49d9a6 LL |
976 | }, |
977 | 'params': { | |
978 | 'skip_download': True, | |
979 | }, | |
980 | }, | |
61f92af1 | 981 | { |
067aa17e | 982 | # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468) |
61f92af1 S |
983 | 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8', |
984 | 'only_matching': True, | |
985 | }, | |
313dfc45 LL |
986 | { |
987 | # Video with yt:stretch=17:0 | |
988 | 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM', | |
989 | 'info_dict': { | |
990 | 'id': 'Q39EVAstoRM', | |
991 | 'ext': 'mp4', | |
992 | 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4', | |
993 | 'description': 'md5:ee18a25c350637c8faff806845bddee9', | |
994 | 'upload_date': '20151107', | |
995 | 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA', | |
996 | 'uploader': 'CH GAMER DROID', | |
997 | }, | |
998 | 'params': { | |
999 | 'skip_download': True, | |
1000 | }, | |
be49068d | 1001 | 'skip': 'This video does not exist.', |
313dfc45 | 1002 | }, |
7caf9830 S |
1003 | { |
1004 | # Video licensed under Creative Commons | |
1005 | 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA', | |
1006 | 'info_dict': { | |
1007 | 'id': 'M4gD1WSo5mA', | |
1008 | 'ext': 'mp4', | |
1009 | 'title': 'md5:e41008789470fc2533a3252216f1c1d1', | |
1010 | 'description': 'md5:a677553cf0840649b731a3024aeff4cc', | |
556dbe7f | 1011 | 'duration': 721, |
7caf9830 S |
1012 | 'upload_date': '20150127', |
1013 | 'uploader_id': 'BerkmanCenter', | |
ec85ded8 | 1014 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter', |
556dbe7f | 1015 | 'uploader': 'The Berkman Klein Center for Internet & Society', |
7caf9830 S |
1016 | 'license': 'Creative Commons Attribution license (reuse allowed)', |
1017 | }, | |
1018 | 'params': { | |
1019 | 'skip_download': True, | |
1020 | }, | |
1021 | }, | |
fd050249 S |
1022 | { |
1023 | # Channel-like uploader_url | |
1024 | 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg', | |
1025 | 'info_dict': { | |
1026 | 'id': 'eQcmzGIKrzg', | |
1027 | 'ext': 'mp4', | |
1028 | 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders', | |
1029 | 'description': 'md5:dda0d780d5a6e120758d1711d062a867', | |
556dbe7f | 1030 | 'duration': 4060, |
fd050249 | 1031 | 'upload_date': '20151119', |
eb6793ba | 1032 | 'uploader': 'Bernie Sanders', |
fd050249 | 1033 | 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg', |
ec85ded8 | 1034 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg', |
fd050249 S |
1035 | 'license': 'Creative Commons Attribution license (reuse allowed)', |
1036 | }, | |
1037 | 'params': { | |
1038 | 'skip_download': True, | |
1039 | }, | |
1040 | }, | |
040ac686 S |
1041 | { |
1042 | 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY', | |
1043 | 'only_matching': True, | |
7f29cf54 S |
1044 | }, |
1045 | { | |
067aa17e | 1046 | # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059) |
7f29cf54 S |
1047 | 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo', |
1048 | 'only_matching': True, | |
6496ccb4 S |
1049 | }, |
1050 | { | |
1051 | # Rental video preview | |
1052 | 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg', | |
1053 | 'info_dict': { | |
1054 | 'id': 'uGpuVWrhIzE', | |
1055 | 'ext': 'mp4', | |
1056 | 'title': 'Piku - Trailer', | |
1057 | 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb', | |
1058 | 'upload_date': '20150811', | |
1059 | 'uploader': 'FlixMatrix', | |
1060 | 'uploader_id': 'FlixMatrixKaravan', | |
ec85ded8 | 1061 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan', |
6496ccb4 S |
1062 | 'license': 'Standard YouTube License', |
1063 | }, | |
1064 | 'params': { | |
1065 | 'skip_download': True, | |
1066 | }, | |
eb6793ba | 1067 | 'skip': 'This video is not available.', |
022a5d66 | 1068 | }, |
12afdc2a S |
1069 | { |
1070 | # YouTube Red video with episode data | |
1071 | 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4', | |
1072 | 'info_dict': { | |
1073 | 'id': 'iqKdEhx-dD4', | |
1074 | 'ext': 'mp4', | |
1075 | 'title': 'Isolation - Mind Field (Ep 1)', | |
4fe54c12 | 1076 | 'description': 'md5:46a29be4ceffa65b92d277b93f463c0f', |
556dbe7f | 1077 | 'duration': 2085, |
12afdc2a S |
1078 | 'upload_date': '20170118', |
1079 | 'uploader': 'Vsauce', | |
1080 | 'uploader_id': 'Vsauce', | |
1081 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce', | |
12afdc2a S |
1082 | 'series': 'Mind Field', |
1083 | 'season_number': 1, | |
1084 | 'episode_number': 1, | |
1085 | }, | |
1086 | 'params': { | |
1087 | 'skip_download': True, | |
1088 | }, | |
1089 | 'expected_warnings': [ | |
1090 | 'Skipping DASH manifest', | |
1091 | ], | |
1092 | }, | |
c7121fa7 S |
1093 | { |
1094 | # The following content has been identified by the YouTube community | |
1095 | # as inappropriate or offensive to some audiences. | |
1096 | 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI', | |
1097 | 'info_dict': { | |
1098 | 'id': '6SJNVb0GnPI', | |
1099 | 'ext': 'mp4', | |
1100 | 'title': 'Race Differences in Intelligence', | |
1101 | 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1', | |
1102 | 'duration': 965, | |
1103 | 'upload_date': '20140124', | |
1104 | 'uploader': 'New Century Foundation', | |
1105 | 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg', | |
1106 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg', | |
c7121fa7 S |
1107 | }, |
1108 | 'params': { | |
1109 | 'skip_download': True, | |
1110 | }, | |
1111 | }, | |
022a5d66 S |
1112 | { |
1113 | # itag 212 | |
1114 | 'url': '1t24XAntNCY', | |
1115 | 'only_matching': True, | |
fd5c4aab S |
1116 | }, |
1117 | { | |
1118 | # geo restricted to JP | |
1119 | 'url': 'sJL6WA-aGkQ', | |
1120 | 'only_matching': True, | |
1121 | }, | |
d0ba5587 S |
1122 | { |
1123 | 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM', | |
1124 | 'only_matching': True, | |
1125 | }, | |
cd5a74a2 S |
1126 | { |
1127 | 'url': 'https://invidio.us/watch?v=BaW_jenozKc', | |
1128 | 'only_matching': True, | |
1129 | }, | |
825cd268 RA |
1130 | { |
1131 | # DRM protected | |
1132 | 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc', | |
1133 | 'only_matching': True, | |
4fe54c12 S |
1134 | }, |
1135 | { | |
1136 | # Video with unsupported adaptive stream type formats | |
1137 | 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U', | |
1138 | 'info_dict': { | |
1139 | 'id': 'Z4Vy8R84T1U', | |
1140 | 'ext': 'mp4', | |
1141 | 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta', | |
1142 | 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', | |
1143 | 'duration': 433, | |
1144 | 'upload_date': '20130923', | |
1145 | 'uploader': 'Amelia Putri Harwita', | |
1146 | 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q', | |
1147 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q', | |
1148 | 'formats': 'maxcount:10', | |
1149 | }, | |
1150 | 'params': { | |
1151 | 'skip_download': True, | |
1152 | 'youtube_include_dash_manifest': False, | |
1153 | }, | |
5429d6a9 | 1154 | 'skip': 'not actual anymore', |
5caabd3c | 1155 | }, |
1156 | { | |
822b9d9c | 1157 | # Youtube Music Auto-generated description |
5caabd3c | 1158 | 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs', |
1159 | 'info_dict': { | |
1160 | 'id': 'MgNrAu2pzNs', | |
1161 | 'ext': 'mp4', | |
1162 | 'title': 'Voyeur Girl', | |
1163 | 'description': 'md5:7ae382a65843d6df2685993e90a8628f', | |
1164 | 'upload_date': '20190312', | |
5429d6a9 S |
1165 | 'uploader': 'Stephen - Topic', |
1166 | 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA', | |
5caabd3c | 1167 | 'artist': 'Stephen', |
1168 | 'track': 'Voyeur Girl', | |
1169 | 'album': 'it\'s too much love to know my dear', | |
1170 | 'release_date': '20190313', | |
1171 | 'release_year': 2019, | |
1172 | }, | |
1173 | 'params': { | |
1174 | 'skip_download': True, | |
1175 | }, | |
1176 | }, | |
1177 | { | |
822b9d9c | 1178 | # Youtube Music Auto-generated description |
5caabd3c | 1179 | # Retrieve 'artist' field from 'Artist:' in video description |
1180 | # when it is present on youtube music video | |
5caabd3c | 1181 | 'url': 'https://www.youtube.com/watch?v=k0jLE7tTwjY', |
1182 | 'info_dict': { | |
1183 | 'id': 'k0jLE7tTwjY', | |
1184 | 'ext': 'mp4', | |
1185 | 'title': 'Latch Feat. Sam Smith', | |
1186 | 'description': 'md5:3cb1e8101a7c85fcba9b4fb41b951335', | |
1187 | 'upload_date': '20150110', | |
1188 | 'uploader': 'Various Artists - Topic', | |
1189 | 'uploader_id': 'UCNkEcmYdjrH4RqtNgh7BZ9w', | |
1190 | 'artist': 'Disclosure', | |
1191 | 'track': 'Latch Feat. Sam Smith', | |
1192 | 'album': 'Latch Featuring Sam Smith', | |
1193 | 'release_date': '20121008', | |
1194 | 'release_year': 2012, | |
1195 | }, | |
1196 | 'params': { | |
1197 | 'skip_download': True, | |
1198 | }, | |
1199 | }, | |
1200 | { | |
822b9d9c | 1201 | # Youtube Music Auto-generated description |
5caabd3c | 1202 | # handle multiple artists on youtube music video |
1203 | 'url': 'https://www.youtube.com/watch?v=74qn0eJSjpA', | |
1204 | 'info_dict': { | |
1205 | 'id': '74qn0eJSjpA', | |
1206 | 'ext': 'mp4', | |
1207 | 'title': 'Eastside', | |
1208 | 'description': 'md5:290516bb73dcbfab0dcc4efe6c3de5f2', | |
1209 | 'upload_date': '20180710', | |
1210 | 'uploader': 'Benny Blanco - Topic', | |
1211 | 'uploader_id': 'UCzqz_ksRu_WkIzmivMdIS7A', | |
1212 | 'artist': 'benny blanco, Halsey, Khalid', | |
1213 | 'track': 'Eastside', | |
1214 | 'album': 'Eastside', | |
1215 | 'release_date': '20180713', | |
1216 | 'release_year': 2018, | |
1217 | }, | |
1218 | 'params': { | |
1219 | 'skip_download': True, | |
1220 | }, | |
1221 | }, | |
1222 | { | |
822b9d9c | 1223 | # Youtube Music Auto-generated description |
5caabd3c | 1224 | # handle youtube music video with release_year and no release_date |
1225 | 'url': 'https://www.youtube.com/watch?v=-hcAI0g-f5M', | |
1226 | 'info_dict': { | |
1227 | 'id': '-hcAI0g-f5M', | |
1228 | 'ext': 'mp4', | |
1229 | 'title': 'Put It On Me', | |
5429d6a9 | 1230 | 'description': 'md5:f6422397c07c4c907c6638e1fee380a5', |
5caabd3c | 1231 | 'upload_date': '20180426', |
1232 | 'uploader': 'Matt Maeson - Topic', | |
1233 | 'uploader_id': 'UCnEkIGqtGcQMLk73Kp-Q5LQ', | |
1234 | 'artist': 'Matt Maeson', | |
1235 | 'track': 'Put It On Me', | |
1236 | 'album': 'The Hearse', | |
1237 | 'release_date': None, | |
1238 | 'release_year': 2018, | |
1239 | }, | |
1240 | 'params': { | |
1241 | 'skip_download': True, | |
1242 | }, | |
1243 | }, | |
66b48727 RA |
1244 | { |
1245 | 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q', | |
1246 | 'only_matching': True, | |
1247 | }, | |
011e75e6 S |
1248 | { |
1249 | # invalid -> valid video id redirection | |
1250 | 'url': 'DJztXj2GPfl', | |
1251 | 'info_dict': { | |
1252 | 'id': 'DJztXj2GPfk', | |
1253 | 'ext': 'mp4', | |
1254 | 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)', | |
1255 | 'description': 'md5:bf577a41da97918e94fa9798d9228825', | |
1256 | 'upload_date': '20090125', | |
1257 | 'uploader': 'Prochorowka', | |
1258 | 'uploader_id': 'Prochorowka', | |
1259 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka', | |
1260 | 'artist': 'Panjabi MC', | |
1261 | 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix', | |
1262 | 'album': 'Beware of the Boys (Mundian To Bach Ke)', | |
1263 | }, | |
1264 | 'params': { | |
1265 | 'skip_download': True, | |
1266 | }, | |
1267 | } | |
2eb88d95 PH |
1268 | ] |
1269 | ||
e0df6211 PH |
1270 | def __init__(self, *args, **kwargs): |
1271 | super(YoutubeIE, self).__init__(*args, **kwargs) | |
83799698 | 1272 | self._player_cache = {} |
e0df6211 | 1273 | |
c5e8d7af PH |
1274 | def report_video_info_webpage_download(self, video_id): |
1275 | """Report attempt to download video info webpage.""" | |
69ea8ca4 | 1276 | self.to_screen('%s: Downloading video info webpage' % video_id) |
c5e8d7af | 1277 | |
c5e8d7af PH |
1278 | def report_information_extraction(self, video_id): |
1279 | """Report attempt to extract video information.""" | |
69ea8ca4 | 1280 | self.to_screen('%s: Extracting video information' % video_id) |
c5e8d7af PH |
1281 | |
1282 | def report_unavailable_format(self, video_id, format): | |
1283 | """Report extracted video URL.""" | |
69ea8ca4 | 1284 | self.to_screen('%s: Format %s not available' % (video_id, format)) |
c5e8d7af PH |
1285 | |
1286 | def report_rtmp_download(self): | |
1287 | """Indicate the download will use the RTMP protocol.""" | |
69ea8ca4 | 1288 | self.to_screen('RTMP download detected') |
c5e8d7af | 1289 | |
60064c53 PH |
1290 | def _signature_cache_id(self, example_sig): |
1291 | """ Return a string representation of a signature """ | |
78caa52a | 1292 | return '.'.join(compat_str(len(part)) for part in example_sig.split('.')) |
60064c53 | 1293 | |
e40c758c S |
1294 | @classmethod |
1295 | def _extract_player_info(cls, player_url): | |
1296 | for player_re in cls._PLAYER_INFO_RE: | |
1297 | id_m = re.search(player_re, player_url) | |
1298 | if id_m: | |
1299 | break | |
1300 | else: | |
c081b35c | 1301 | raise ExtractorError('Cannot identify player %r' % player_url) |
e40c758c S |
1302 | return id_m.group('ext'), id_m.group('id') |
1303 | ||
1304 | def _extract_signature_function(self, video_id, player_url, example_sig): | |
1305 | player_type, player_id = self._extract_player_info(player_url) | |
e0df6211 | 1306 | |
c4417ddb | 1307 | # Read from filesystem cache |
60064c53 PH |
1308 | func_id = '%s_%s_%s' % ( |
1309 | player_type, player_id, self._signature_cache_id(example_sig)) | |
c4417ddb | 1310 | assert os.path.basename(func_id) == func_id |
a0e07d31 | 1311 | |
69ea8ca4 | 1312 | cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id) |
a0e07d31 | 1313 | if cache_spec is not None: |
78caa52a | 1314 | return lambda s: ''.join(s[i] for i in cache_spec) |
83799698 | 1315 | |
6d1a55a5 PH |
1316 | download_note = ( |
1317 | 'Downloading player %s' % player_url | |
1318 | if self._downloader.params.get('verbose') else | |
1319 | 'Downloading %s player %s' % (player_type, player_id) | |
1320 | ) | |
e0df6211 PH |
1321 | if player_type == 'js': |
1322 | code = self._download_webpage( | |
1323 | player_url, video_id, | |
6d1a55a5 | 1324 | note=download_note, |
69ea8ca4 | 1325 | errnote='Download of %s failed' % player_url) |
83799698 | 1326 | res = self._parse_sig_js(code) |
c4417ddb | 1327 | elif player_type == 'swf': |
e0df6211 PH |
1328 | urlh = self._request_webpage( |
1329 | player_url, video_id, | |
6d1a55a5 | 1330 | note=download_note, |
69ea8ca4 | 1331 | errnote='Download of %s failed' % player_url) |
e0df6211 | 1332 | code = urlh.read() |
83799698 | 1333 | res = self._parse_sig_swf(code) |
e0df6211 PH |
1334 | else: |
1335 | assert False, 'Invalid player type %r' % player_type | |
1336 | ||
785521bf PH |
1337 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
1338 | cache_res = res(test_string) | |
1339 | cache_spec = [ord(c) for c in cache_res] | |
83799698 | 1340 | |
69ea8ca4 | 1341 | self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec) |
83799698 PH |
1342 | return res |
1343 | ||
60064c53 | 1344 | def _print_sig_code(self, func, example_sig): |
edf3e38e PH |
1345 | def gen_sig_code(idxs): |
1346 | def _genslice(start, end, step): | |
78caa52a | 1347 | starts = '' if start == 0 else str(start) |
8bcc8756 | 1348 | ends = (':%d' % (end + step)) if end + step >= 0 else ':' |
69ea8ca4 | 1349 | steps = '' if step == 1 else (':%d' % step) |
78caa52a | 1350 | return 's[%s%s%s]' % (starts, ends, steps) |
edf3e38e PH |
1351 | |
1352 | step = None | |
7af808a5 PH |
1353 | # Quelch pyflakes warnings - start will be set when step is set |
1354 | start = '(Never used)' | |
edf3e38e PH |
1355 | for i, prev in zip(idxs[1:], idxs[:-1]): |
1356 | if step is not None: | |
1357 | if i - prev == step: | |
1358 | continue | |
1359 | yield _genslice(start, prev, step) | |
1360 | step = None | |
1361 | continue | |
1362 | if i - prev in [-1, 1]: | |
1363 | step = i - prev | |
1364 | start = prev | |
1365 | continue | |
1366 | else: | |
78caa52a | 1367 | yield 's[%d]' % prev |
edf3e38e | 1368 | if step is None: |
78caa52a | 1369 | yield 's[%d]' % i |
edf3e38e PH |
1370 | else: |
1371 | yield _genslice(start, i, step) | |
1372 | ||
78caa52a | 1373 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
c705320f | 1374 | cache_res = func(test_string) |
edf3e38e | 1375 | cache_spec = [ord(c) for c in cache_res] |
78caa52a | 1376 | expr_code = ' + '.join(gen_sig_code(cache_spec)) |
60064c53 PH |
1377 | signature_id_tuple = '(%s)' % ( |
1378 | ', '.join(compat_str(len(p)) for p in example_sig.split('.'))) | |
69ea8ca4 | 1379 | code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n' |
78caa52a | 1380 | ' return %s\n') % (signature_id_tuple, expr_code) |
69ea8ca4 | 1381 | self.to_screen('Extracted signature function:\n' + code) |
edf3e38e | 1382 | |
e0df6211 PH |
1383 | def _parse_sig_js(self, jscode): |
1384 | funcname = self._search_regex( | |
abefc03f S |
1385 | (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', |
1386 | 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 | 1387 | 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 | 1388 | r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)', |
abefc03f S |
1389 | # Obsolete patterns |
1390 | r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
9a47fa35 | 1391 | r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(', |
abefc03f S |
1392 | r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(', |
1393 | r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1394 | r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1395 | r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1396 | r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1397 | r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('), | |
3c90cc8b | 1398 | jscode, 'Initial JS player signature function name', group='sig') |
2b25cb5d PH |
1399 | |
1400 | jsi = JSInterpreter(jscode) | |
1401 | initial_function = jsi.extract_function(funcname) | |
e0df6211 PH |
1402 | return lambda s: initial_function([s]) |
1403 | ||
1404 | def _parse_sig_swf(self, file_contents): | |
54256267 | 1405 | swfi = SWFInterpreter(file_contents) |
78caa52a | 1406 | TARGET_CLASSNAME = 'SignatureDecipher' |
54256267 | 1407 | searched_class = swfi.extract_class(TARGET_CLASSNAME) |
78caa52a | 1408 | initial_function = swfi.extract_function(searched_class, 'decipher') |
e0df6211 PH |
1409 | return lambda s: initial_function([s]) |
1410 | ||
83799698 | 1411 | def _decrypt_signature(self, s, video_id, player_url, age_gate=False): |
257a2501 | 1412 | """Turn the encrypted s field into a working signature""" |
6b37f0be | 1413 | |
c8bf86d5 | 1414 | if player_url is None: |
69ea8ca4 | 1415 | raise ExtractorError('Cannot decrypt signature without player_url') |
920de7a2 | 1416 | |
69ea8ca4 | 1417 | if player_url.startswith('//'): |
78caa52a | 1418 | player_url = 'https:' + player_url |
3c90cc8b S |
1419 | elif not re.match(r'https?://', player_url): |
1420 | player_url = compat_urlparse.urljoin( | |
1421 | 'https://www.youtube.com', player_url) | |
c8bf86d5 | 1422 | try: |
62af3a0e | 1423 | player_id = (player_url, self._signature_cache_id(s)) |
c8bf86d5 PH |
1424 | if player_id not in self._player_cache: |
1425 | func = self._extract_signature_function( | |
60064c53 | 1426 | video_id, player_url, s |
c8bf86d5 PH |
1427 | ) |
1428 | self._player_cache[player_id] = func | |
1429 | func = self._player_cache[player_id] | |
1430 | if self._downloader.params.get('youtube_print_sig_code'): | |
60064c53 | 1431 | self._print_sig_code(func, s) |
c8bf86d5 PH |
1432 | return func(s) |
1433 | except Exception as e: | |
1434 | tb = traceback.format_exc() | |
1435 | raise ExtractorError( | |
78caa52a | 1436 | 'Signature extraction failed: ' + tb, cause=e) |
e0df6211 | 1437 | |
360e1ca5 | 1438 | def _get_subtitles(self, video_id, webpage): |
de7f3446 | 1439 | try: |
60e47a26 | 1440 | subs_doc = self._download_xml( |
38c2e5b8 | 1441 | 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id, |
7fad1c63 JMF |
1442 | video_id, note=False) |
1443 | except ExtractorError as err: | |
9b9c5355 | 1444 | self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err)) |
de7f3446 | 1445 | return {} |
de7f3446 JMF |
1446 | |
1447 | sub_lang_list = {} | |
60e47a26 JMF |
1448 | for track in subs_doc.findall('track'): |
1449 | lang = track.attrib['lang_code'] | |
7e660ac1 LD |
1450 | if lang in sub_lang_list: |
1451 | continue | |
360e1ca5 | 1452 | sub_formats = [] |
23d17e4b | 1453 | for ext in self._SUBTITLE_FORMATS: |
15707c7e | 1454 | params = compat_urllib_parse_urlencode({ |
360e1ca5 JMF |
1455 | 'lang': lang, |
1456 | 'v': video_id, | |
1457 | 'fmt': ext, | |
1458 | 'name': track.attrib['name'].encode('utf-8'), | |
1459 | }) | |
1460 | sub_formats.append({ | |
1461 | 'url': 'https://www.youtube.com/api/timedtext?' + params, | |
1462 | 'ext': ext, | |
1463 | }) | |
1464 | sub_lang_list[lang] = sub_formats | |
de7f3446 | 1465 | if not sub_lang_list: |
69ea8ca4 | 1466 | self._downloader.report_warning('video doesn\'t have subtitles') |
de7f3446 JMF |
1467 | return {} |
1468 | return sub_lang_list | |
1469 | ||
a72778d3 S |
1470 | def _get_ytplayer_config(self, video_id, webpage): |
1471 | patterns = ( | |
526b3b07 S |
1472 | # User data may contain arbitrary character sequences that may affect |
1473 | # JSON extraction with regex, e.g. when '};' is contained the second | |
1474 | # regex won't capture the whole JSON. Yet working around by trying more | |
1475 | # concrete regex first keeping in mind proper quoted string handling | |
1476 | # to be implemented in future that will replace this workaround (see | |
067aa17e S |
1477 | # https://github.com/ytdl-org/youtube-dl/issues/7468, |
1478 | # https://github.com/ytdl-org/youtube-dl/pull/7599) | |
a72778d3 S |
1479 | r';ytplayer\.config\s*=\s*({.+?});ytplayer', |
1480 | r';ytplayer\.config\s*=\s*({.+?});', | |
1481 | ) | |
1482 | config = self._search_regex( | |
1483 | patterns, webpage, 'ytplayer.config', default=None) | |
1484 | if config: | |
1485 | return self._parse_json( | |
1486 | uppercase_escape(config), video_id, fatal=False) | |
0e49d9a6 | 1487 | |
360e1ca5 | 1488 | def _get_automatic_captions(self, video_id, webpage): |
de7f3446 JMF |
1489 | """We need the webpage for getting the captions url, pass it as an |
1490 | argument to speed up the process.""" | |
69ea8ca4 | 1491 | self.to_screen('%s: Looking for automatic captions' % video_id) |
a72778d3 | 1492 | player_config = self._get_ytplayer_config(video_id, webpage) |
78caa52a | 1493 | err_msg = 'Couldn\'t find automatic captions for %s' % video_id |
a72778d3 | 1494 | if not player_config: |
de7f3446 JMF |
1495 | self._downloader.report_warning(err_msg) |
1496 | return {} | |
de7f3446 | 1497 | try: |
0792d563 | 1498 | args = player_config['args'] |
b78b292f S |
1499 | caption_url = args.get('ttsurl') |
1500 | if caption_url: | |
1501 | timestamp = args['timestamp'] | |
1502 | # We get the available subtitles | |
15707c7e | 1503 | list_params = compat_urllib_parse_urlencode({ |
b78b292f S |
1504 | 'type': 'list', |
1505 | 'tlangs': 1, | |
1506 | 'asrs': 1, | |
1507 | }) | |
1508 | list_url = caption_url + '&' + list_params | |
1509 | caption_list = self._download_xml(list_url, video_id) | |
1510 | original_lang_node = caption_list.find('track') | |
1511 | if original_lang_node is None: | |
1512 | self._downloader.report_warning('Video doesn\'t have automatic captions') | |
1513 | return {} | |
1514 | original_lang = original_lang_node.attrib['lang_code'] | |
1515 | caption_kind = original_lang_node.attrib.get('kind', '') | |
1516 | ||
1517 | sub_lang_list = {} | |
1518 | for lang_node in caption_list.findall('target'): | |
1519 | sub_lang = lang_node.attrib['lang_code'] | |
1520 | sub_formats = [] | |
1521 | for ext in self._SUBTITLE_FORMATS: | |
15707c7e | 1522 | params = compat_urllib_parse_urlencode({ |
b78b292f S |
1523 | 'lang': original_lang, |
1524 | 'tlang': sub_lang, | |
1525 | 'fmt': ext, | |
1526 | 'ts': timestamp, | |
1527 | 'kind': caption_kind, | |
1528 | }) | |
1529 | sub_formats.append({ | |
1530 | 'url': caption_url + '&' + params, | |
1531 | 'ext': ext, | |
1532 | }) | |
1533 | sub_lang_list[sub_lang] = sub_formats | |
1534 | return sub_lang_list | |
1535 | ||
ddbb4c5c S |
1536 | def make_captions(sub_url, sub_langs): |
1537 | parsed_sub_url = compat_urllib_parse_urlparse(sub_url) | |
1538 | caption_qs = compat_parse_qs(parsed_sub_url.query) | |
1539 | captions = {} | |
1540 | for sub_lang in sub_langs: | |
1541 | sub_formats = [] | |
1542 | for ext in self._SUBTITLE_FORMATS: | |
1543 | caption_qs.update({ | |
1544 | 'tlang': [sub_lang], | |
1545 | 'fmt': [ext], | |
1546 | }) | |
1547 | sub_url = compat_urlparse.urlunparse(parsed_sub_url._replace( | |
1548 | query=compat_urllib_parse_urlencode(caption_qs, True))) | |
1549 | sub_formats.append({ | |
1550 | 'url': sub_url, | |
1551 | 'ext': ext, | |
1552 | }) | |
1553 | captions[sub_lang] = sub_formats | |
1554 | return captions | |
1555 | ||
1556 | # New captions format as of 22.06.2017 | |
1557 | player_response = args.get('player_response') | |
1558 | if player_response and isinstance(player_response, compat_str): | |
1559 | player_response = self._parse_json( | |
1560 | player_response, video_id, fatal=False) | |
1561 | if player_response: | |
1562 | renderer = player_response['captions']['playerCaptionsTracklistRenderer'] | |
1563 | base_url = renderer['captionTracks'][0]['baseUrl'] | |
1564 | sub_lang_list = [] | |
1565 | for lang in renderer['translationLanguages']: | |
1566 | lang_code = lang.get('languageCode') | |
1567 | if lang_code: | |
1568 | sub_lang_list.append(lang_code) | |
1569 | return make_captions(base_url, sub_lang_list) | |
1570 | ||
b78b292f S |
1571 | # Some videos don't provide ttsurl but rather caption_tracks and |
1572 | # caption_translation_languages (e.g. 20LmZk1hakA) | |
ddbb4c5c | 1573 | # Does not used anymore as of 22.06.2017 |
b78b292f S |
1574 | caption_tracks = args['caption_tracks'] |
1575 | caption_translation_languages = args['caption_translation_languages'] | |
1576 | caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0] | |
ddbb4c5c | 1577 | sub_lang_list = [] |
b78b292f S |
1578 | for lang in caption_translation_languages.split(','): |
1579 | lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang)) | |
1580 | sub_lang = lang_qs.get('lc', [None])[0] | |
ddbb4c5c S |
1581 | if sub_lang: |
1582 | sub_lang_list.append(sub_lang) | |
1583 | return make_captions(caption_url, sub_lang_list) | |
de7f3446 JMF |
1584 | # An extractor error can be raise by the download process if there are |
1585 | # no automatic captions but there are subtitles | |
ddbb4c5c | 1586 | except (KeyError, IndexError, ExtractorError): |
de7f3446 JMF |
1587 | self._downloader.report_warning(err_msg) |
1588 | return {} | |
1589 | ||
21c340b8 S |
1590 | def _mark_watched(self, video_id, video_info, player_response): |
1591 | playback_url = url_or_none(try_get( | |
1592 | player_response, | |
1593 | lambda x: x['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get( | |
1594 | video_info, lambda x: x['videostats_playback_base_url'][0])) | |
d77ab8e2 S |
1595 | if not playback_url: |
1596 | return | |
1597 | parsed_playback_url = compat_urlparse.urlparse(playback_url) | |
1598 | qs = compat_urlparse.parse_qs(parsed_playback_url.query) | |
1599 | ||
1600 | # cpn generation algorithm is reverse engineered from base.js. | |
1601 | # In fact it works even with dummy cpn. | |
1602 | CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_' | |
1603 | cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))) | |
1604 | ||
1605 | qs.update({ | |
1606 | 'ver': ['2'], | |
1607 | 'cpn': [cpn], | |
1608 | }) | |
1609 | playback_url = compat_urlparse.urlunparse( | |
15707c7e | 1610 | parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True))) |
d77ab8e2 S |
1611 | |
1612 | self._download_webpage( | |
1613 | playback_url, video_id, 'Marking watched', | |
1614 | 'Unable to mark watched', fatal=False) | |
1615 | ||
66c9fa36 S |
1616 | @staticmethod |
1617 | def _extract_urls(webpage): | |
1618 | # Embedded YouTube player | |
1619 | entries = [ | |
1620 | unescapeHTML(mobj.group('url')) | |
1621 | for mobj in re.finditer(r'''(?x) | |
1622 | (?: | |
1623 | <iframe[^>]+?src=| | |
1624 | data-video-url=| | |
1625 | <embed[^>]+?src=| | |
1626 | embedSWF\(?:\s*| | |
1627 | <object[^>]+data=| | |
1628 | new\s+SWFObject\( | |
1629 | ) | |
1630 | (["\']) | |
1631 | (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/ | |
f2332f18 | 1632 | (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?) |
66c9fa36 S |
1633 | \1''', webpage)] |
1634 | ||
1635 | # lazyYT YouTube embed | |
1636 | entries.extend(list(map( | |
1637 | unescapeHTML, | |
1638 | re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)))) | |
1639 | ||
1640 | # Wordpress "YouTube Video Importer" plugin | |
1641 | matches = re.findall(r'''(?x)<div[^>]+ | |
1642 | class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+ | |
1643 | data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage) | |
1644 | entries.extend(m[-1] for m in matches) | |
1645 | ||
1646 | return entries | |
1647 | ||
1648 | @staticmethod | |
1649 | def _extract_url(webpage): | |
1650 | urls = YoutubeIE._extract_urls(webpage) | |
1651 | return urls[0] if urls else None | |
1652 | ||
97665381 PH |
1653 | @classmethod |
1654 | def extract_id(cls, url): | |
1655 | mobj = re.match(cls._VALID_URL, url, re.VERBOSE) | |
c5e8d7af | 1656 | if mobj is None: |
69ea8ca4 | 1657 | raise ExtractorError('Invalid URL: %s' % url) |
c5e8d7af PH |
1658 | video_id = mobj.group(2) |
1659 | return video_id | |
1660 | ||
84213ea8 S |
1661 | def _extract_chapters_from_json(self, webpage, video_id, duration): |
1662 | if not webpage: | |
1663 | return | |
1664 | player = self._parse_json( | |
1665 | self._search_regex( | |
1666 | r'RELATED_PLAYER_ARGS["\']\s*:\s*({.+})\s*,?\s*\n', webpage, | |
1667 | 'player args', default='{}'), | |
1668 | video_id, fatal=False) | |
1669 | if not player or not isinstance(player, dict): | |
1670 | return | |
1671 | watch_next_response = player.get('watch_next_response') | |
1672 | if not isinstance(watch_next_response, compat_str): | |
1673 | return | |
1674 | response = self._parse_json(watch_next_response, video_id, fatal=False) | |
1675 | if not response or not isinstance(response, dict): | |
1676 | return | |
1677 | chapters_list = try_get( | |
1678 | response, | |
1679 | lambda x: x['playerOverlays'] | |
1680 | ['playerOverlayRenderer'] | |
1681 | ['decoratedPlayerBarRenderer'] | |
1682 | ['decoratedPlayerBarRenderer'] | |
1683 | ['playerBar'] | |
1684 | ['chapteredPlayerBarRenderer'] | |
1685 | ['chapters'], | |
1686 | list) | |
1687 | if not chapters_list: | |
1688 | return | |
1689 | ||
1690 | def chapter_time(chapter): | |
1691 | return float_or_none( | |
1692 | try_get( | |
1693 | chapter, | |
1694 | lambda x: x['chapterRenderer']['timeRangeStartMillis'], | |
1695 | int), | |
1696 | scale=1000) | |
1697 | chapters = [] | |
1698 | for next_num, chapter in enumerate(chapters_list, start=1): | |
1699 | start_time = chapter_time(chapter) | |
1700 | if start_time is None: | |
1701 | continue | |
1702 | end_time = (chapter_time(chapters_list[next_num]) | |
1703 | if next_num < len(chapters_list) else duration) | |
1704 | if end_time is None: | |
1705 | continue | |
1706 | title = try_get( | |
1707 | chapter, lambda x: x['chapterRenderer']['title']['simpleText'], | |
1708 | compat_str) | |
1709 | chapters.append({ | |
1710 | 'start_time': start_time, | |
1711 | 'end_time': end_time, | |
1712 | 'title': title, | |
1713 | }) | |
1714 | return chapters | |
1715 | ||
9cafc3fd | 1716 | @staticmethod |
84213ea8 | 1717 | def _extract_chapters_from_description(description, duration): |
9cafc3fd S |
1718 | if not description: |
1719 | return None | |
1720 | chapter_lines = re.findall( | |
1721 | r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<br\s*/>)', | |
1722 | description) | |
1723 | if not chapter_lines: | |
1724 | return None | |
1725 | chapters = [] | |
1726 | for next_num, (chapter_line, time_point) in enumerate( | |
1727 | chapter_lines, start=1): | |
1728 | start_time = parse_duration(time_point) | |
1729 | if start_time is None: | |
1730 | continue | |
39d4c1be S |
1731 | if start_time > duration: |
1732 | break | |
9cafc3fd S |
1733 | end_time = (duration if next_num == len(chapter_lines) |
1734 | else parse_duration(chapter_lines[next_num][1])) | |
1735 | if end_time is None: | |
1736 | continue | |
39d4c1be S |
1737 | if end_time > duration: |
1738 | end_time = duration | |
1739 | if start_time > end_time: | |
1740 | break | |
9cafc3fd S |
1741 | chapter_title = re.sub( |
1742 | r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-') | |
1743 | chapter_title = re.sub(r'\s+', ' ', chapter_title) | |
1744 | chapters.append({ | |
1745 | 'start_time': start_time, | |
1746 | 'end_time': end_time, | |
1747 | 'title': chapter_title, | |
1748 | }) | |
1749 | return chapters | |
1750 | ||
84213ea8 S |
1751 | def _extract_chapters(self, webpage, description, video_id, duration): |
1752 | return (self._extract_chapters_from_json(webpage, video_id, duration) | |
1753 | or self._extract_chapters_from_description(description, duration)) | |
1754 | ||
c5e8d7af | 1755 | def _real_extract(self, url): |
cf7e015f S |
1756 | url, smuggled_data = unsmuggle_url(url, {}) |
1757 | ||
7e8c0af0 | 1758 | proto = ( |
78caa52a PH |
1759 | 'http' if self._downloader.params.get('prefer_insecure', False) |
1760 | else 'https') | |
7e8c0af0 | 1761 | |
7c80519c | 1762 | start_time = None |
297a564b | 1763 | end_time = None |
7c80519c JMF |
1764 | parsed_url = compat_urllib_parse_urlparse(url) |
1765 | for component in [parsed_url.fragment, parsed_url.query]: | |
1766 | query = compat_parse_qs(component) | |
297a564b | 1767 | if start_time is None and 't' in query: |
7c80519c | 1768 | start_time = parse_duration(query['t'][0]) |
2929fa0e JMF |
1769 | if start_time is None and 'start' in query: |
1770 | start_time = parse_duration(query['start'][0]) | |
297a564b JMF |
1771 | if end_time is None and 'end' in query: |
1772 | end_time = parse_duration(query['end'][0]) | |
7c80519c | 1773 | |
c5e8d7af PH |
1774 | # Extract original video URL from URL with redirection, like age verification, using next_url parameter |
1775 | mobj = re.search(self._NEXT_URL_RE, url) | |
1776 | if mobj: | |
7fd002c0 | 1777 | url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/') |
97665381 | 1778 | video_id = self.extract_id(url) |
c5e8d7af PH |
1779 | |
1780 | # Get video webpage | |
aa79ac0c | 1781 | url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id |
011e75e6 S |
1782 | video_webpage, urlh = self._download_webpage_handle(url, video_id) |
1783 | ||
1784 | qs = compat_parse_qs(compat_urllib_parse_urlparse(urlh.geturl()).query) | |
1785 | video_id = qs.get('v', [None])[0] or video_id | |
c5e8d7af PH |
1786 | |
1787 | # Attempt to extract SWF player URL | |
e0df6211 | 1788 | mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) |
c5e8d7af PH |
1789 | if mobj is not None: |
1790 | player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) | |
1791 | else: | |
1792 | player_url = None | |
1793 | ||
d8d24a92 S |
1794 | dash_mpds = [] |
1795 | ||
1796 | def add_dash_mpd(video_info): | |
1797 | dash_mpd = video_info.get('dashmpd') | |
1798 | if dash_mpd and dash_mpd[0] not in dash_mpds: | |
1799 | dash_mpds.append(dash_mpd[0]) | |
1800 | ||
561b456e S |
1801 | def add_dash_mpd_pr(pl_response): |
1802 | dash_mpd = url_or_none(try_get( | |
1803 | pl_response, lambda x: x['streamingData']['dashManifestUrl'], | |
1804 | compat_str)) | |
1805 | if dash_mpd and dash_mpd not in dash_mpds: | |
1806 | dash_mpds.append(dash_mpd) | |
1807 | ||
c7121fa7 S |
1808 | is_live = None |
1809 | view_count = None | |
1810 | ||
1811 | def extract_view_count(v_info): | |
1812 | return int_or_none(try_get(v_info, lambda x: x['view_count'][0])) | |
1813 | ||
c2d125d9 S |
1814 | def extract_player_response(player_response, video_id): |
1815 | pl_response = str_or_none(player_response) | |
1816 | if not pl_response: | |
1817 | return | |
1818 | pl_response = self._parse_json(pl_response, video_id, fatal=False) | |
1819 | if isinstance(pl_response, dict): | |
1820 | add_dash_mpd_pr(pl_response) | |
1821 | return pl_response | |
1822 | ||
dbdaaa23 S |
1823 | player_response = {} |
1824 | ||
c5e8d7af | 1825 | # Get video info |
43ebf77d | 1826 | video_info = {} |
6449cd80 | 1827 | embed_webpage = None |
16ee69c1 | 1828 | if (self._og_search_property('restrictions:age', video_webpage, default=None) == '18+' |
1829 | or re.search(r'player-age-gate-content">', video_webpage) is not None): | |
c108eb73 JMF |
1830 | age_gate = True |
1831 | # We simulate the access to the video from www.youtube.com/v/{video_id} | |
1832 | # this can be viewed without login into Youtube | |
beb95e77 CL |
1833 | url = proto + '://www.youtube.com/embed/%s' % video_id |
1834 | embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage') | |
15707c7e | 1835 | data = compat_urllib_parse_urlencode({ |
2c57c7fa JMF |
1836 | 'video_id': video_id, |
1837 | 'eurl': 'https://youtube.googleapis.com/v/' + video_id, | |
c084c934 | 1838 | 'sts': self._search_regex( |
beb95e77 | 1839 | r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''), |
2c57c7fa | 1840 | }) |
7e8c0af0 | 1841 | video_info_url = proto + '://www.youtube.com/get_video_info?' + data |
d332ec72 S |
1842 | try: |
1843 | video_info_webpage = self._download_webpage( | |
1844 | video_info_url, video_id, | |
1845 | note='Refetching age-gated info webpage', | |
1846 | errnote='unable to download video info webpage') | |
1847 | except ExtractorError: | |
1848 | video_info_webpage = None | |
1849 | if video_info_webpage: | |
1850 | video_info = compat_parse_qs(video_info_webpage) | |
1851 | pl_response = video_info.get('player_response', [None])[0] | |
1852 | player_response = extract_player_response(pl_response, video_id) | |
1853 | add_dash_mpd(video_info) | |
1854 | view_count = extract_view_count(video_info) | |
c108eb73 JMF |
1855 | else: |
1856 | age_gate = False | |
d8d24a92 | 1857 | # Try looking directly into the video webpage |
a72778d3 S |
1858 | ytplayer_config = self._get_ytplayer_config(video_id, video_webpage) |
1859 | if ytplayer_config: | |
4e62ebe2 | 1860 | args = ytplayer_config['args'] |
4c76aa06 | 1861 | if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'): |
d8d24a92 S |
1862 | # Convert to the same format returned by compat_parse_qs |
1863 | video_info = dict((k, [v]) for k, v in args.items()) | |
1864 | add_dash_mpd(video_info) | |
6496ccb4 S |
1865 | # Rental video is not rented but preview is available (e.g. |
1866 | # https://www.youtube.com/watch?v=yYr8q0y5Jfg, | |
067aa17e | 1867 | # https://github.com/ytdl-org/youtube-dl/issues/10532) |
6496ccb4 S |
1868 | if not video_info and args.get('ypc_vid'): |
1869 | return self.url_result( | |
1870 | args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid']) | |
2fe1ff85 JMF |
1871 | if args.get('livestream') == '1' or args.get('live_playback') == 1: |
1872 | is_live = True | |
dbdaaa23 | 1873 | if not player_response: |
c2d125d9 | 1874 | player_response = extract_player_response(args.get('player_response'), video_id) |
0a3cf9ad | 1875 | if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True): |
561b456e | 1876 | add_dash_mpd_pr(player_response) |
bbb7c3f7 YCH |
1877 | |
1878 | def extract_unavailable_message(): | |
0add33ab S |
1879 | messages = [] |
1880 | for tag, kind in (('h1', 'message'), ('div', 'submessage')): | |
1881 | msg = self._html_search_regex( | |
1882 | r'(?s)<{tag}[^>]+id=["\']unavailable-{kind}["\'][^>]*>(.+?)</{tag}>'.format(tag=tag, kind=kind), | |
1883 | video_webpage, 'unavailable %s' % kind, default=None) | |
1884 | if msg: | |
1885 | messages.append(msg) | |
1886 | if messages: | |
1887 | return '\n'.join(messages) | |
bbb7c3f7 | 1888 | |
f93abcf1 | 1889 | if not video_info and not player_response: |
15be3eb5 RA |
1890 | unavailable_message = extract_unavailable_message() |
1891 | if not unavailable_message: | |
1892 | unavailable_message = 'Unable to extract video data' | |
1893 | raise ExtractorError( | |
1894 | 'YouTube said: %s' % unavailable_message, expected=True, video_id=video_id) | |
1895 | ||
f93abcf1 S |
1896 | if not isinstance(video_info, dict): |
1897 | video_info = {} | |
1898 | ||
dbdaaa23 S |
1899 | video_details = try_get( |
1900 | player_response, lambda x: x['videoDetails'], dict) or {} | |
1901 | ||
37357d21 S |
1902 | microformat = try_get( |
1903 | player_response, lambda x: x['microformat']['playerMicroformatRenderer'], dict) or {} | |
1904 | ||
8dbf751a RA |
1905 | video_title = video_info.get('title', [None])[0] or video_details.get('title') |
1906 | if not video_title: | |
cf7e015f S |
1907 | self._downloader.report_warning('Unable to extract video title') |
1908 | video_title = '_' | |
1909 | ||
9cafc3fd | 1910 | description_original = video_description = get_element_by_id("eow-description", video_webpage) |
cf7e015f | 1911 | if video_description: |
fa4bc6e7 RA |
1912 | |
1913 | def replace_url(m): | |
1914 | redir_url = compat_urlparse.urljoin(url, m.group(1)) | |
1915 | parsed_redir_url = compat_urllib_parse_urlparse(redir_url) | |
1916 | if re.search(r'^(?:www\.)?(?:youtube(?:-nocookie)?\.com|youtu\.be)$', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect': | |
1917 | qs = compat_parse_qs(parsed_redir_url.query) | |
1918 | q = qs.get('q') | |
1919 | if q and q[0]: | |
1920 | return q[0] | |
1921 | return redir_url | |
1922 | ||
9cafc3fd | 1923 | description_original = video_description = re.sub(r'''(?x) |
cf7e015f | 1924 | <a\s+ |
25cb7a0e | 1925 | (?:[a-zA-Z-]+="[^"]*"\s+)*? |
23f13e97 | 1926 | (?:title|href)="([^"]+)"\s+ |
25cb7a0e | 1927 | (?:[a-zA-Z-]+="[^"]*"\s+)*? |
525cedb9 | 1928 | class="[^"]*"[^>]*> |
23f13e97 | 1929 | [^<]+\.{3}\s* |
cf7e015f | 1930 | </a> |
fa4bc6e7 | 1931 | ''', replace_url, video_description) |
cf7e015f S |
1932 | video_description = clean_html(video_description) |
1933 | else: | |
a115e075 | 1934 | video_description = video_details.get('shortDescription') or self._html_search_meta('description', video_webpage) |
cf7e015f | 1935 | |
8fe10494 | 1936 | if not smuggled_data.get('force_singlefeed', False): |
5e1eddb9 | 1937 | if not self._downloader.params.get('noplaylist'): |
8fe10494 S |
1938 | multifeed_metadata_list = try_get( |
1939 | player_response, | |
1940 | lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'], | |
1941 | compat_str) or try_get( | |
1942 | video_info, lambda x: x['multifeed_metadata_list'][0], compat_str) | |
1943 | if multifeed_metadata_list: | |
1944 | entries = [] | |
1945 | feed_ids = [] | |
1946 | for feed in multifeed_metadata_list.split(','): | |
1947 | # Unquote should take place before split on comma (,) since textual | |
1948 | # fields may contain comma as well (see | |
067aa17e | 1949 | # https://github.com/ytdl-org/youtube-dl/issues/8536) |
8fe10494 | 1950 | feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed)) |
6b09401b S |
1951 | |
1952 | def feed_entry(name): | |
1953 | return try_get(feed_data, lambda x: x[name][0], compat_str) | |
1954 | ||
1955 | feed_id = feed_entry('id') | |
1956 | if not feed_id: | |
1957 | continue | |
1958 | feed_title = feed_entry('title') | |
1959 | title = video_title | |
1960 | if feed_title: | |
1961 | title += ' (%s)' % feed_title | |
8fe10494 S |
1962 | entries.append({ |
1963 | '_type': 'url_transparent', | |
1964 | 'ie_key': 'Youtube', | |
1965 | 'url': smuggle_url( | |
1966 | '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]), | |
1967 | {'force_singlefeed': True}), | |
6b09401b | 1968 | 'title': title, |
8fe10494 | 1969 | }) |
6b09401b | 1970 | feed_ids.append(feed_id) |
8fe10494 S |
1971 | self.to_screen( |
1972 | 'Downloading multifeed video (%s) - add --no-playlist to just download video %s' | |
1973 | % (', '.join(feed_ids), video_id)) | |
1974 | return self.playlist_result(entries, video_id, video_title, video_description) | |
1975 | else: | |
1976 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
cf7e015f | 1977 | |
c7121fa7 | 1978 | if view_count is None: |
1c9c8de2 | 1979 | view_count = extract_view_count(video_info) |
dbdaaa23 S |
1980 | if view_count is None and video_details: |
1981 | view_count = int_or_none(video_details.get('viewCount')) | |
7b16239a S |
1982 | if view_count is None and microformat: |
1983 | view_count = int_or_none(microformat.get('viewCount')) | |
1d699755 | 1984 | |
27019dbb | 1985 | if is_live is None: |
898238e9 | 1986 | is_live = bool_or_none(video_details.get('isLive')) |
27019dbb | 1987 | |
c5e8d7af PH |
1988 | # Check for "rental" videos |
1989 | if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: | |
067aa17e | 1990 | raise ExtractorError('"rental" videos not supported. See https://github.com/ytdl-org/youtube-dl/issues/359 for more information.', expected=True) |
c5e8d7af | 1991 | |
c63ca0ee S |
1992 | def _extract_filesize(media_url): |
1993 | return int_or_none(self._search_regex( | |
1994 | r'\bclen[=/](\d+)', media_url, 'filesize', default=None)) | |
1995 | ||
bf1317d2 S |
1996 | streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list) or [] |
1997 | streaming_formats.extend(try_get(player_response, lambda x: x['streamingData']['adaptiveFormats'], list) or []) | |
1998 | ||
c5e8d7af PH |
1999 | if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): |
2000 | self.report_rtmp_download() | |
dd27fd17 PH |
2001 | formats = [{ |
2002 | 'format_id': '_rtmp', | |
2003 | 'protocol': 'rtmp', | |
2004 | 'url': video_info['conn'][0], | |
2005 | 'player_url': player_url, | |
2006 | }] | |
bf1317d2 | 2007 | 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 | 2008 | encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0] |
00fe14fc | 2009 | if 'rtmpe%3Dyes' in encoded_url_map: |
067aa17e | 2010 | raise ExtractorError('rtmpe downloads are not supported, see https://github.com/ytdl-org/youtube-dl/issues/343 for more information.', expected=True) |
bf1317d2 | 2011 | formats = [] |
3318832e | 2012 | formats_spec = {} |
82156fdb | 2013 | fmt_list = video_info.get('fmt_list', [''])[0] |
2014 | if fmt_list: | |
2015 | for fmt in fmt_list.split(','): | |
2016 | spec = fmt.split('/') | |
3318832e | 2017 | if len(spec) > 1: |
2018 | width_height = spec[1].split('x') | |
2019 | if len(width_height) == 2: | |
2020 | formats_spec[spec[0]] = { | |
2021 | 'resolution': spec[1], | |
2022 | 'width': int_or_none(width_height[0]), | |
2023 | 'height': int_or_none(width_height[1]), | |
2024 | } | |
bf1317d2 S |
2025 | for fmt in streaming_formats: |
2026 | itag = str_or_none(fmt.get('itag')) | |
2027 | if not itag: | |
201e9eaa | 2028 | continue |
bf1317d2 S |
2029 | quality = fmt.get('quality') |
2030 | quality_label = fmt.get('qualityLabel') or quality | |
2031 | formats_spec[itag] = { | |
2032 | 'asr': int_or_none(fmt.get('audioSampleRate')), | |
2033 | 'filesize': int_or_none(fmt.get('contentLength')), | |
2034 | 'format_note': quality_label, | |
2035 | 'fps': int_or_none(fmt.get('fps')), | |
2036 | 'height': int_or_none(fmt.get('height')), | |
bf1317d2 S |
2037 | # bitrate for itag 43 is always 2147483647 |
2038 | 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None, | |
2039 | 'width': int_or_none(fmt.get('width')), | |
2040 | } | |
2041 | ||
2042 | for fmt in streaming_formats: | |
00eb865b | 2043 | if fmt.get('drmFamilies') or fmt.get('drm_families'): |
bf1317d2 S |
2044 | continue |
2045 | url = url_or_none(fmt.get('url')) | |
2046 | ||
2047 | if not url: | |
fa3db383 | 2048 | cipher = fmt.get('cipher') or fmt.get('signatureCipher') |
bf1317d2 S |
2049 | if not cipher: |
2050 | continue | |
2051 | url_data = compat_parse_qs(cipher) | |
2052 | url = url_or_none(try_get(url_data, lambda x: x['url'][0], compat_str)) | |
2053 | if not url: | |
2054 | continue | |
2055 | else: | |
2056 | cipher = None | |
2057 | url_data = compat_parse_qs(compat_urllib_parse_urlparse(url).query) | |
2058 | ||
2f483bc1 S |
2059 | stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0])) |
2060 | # Unsupported FORMAT_STREAM_TYPE_OTF | |
2061 | if stream_type == 3: | |
2062 | continue | |
6449cd80 | 2063 | |
bf1317d2 S |
2064 | format_id = fmt.get('itag') or url_data['itag'][0] |
2065 | if not format_id: | |
2066 | continue | |
2067 | format_id = compat_str(format_id) | |
a49eccdf | 2068 | |
bf1317d2 S |
2069 | if cipher: |
2070 | if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True): | |
2071 | ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")' | |
2072 | jsplayer_url_json = self._search_regex( | |
2073 | ASSETS_RE, | |
2074 | embed_webpage if age_gate else video_webpage, | |
2075 | 'JS player URL (1)', default=None) | |
2076 | if not jsplayer_url_json and not age_gate: | |
2077 | # We need the embed website after all | |
2078 | if embed_webpage is None: | |
2079 | embed_url = proto + '://www.youtube.com/embed/%s' % video_id | |
2080 | embed_webpage = self._download_webpage( | |
2081 | embed_url, video_id, 'Downloading embed webpage') | |
2082 | jsplayer_url_json = self._search_regex( | |
2083 | ASSETS_RE, embed_webpage, 'JS player URL') | |
2084 | ||
2085 | player_url = json.loads(jsplayer_url_json) | |
cf010131 | 2086 | if player_url is None: |
bf1317d2 S |
2087 | player_url_json = self._search_regex( |
2088 | r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")', | |
2089 | video_webpage, 'age gate player URL') | |
2090 | player_url = json.loads(player_url_json) | |
2091 | ||
2092 | if 'sig' in url_data: | |
2093 | url += '&signature=' + url_data['sig'][0] | |
2094 | elif 's' in url_data: | |
2095 | encrypted_sig = url_data['s'][0] | |
2096 | ||
2097 | if self._downloader.params.get('verbose'): | |
2098 | if player_url is None: | |
bf1317d2 | 2099 | player_desc = 'unknown' |
cf010131 | 2100 | else: |
e40c758c S |
2101 | player_type, player_version = self._extract_player_info(player_url) |
2102 | player_desc = '%s player %s' % ('flash' if player_type == 'swf' else 'html5', player_version) | |
bf1317d2 S |
2103 | parts_sizes = self._signature_cache_id(encrypted_sig) |
2104 | self.to_screen('{%s} signature length %s, %s' % | |
2105 | (format_id, parts_sizes, player_desc)) | |
2106 | ||
2107 | signature = self._decrypt_signature( | |
2108 | encrypted_sig, video_id, player_url, age_gate) | |
2109 | sp = try_get(url_data, lambda x: x['sp'][0], compat_str) or 'signature' | |
2110 | url += '&%s=%s' % (sp, signature) | |
201e9eaa PH |
2111 | if 'ratebypass' not in url: |
2112 | url += '&ratebypass=yes' | |
c9afb51c | 2113 | |
94278f72 YCH |
2114 | dct = { |
2115 | 'format_id': format_id, | |
2116 | 'url': url, | |
2117 | 'player_url': player_url, | |
2118 | } | |
2119 | if format_id in self._formats: | |
2120 | dct.update(self._formats[format_id]) | |
3318832e | 2121 | if format_id in formats_spec: |
2122 | dct.update(formats_spec[format_id]) | |
94278f72 | 2123 | |
aabc2be6 | 2124 | # Some itags are not included in DASH manifest thus corresponding formats will |
067aa17e | 2125 | # lack metadata (see https://github.com/ytdl-org/youtube-dl/pull/5993). |
aabc2be6 S |
2126 | # Trying to extract metadata from url_encoded_fmt_stream_map entry. |
2127 | mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0]) | |
2128 | width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None) | |
94278f72 | 2129 | |
bf1317d2 S |
2130 | if width is None: |
2131 | width = int_or_none(fmt.get('width')) | |
2132 | if height is None: | |
2133 | height = int_or_none(fmt.get('height')) | |
2134 | ||
c63ca0ee S |
2135 | filesize = int_or_none(url_data.get( |
2136 | 'clen', [None])[0]) or _extract_filesize(url) | |
2137 | ||
bf1317d2 S |
2138 | quality = url_data.get('quality', [None])[0] or fmt.get('quality') |
2139 | quality_label = url_data.get('quality_label', [None])[0] or fmt.get('qualityLabel') | |
2140 | ||
4878759f S |
2141 | tbr = (float_or_none(url_data.get('bitrate', [None])[0], 1000) |
2142 | or float_or_none(fmt.get('bitrate'), 1000)) if format_id != '43' else None | |
bf1317d2 | 2143 | fps = int_or_none(url_data.get('fps', [None])[0]) or int_or_none(fmt.get('fps')) |
54fc90aa | 2144 | |
94278f72 | 2145 | more_fields = { |
c63ca0ee | 2146 | 'filesize': filesize, |
bf1317d2 | 2147 | 'tbr': tbr, |
c9afb51c AH |
2148 | 'width': width, |
2149 | 'height': height, | |
bf1317d2 S |
2150 | 'fps': fps, |
2151 | 'format_note': quality_label or quality, | |
c9afb51c | 2152 | } |
94278f72 YCH |
2153 | for key, value in more_fields.items(): |
2154 | if value: | |
2155 | dct[key] = value | |
bf1317d2 | 2156 | type_ = url_data.get('type', [None])[0] or fmt.get('mimeType') |
aabc2be6 S |
2157 | if type_: |
2158 | type_split = type_.split(';') | |
2159 | kind_ext = type_split[0].split('/') | |
2160 | if len(kind_ext) == 2: | |
94278f72 YCH |
2161 | kind, _ = kind_ext |
2162 | dct['ext'] = mimetype2ext(type_split[0]) | |
aabc2be6 S |
2163 | if kind in ('audio', 'video'): |
2164 | codecs = None | |
2165 | for mobj in re.finditer( | |
2166 | r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_): | |
2167 | if mobj.group('key') == 'codecs': | |
2168 | codecs = mobj.group('val') | |
2169 | break | |
2170 | if codecs: | |
6310acf5 | 2171 | dct.update(parse_codecs(codecs)) |
e4a60912 S |
2172 | if dct.get('acodec') == 'none' or dct.get('vcodec') == 'none': |
2173 | dct['downloader_options'] = { | |
2174 | # Youtube throttles chunks >~10M | |
2175 | 'http_chunk_size': 10485760, | |
2176 | } | |
aabc2be6 | 2177 | formats.append(dct) |
c5e8d7af | 2178 | else: |
c3e54389 S |
2179 | manifest_url = ( |
2180 | url_or_none(try_get( | |
2181 | player_response, | |
2182 | lambda x: x['streamingData']['hlsManifestUrl'], | |
3089bc74 S |
2183 | compat_str)) |
2184 | or url_or_none(try_get( | |
c3e54389 S |
2185 | video_info, lambda x: x['hlsvp'][0], compat_str))) |
2186 | if manifest_url: | |
2187 | formats = [] | |
2188 | m3u8_formats = self._extract_m3u8_formats( | |
2189 | manifest_url, video_id, 'mp4', fatal=False) | |
2190 | for a_format in m3u8_formats: | |
2191 | itag = self._search_regex( | |
2192 | r'/itag/(\d+)/', a_format['url'], 'itag', default=None) | |
2193 | if itag: | |
2194 | a_format['format_id'] = itag | |
2195 | if itag in self._formats: | |
2196 | dct = self._formats[itag].copy() | |
2197 | dct.update(a_format) | |
2198 | a_format = dct | |
2199 | a_format['player_url'] = player_url | |
2200 | # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming | |
2201 | a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True' | |
2202 | formats.append(a_format) | |
2203 | else: | |
13577349 | 2204 | error_message = extract_unavailable_message() |
c3e54389 | 2205 | if not error_message: |
13577349 S |
2206 | error_message = clean_html(try_get( |
2207 | player_response, lambda x: x['playabilityStatus']['reason'], | |
2208 | compat_str)) | |
2209 | if not error_message: | |
2210 | error_message = clean_html( | |
2211 | try_get(video_info, lambda x: x['reason'][0], compat_str)) | |
c3e54389 S |
2212 | if error_message: |
2213 | raise ExtractorError(error_message, expected=True) | |
2214 | raise ExtractorError('no conn, hlsvp, hlsManifestUrl or url_encoded_fmt_stream_map information found in video info') | |
c5e8d7af | 2215 | |
7e72694b | 2216 | # uploader |
dbdaaa23 S |
2217 | video_uploader = try_get( |
2218 | video_info, lambda x: x['author'][0], | |
2219 | compat_str) or str_or_none(video_details.get('author')) | |
7e72694b S |
2220 | if video_uploader: |
2221 | video_uploader = compat_urllib_parse_unquote_plus(video_uploader) | |
2222 | else: | |
2223 | self._downloader.report_warning('unable to extract uploader name') | |
2224 | ||
2225 | # uploader_id | |
2226 | video_uploader_id = None | |
2227 | video_uploader_url = None | |
2228 | mobj = re.search( | |
2229 | r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">', | |
2230 | video_webpage) | |
2231 | if mobj is not None: | |
2232 | video_uploader_id = mobj.group('uploader_id') | |
2233 | video_uploader_url = mobj.group('uploader_url') | |
a6211d23 S |
2234 | else: |
2235 | owner_profile_url = url_or_none(microformat.get('ownerProfileUrl')) | |
2236 | if owner_profile_url: | |
2237 | video_uploader_id = self._search_regex( | |
2238 | r'(?:user|channel)/([^/]+)', owner_profile_url, 'uploader id', | |
2239 | default=None) | |
2240 | video_uploader_url = owner_profile_url | |
7e72694b | 2241 | |
b45a9e69 | 2242 | channel_id = ( |
3089bc74 S |
2243 | str_or_none(video_details.get('channelId')) |
2244 | or self._html_search_meta( | |
2245 | 'channelId', video_webpage, 'channel id', default=None) | |
2246 | or self._search_regex( | |
b45a9e69 | 2247 | r'data-channel-external-id=(["\'])(?P<id>(?:(?!\1).)+)\1', |
2248 | video_webpage, 'channel id', default=None, group='id')) | |
dd4c4492 S |
2249 | channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None |
2250 | ||
b477fc13 S |
2251 | thumbnails = [] |
2252 | thumbnails_list = try_get( | |
2253 | video_details, lambda x: x['thumbnail']['thumbnails'], list) or [] | |
2254 | for t in thumbnails_list: | |
2255 | if not isinstance(t, dict): | |
2256 | continue | |
2257 | thumbnail_url = url_or_none(t.get('url')) | |
2258 | if not thumbnail_url: | |
2259 | continue | |
2260 | thumbnails.append({ | |
2261 | 'url': thumbnail_url, | |
2262 | 'width': int_or_none(t.get('width')), | |
2263 | 'height': int_or_none(t.get('height')), | |
2264 | }) | |
2265 | ||
2266 | if not thumbnails: | |
7e72694b | 2267 | video_thumbnail = None |
b477fc13 S |
2268 | # We try first to get a high quality image: |
2269 | m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">', | |
2270 | video_webpage, re.DOTALL) | |
2271 | if m_thumb is not None: | |
2272 | video_thumbnail = m_thumb.group(1) | |
2273 | thumbnail_url = try_get(video_info, lambda x: x['thumbnail_url'][0], compat_str) | |
2274 | if thumbnail_url: | |
2275 | video_thumbnail = compat_urllib_parse_unquote_plus(thumbnail_url) | |
2276 | if video_thumbnail: | |
2277 | thumbnails.append({'url': video_thumbnail}) | |
7e72694b S |
2278 | |
2279 | # upload date | |
2280 | upload_date = self._html_search_meta( | |
2281 | 'datePublished', video_webpage, 'upload date', default=None) | |
2282 | if not upload_date: | |
2283 | upload_date = self._search_regex( | |
2284 | [r'(?s)id="eow-date.*?>(.*?)</span>', | |
2285 | r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'], | |
2286 | video_webpage, 'upload date', default=None) | |
37357d21 S |
2287 | if not upload_date: |
2288 | upload_date = microformat.get('publishDate') or microformat.get('uploadDate') | |
7e72694b S |
2289 | upload_date = unified_strdate(upload_date) |
2290 | ||
2291 | video_license = self._html_search_regex( | |
2292 | r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li', | |
2293 | video_webpage, 'license', default=None) | |
2294 | ||
2295 | m_music = re.search( | |
2296 | r'''(?x) | |
2297 | <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s* | |
2298 | <ul[^>]*>\s* | |
2299 | <li>(?P<title>.+?) | |
2300 | by (?P<creator>.+?) | |
2301 | (?: | |
2302 | \(.+?\)| | |
2303 | <a[^>]* | |
2304 | (?: | |
2305 | \bhref=["\']/red[^>]*>| # drop possible | |
2306 | >\s*Listen ad-free with YouTube Red # YouTube Red ad | |
2307 | ) | |
2308 | .*? | |
2309 | )?</li | |
2310 | ''', | |
2311 | video_webpage) | |
2312 | if m_music: | |
2313 | video_alt_title = remove_quotes(unescapeHTML(m_music.group('title'))) | |
2314 | video_creator = clean_html(m_music.group('creator')) | |
2315 | else: | |
2316 | video_alt_title = video_creator = None | |
2317 | ||
2318 | def extract_meta(field): | |
2319 | return self._html_search_regex( | |
2320 | r'<h4[^>]+class="title"[^>]*>\s*%s\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li>\s*' % field, | |
2321 | video_webpage, field, default=None) | |
2322 | ||
2323 | track = extract_meta('Song') | |
2324 | artist = extract_meta('Artist') | |
92bc97d3 | 2325 | album = extract_meta('Album') |
822b9d9c RA |
2326 | |
2327 | # Youtube Music Auto-generated description | |
92bc97d3 | 2328 | release_date = release_year = None |
822b9d9c RA |
2329 | if video_description: |
2330 | mobj = re.search(r'(?s)Provided to YouTube by [^\n]+\n+(?P<track>[^·]+)·(?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]+))?', video_description) | |
2331 | if mobj: | |
2332 | if not track: | |
2333 | track = mobj.group('track').strip() | |
2334 | if not artist: | |
2335 | artist = mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')) | |
92bc97d3 RA |
2336 | if not album: |
2337 | album = mobj.group('album'.strip()) | |
822b9d9c RA |
2338 | release_year = mobj.group('release_year') |
2339 | release_date = mobj.group('release_date') | |
2340 | if release_date: | |
2341 | release_date = release_date.replace('-', '') | |
2342 | if not release_year: | |
2343 | release_year = int(release_date[:4]) | |
2344 | if release_year: | |
2345 | release_year = int(release_year) | |
7e72694b S |
2346 | |
2347 | m_episode = re.search( | |
2348 | r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>', | |
2349 | video_webpage) | |
2350 | if m_episode: | |
c2dd2dc0 | 2351 | series = unescapeHTML(m_episode.group('series')) |
7e72694b S |
2352 | season_number = int(m_episode.group('season')) |
2353 | episode_number = int(m_episode.group('episode')) | |
2354 | else: | |
2355 | series = season_number = episode_number = None | |
2356 | ||
2357 | m_cat_container = self._search_regex( | |
2358 | r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>', | |
2359 | video_webpage, 'categories', default=None) | |
dbeafce5 | 2360 | category = None |
7e72694b S |
2361 | if m_cat_container: |
2362 | category = self._html_search_regex( | |
2363 | r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category', | |
2364 | default=None) | |
dbeafce5 S |
2365 | if not category: |
2366 | category = try_get( | |
2367 | microformat, lambda x: x['category'], compat_str) | |
2368 | video_categories = None if category is None else [category] | |
7e72694b S |
2369 | |
2370 | video_tags = [ | |
2371 | unescapeHTML(m.group('content')) | |
2372 | for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)] | |
dbeafce5 S |
2373 | if not video_tags: |
2374 | video_tags = try_get(video_details, lambda x: x['keywords'], list) | |
7e72694b S |
2375 | |
2376 | def _extract_count(count_name): | |
2377 | return str_to_int(self._search_regex( | |
2378 | r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>' | |
2379 | % re.escape(count_name), | |
2380 | video_webpage, count_name, default=None)) | |
2381 | ||
2382 | like_count = _extract_count('like') | |
2383 | dislike_count = _extract_count('dislike') | |
2384 | ||
dbdaaa23 S |
2385 | if view_count is None: |
2386 | view_count = str_to_int(self._search_regex( | |
2387 | r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage, | |
2388 | 'view count', default=None)) | |
2389 | ||
bf3c9326 S |
2390 | average_rating = ( |
2391 | float_or_none(video_details.get('averageRating')) | |
2392 | or try_get(video_info, lambda x: float_or_none(x['avg_rating'][0]))) | |
2393 | ||
7e72694b S |
2394 | # subtitles |
2395 | video_subtitles = self.extract_subtitles(video_id, video_webpage) | |
2396 | automatic_captions = self.extract_automatic_captions(video_id, video_webpage) | |
2397 | ||
2398 | video_duration = try_get( | |
2399 | video_info, lambda x: int_or_none(x['length_seconds'][0])) | |
dbdaaa23 S |
2400 | if not video_duration: |
2401 | video_duration = int_or_none(video_details.get('lengthSeconds')) | |
7e72694b S |
2402 | if not video_duration: |
2403 | video_duration = parse_duration(self._html_search_meta( | |
2404 | 'duration', video_webpage, 'video duration')) | |
2405 | ||
2406 | # annotations | |
2407 | video_annotations = None | |
2408 | if self._downloader.params.get('writeannotations', False): | |
64b6a4e9 RA |
2409 | xsrf_token = self._search_regex( |
2410 | r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P<xsrf_token>[A-Za-z0-9+/=]+)\2', | |
2411 | video_webpage, 'xsrf token', group='xsrf_token', fatal=False) | |
2412 | invideo_url = try_get( | |
2413 | player_response, lambda x: x['annotations'][0]['playerAnnotationsUrlsRenderer']['invideoUrl'], compat_str) | |
2414 | if xsrf_token and invideo_url: | |
2415 | xsrf_field_name = self._search_regex( | |
2416 | r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P<xsrf_field_name>\w+)\2', | |
2417 | video_webpage, 'xsrf field name', | |
2418 | group='xsrf_field_name', default='session_token') | |
2419 | video_annotations = self._download_webpage( | |
2420 | self._proto_relative_url(invideo_url), | |
2421 | video_id, note='Downloading annotations', | |
2422 | errnote='Unable to download video annotations', fatal=False, | |
2423 | data=urlencode_postdata({xsrf_field_name: xsrf_token})) | |
7e72694b | 2424 | |
84213ea8 | 2425 | chapters = self._extract_chapters(video_webpage, description_original, video_id, video_duration) |
7e72694b | 2426 | |
dd27fd17 | 2427 | # Look for the DASH manifest |
203fb43f | 2428 | if self._downloader.params.get('youtube_include_dash_manifest', True): |
77c6fb5b | 2429 | dash_mpd_fatal = True |
8ff648e4 | 2430 | for mpd_url in dash_mpds: |
d8d24a92 | 2431 | dash_formats = {} |
774e208f | 2432 | try: |
05d0d131 YCH |
2433 | def decrypt_sig(mobj): |
2434 | s = mobj.group(1) | |
2435 | dec_s = self._decrypt_signature(s, video_id, player_url, age_gate) | |
2436 | return '/signature/%s' % dec_s | |
2437 | ||
8ff648e4 | 2438 | mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url) |
2d2fa82d | 2439 | |
8ff648e4 | 2440 | for df in self._extract_mpd_formats( |
2441 | mpd_url, video_id, fatal=dash_mpd_fatal, | |
2442 | formats_dict=self._formats): | |
c63ca0ee S |
2443 | if not df.get('filesize'): |
2444 | df['filesize'] = _extract_filesize(df['url']) | |
d8d24a92 S |
2445 | # Do not overwrite DASH format found in some previous DASH manifest |
2446 | if df['format_id'] not in dash_formats: | |
2447 | dash_formats[df['format_id']] = df | |
77c6fb5b S |
2448 | # Additional DASH manifests may end up in HTTP Error 403 therefore |
2449 | # allow them to fail without bug report message if we already have | |
2450 | # some DASH manifest succeeded. This is temporary workaround to reduce | |
2451 | # burst of bug reports until we figure out the reason and whether it | |
2452 | # can be fixed at all. | |
2453 | dash_mpd_fatal = False | |
774e208f PH |
2454 | except (ExtractorError, KeyError) as e: |
2455 | self.report_warning( | |
2456 | 'Skipping DASH manifest: %r' % e, video_id) | |
d8d24a92 | 2457 | if dash_formats: |
04b3b3df JMF |
2458 | # Remove the formats we found through non-DASH, they |
2459 | # contain less info and it can be wrong, because we use | |
2460 | # fixed values (for example the resolution). See | |
067aa17e | 2461 | # https://github.com/ytdl-org/youtube-dl/issues/5774 for an |
04b3b3df | 2462 | # example. |
d80265cc | 2463 | formats = [f for f in formats if f['format_id'] not in dash_formats.keys()] |
d8d24a92 | 2464 | formats.extend(dash_formats.values()) |
d80044c2 | 2465 | |
6271f1ca PH |
2466 | # Check for malformed aspect ratio |
2467 | stretched_m = re.search( | |
2468 | r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">', | |
2469 | video_webpage) | |
2470 | if stretched_m: | |
313dfc45 LL |
2471 | w = float(stretched_m.group('w')) |
2472 | h = float(stretched_m.group('h')) | |
5faf9fed S |
2473 | # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0). |
2474 | # We will only process correct ratios. | |
313dfc45 | 2475 | if w > 0 and h > 0: |
41f24c32 | 2476 | ratio = w / h |
313dfc45 LL |
2477 | for f in formats: |
2478 | if f.get('vcodec') != 'none': | |
2479 | f['stretched_ratio'] = ratio | |
6271f1ca | 2480 | |
026fbedc | 2481 | if not formats: |
43ebf77d S |
2482 | if 'reason' in video_info: |
2483 | if 'The uploader has not made this video available in your country.' in video_info['reason']: | |
2484 | regions_allowed = self._html_search_meta( | |
2485 | 'regionsAllowed', video_webpage, default=None) | |
2486 | countries = regions_allowed.split(',') if regions_allowed else None | |
2487 | self.raise_geo_restricted( | |
2488 | msg=video_info['reason'][0], countries=countries) | |
2489 | reason = video_info['reason'][0] | |
2490 | if 'Invalid parameters' in reason: | |
2491 | unavailable_message = extract_unavailable_message() | |
2492 | if unavailable_message: | |
2493 | reason = unavailable_message | |
2494 | raise ExtractorError( | |
2495 | 'YouTube said: %s' % reason, | |
2496 | expected=True, video_id=video_id) | |
2497 | if video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos']): | |
2498 | raise ExtractorError('This video is DRM protected.', expected=True) | |
0d297518 | 2499 | |
4bcc7bd1 | 2500 | self._sort_formats(formats) |
4ea3be0a | 2501 | |
21c340b8 | 2502 | self.mark_watched(video_id, video_info, player_response) |
d77ab8e2 | 2503 | |
4ea3be0a | 2504 | return { |
8bcc8756 JW |
2505 | 'id': video_id, |
2506 | 'uploader': video_uploader, | |
2507 | 'uploader_id': video_uploader_id, | |
fd050249 | 2508 | 'uploader_url': video_uploader_url, |
dd4c4492 S |
2509 | 'channel_id': channel_id, |
2510 | 'channel_url': channel_url, | |
8bcc8756 | 2511 | 'upload_date': upload_date, |
7caf9830 | 2512 | 'license': video_license, |
936784b2 | 2513 | 'creator': video_creator or artist, |
8bcc8756 | 2514 | 'title': video_title, |
936784b2 | 2515 | 'alt_title': video_alt_title or track, |
b477fc13 | 2516 | 'thumbnails': thumbnails, |
8bcc8756 JW |
2517 | 'description': video_description, |
2518 | 'categories': video_categories, | |
000b6b5a | 2519 | 'tags': video_tags, |
8bcc8756 | 2520 | 'subtitles': video_subtitles, |
360e1ca5 | 2521 | 'automatic_captions': automatic_captions, |
8bcc8756 JW |
2522 | 'duration': video_duration, |
2523 | 'age_limit': 18 if age_gate else 0, | |
2524 | 'annotations': video_annotations, | |
9cafc3fd | 2525 | 'chapters': chapters, |
7e8c0af0 | 2526 | 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id, |
8bcc8756 | 2527 | 'view_count': view_count, |
4ea3be0a | 2528 | 'like_count': like_count, |
2529 | 'dislike_count': dislike_count, | |
bf3c9326 | 2530 | 'average_rating': average_rating, |
8bcc8756 | 2531 | 'formats': formats, |
2fe1ff85 | 2532 | 'is_live': is_live, |
7c80519c | 2533 | 'start_time': start_time, |
297a564b | 2534 | 'end_time': end_time, |
12afdc2a S |
2535 | 'series': series, |
2536 | 'season_number': season_number, | |
2537 | 'episode_number': episode_number, | |
936784b2 S |
2538 | 'track': track, |
2539 | 'artist': artist, | |
5caabd3c | 2540 | 'album': album, |
2541 | 'release_date': release_date, | |
2542 | 'release_year': release_year, | |
4ea3be0a | 2543 | } |
c5e8d7af | 2544 | |
5f6a1245 | 2545 | |
8e7aad20 | 2546 | class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): |
78caa52a | 2547 | IE_DESC = 'YouTube.com playlists' |
d67cc9fa | 2548 | _VALID_URL = r"""(?x)(?: |
c5e8d7af PH |
2549 | (?:https?://)? |
2550 | (?:\w+\.)? | |
c5e8d7af | 2551 | (?: |
c0345b82 | 2552 | (?: |
66b48727 | 2553 | youtube(?:kids)?\.com| |
c0345b82 S |
2554 | invidio\.us |
2555 | ) | |
2556 | / | |
feaa5ad7 | 2557 | (?: |
87dadd45 | 2558 | (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11})) |
feaa5ad7 S |
2559 | \? (?:.*?[&;])*? (?:p|a|list)= |
2560 | | p/ | |
2561 | )| | |
2562 | youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist= | |
c5e8d7af | 2563 | ) |
d67cc9fa | 2564 | ( |
66b48727 | 2565 | (?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)?[0-9A-Za-z-_]{10,} |
5f6a1245 | 2566 | # Top tracks, they can also include dots |
d67cc9fa JMF |
2567 | |(?:MC)[\w\.]* |
2568 | ) | |
c5e8d7af PH |
2569 | .* |
2570 | | | |
d0ba5587 S |
2571 | (%(playlist_id)s) |
2572 | )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE} | |
8d81f3e3 | 2573 | _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s' |
351f37c0 S |
2574 | _VIDEO_RE_TPL = r'href="\s*/watch\?v=%s(?:&(?:[^"]*?index=(?P<index>\d+))?(?:[^>]+>(?P<title>[^<]+))?)?' |
2575 | _VIDEO_RE = _VIDEO_RE_TPL % r'(?P<id>[0-9A-Za-z_-]{11})' | |
78caa52a | 2576 | IE_NAME = 'youtube:playlist' |
81127aa5 | 2577 | _TESTS = [{ |
0e30a7b9 | 2578 | 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', |
81127aa5 | 2579 | 'info_dict': { |
0e30a7b9 | 2580 | 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', |
2581 | 'uploader': 'Sergey M.', | |
2582 | 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', | |
2583 | 'title': 'youtube-dl public playlist', | |
81127aa5 | 2584 | }, |
0e30a7b9 | 2585 | 'playlist_count': 1, |
9291475f | 2586 | }, { |
0e30a7b9 | 2587 | 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', |
9291475f | 2588 | 'info_dict': { |
0e30a7b9 | 2589 | 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', |
2590 | 'uploader': 'Sergey M.', | |
2591 | 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', | |
2592 | 'title': 'youtube-dl empty playlist', | |
9291475f PH |
2593 | }, |
2594 | 'playlist_count': 0, | |
2595 | }, { | |
2596 | 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', | |
2597 | 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
2598 | 'info_dict': { | |
2599 | 'title': '29C3: Not my department', | |
acf757f4 | 2600 | 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', |
13a75688 S |
2601 | 'uploader': 'Christiaan008', |
2602 | 'uploader_id': 'ChRiStIaAn008', | |
9291475f | 2603 | }, |
0e30a7b9 | 2604 | 'playlist_count': 96, |
9291475f PH |
2605 | }, { |
2606 | 'note': 'issue #673', | |
2607 | 'url': 'PLBB231211A4F62143', | |
2608 | 'info_dict': { | |
f46a8702 | 2609 | 'title': '[OLD]Team Fortress 2 (Class-based LP)', |
acf757f4 | 2610 | 'id': 'PLBB231211A4F62143', |
13a75688 S |
2611 | 'uploader': 'Wickydoo', |
2612 | 'uploader_id': 'Wickydoo', | |
9291475f PH |
2613 | }, |
2614 | 'playlist_mincount': 26, | |
2615 | }, { | |
2616 | 'note': 'Large playlist', | |
2617 | 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', | |
2618 | 'info_dict': { | |
2619 | 'title': 'Uploads from Cauchemar', | |
acf757f4 | 2620 | 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', |
13a75688 S |
2621 | 'uploader': 'Cauchemar', |
2622 | 'uploader_id': 'Cauchemar89', | |
9291475f PH |
2623 | }, |
2624 | 'playlist_mincount': 799, | |
2625 | }, { | |
2626 | 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
2627 | 'info_dict': { | |
2628 | 'title': 'YDL_safe_search', | |
acf757f4 | 2629 | 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', |
9291475f PH |
2630 | }, |
2631 | 'playlist_count': 2, | |
4201ba13 | 2632 | 'skip': 'This playlist is private', |
ac7553d0 PH |
2633 | }, { |
2634 | 'note': 'embedded', | |
2d3d2997 | 2635 | 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', |
ac7553d0 PH |
2636 | 'playlist_count': 4, |
2637 | 'info_dict': { | |
2638 | 'title': 'JODA15', | |
acf757f4 | 2639 | 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', |
13a75688 S |
2640 | 'uploader': 'milan', |
2641 | 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw', | |
ac7553d0 | 2642 | } |
87dadd45 S |
2643 | }, { |
2644 | 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', | |
2645 | 'playlist_mincount': 485, | |
2646 | 'info_dict': { | |
13a75688 | 2647 | 'title': '2018 Chinese New Singles (11/6 updated)', |
87dadd45 | 2648 | 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', |
13a75688 S |
2649 | 'uploader': 'LBK', |
2650 | 'uploader_id': 'sdragonfang', | |
87dadd45 | 2651 | } |
6b08cdf6 PH |
2652 | }, { |
2653 | 'note': 'Embedded SWF player', | |
2d3d2997 | 2654 | 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0', |
6b08cdf6 PH |
2655 | 'playlist_count': 4, |
2656 | 'info_dict': { | |
2657 | 'title': 'JODA7', | |
acf757f4 | 2658 | 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ', |
13a75688 S |
2659 | }, |
2660 | 'skip': 'This playlist does not exist', | |
4b7df0d3 JMF |
2661 | }, { |
2662 | 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', | |
2663 | 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', | |
2664 | 'info_dict': { | |
acf757f4 PH |
2665 | 'title': 'Uploads from Interstellar Movie', |
2666 | 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', | |
13a75688 S |
2667 | 'uploader': 'Interstellar Movie', |
2668 | 'uploader_id': 'InterstellarMovie1', | |
4b7df0d3 | 2669 | }, |
481cc733 | 2670 | 'playlist_mincount': 21, |
dacb3a86 S |
2671 | }, { |
2672 | # Playlist URL that does not actually serve a playlist | |
2673 | 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4', | |
2674 | 'info_dict': { | |
2675 | 'id': 'FqZTN594JQw', | |
2676 | 'ext': 'webm', | |
2677 | 'title': "Smiley's People 01 detective, Adventure Series, Action", | |
2678 | 'uploader': 'STREEM', | |
2679 | 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng', | |
ec85ded8 | 2680 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng', |
dacb3a86 S |
2681 | 'upload_date': '20150526', |
2682 | 'license': 'Standard YouTube License', | |
2683 | 'description': 'md5:507cdcb5a49ac0da37a920ece610be80', | |
2684 | 'categories': ['People & Blogs'], | |
2685 | 'tags': list, | |
dbdaaa23 | 2686 | 'view_count': int, |
dacb3a86 S |
2687 | 'like_count': int, |
2688 | 'dislike_count': int, | |
2689 | }, | |
2690 | 'params': { | |
2691 | 'skip_download': True, | |
2692 | }, | |
13a75688 | 2693 | 'skip': 'This video is not available.', |
dacb3a86 | 2694 | 'add_ie': [YoutubeIE.ie_key()], |
481cc733 S |
2695 | }, { |
2696 | 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5', | |
2697 | 'info_dict': { | |
2698 | 'id': 'yeWKywCrFtk', | |
2699 | 'ext': 'mp4', | |
2700 | 'title': 'Small Scale Baler and Braiding Rugs', | |
2701 | 'uploader': 'Backus-Page House Museum', | |
2702 | 'uploader_id': 'backuspagemuseum', | |
ec85ded8 | 2703 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum', |
481cc733 | 2704 | 'upload_date': '20161008', |
481cc733 S |
2705 | 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a', |
2706 | 'categories': ['Nonprofits & Activism'], | |
2707 | 'tags': list, | |
2708 | 'like_count': int, | |
2709 | 'dislike_count': int, | |
2710 | }, | |
2711 | 'params': { | |
2712 | 'noplaylist': True, | |
2713 | 'skip_download': True, | |
2714 | }, | |
2e18adec S |
2715 | }, { |
2716 | # https://github.com/ytdl-org/youtube-dl/issues/21844 | |
2717 | 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', | |
2718 | 'info_dict': { | |
2719 | 'title': 'Data Analysis with Dr Mike Pound', | |
2720 | 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', | |
2721 | 'uploader_id': 'Computerphile', | |
2722 | 'uploader': 'Computerphile', | |
2723 | }, | |
2724 | 'playlist_mincount': 11, | |
feaa5ad7 S |
2725 | }, { |
2726 | 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21', | |
2727 | 'only_matching': True, | |
a6857510 S |
2728 | }, { |
2729 | 'url': 'TLGGrESM50VT6acwMjAyMjAxNw', | |
2730 | 'only_matching': True, | |
409b9324 S |
2731 | }, { |
2732 | # music album playlist | |
2733 | 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM', | |
2734 | 'only_matching': True, | |
c0345b82 S |
2735 | }, { |
2736 | 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU', | |
2737 | 'only_matching': True, | |
66b48727 RA |
2738 | }, { |
2739 | 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g', | |
2740 | 'only_matching': True, | |
81127aa5 | 2741 | }] |
c5e8d7af | 2742 | |
880e1c52 JMF |
2743 | def _real_initialize(self): |
2744 | self._login() | |
2745 | ||
351f37c0 S |
2746 | def extract_videos_from_page(self, page): |
2747 | ids_in_page = [] | |
2748 | titles_in_page = [] | |
2749 | ||
2750 | for item in re.findall( | |
2751 | r'(<[^>]*\bdata-video-id\s*=\s*["\'][0-9A-Za-z_-]{11}[^>]+>)', page): | |
2752 | attrs = extract_attributes(item) | |
2753 | video_id = attrs['data-video-id'] | |
2754 | video_title = unescapeHTML(attrs.get('data-title')) | |
2755 | if video_title: | |
2756 | video_title = video_title.strip() | |
2757 | ids_in_page.append(video_id) | |
2758 | titles_in_page.append(video_title) | |
2759 | ||
2760 | # Fallback with old _VIDEO_RE | |
2761 | self.extract_videos_from_page_impl( | |
2762 | self._VIDEO_RE, page, ids_in_page, titles_in_page) | |
2763 | ||
2764 | # Relaxed fallbacks | |
2765 | self.extract_videos_from_page_impl( | |
2766 | r'href="\s*/watch\?v\s*=\s*(?P<id>[0-9A-Za-z_-]{11})', page, | |
2767 | ids_in_page, titles_in_page) | |
2768 | self.extract_videos_from_page_impl( | |
2769 | r'data-video-ids\s*=\s*["\'](?P<id>[0-9A-Za-z_-]{11})', page, | |
2770 | ids_in_page, titles_in_page) | |
2771 | ||
2772 | return zip(ids_in_page, titles_in_page) | |
2773 | ||
652cdaa2 | 2774 | def _extract_mix(self, playlist_id): |
99209c29 | 2775 | # The mixes are generated from a single video |
652cdaa2 | 2776 | # the id of the playlist is just 'RD' + video_id |
1b6182d8 JMF |
2777 | ids = [] |
2778 | last_id = playlist_id[-11:] | |
2779 | for n in itertools.count(1): | |
07af16b9 | 2780 | url = 'https://www.youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id) |
1b6182d8 JMF |
2781 | webpage = self._download_webpage( |
2782 | url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n)) | |
2783 | new_ids = orderedSet(re.findall( | |
2784 | r'''(?xs)data-video-username=".*?".*? | |
2785 | href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id), | |
2786 | webpage)) | |
2787 | # Fetch new pages until all the videos are repeated, it seems that | |
2788 | # there are always 51 unique videos. | |
2789 | new_ids = [_id for _id in new_ids if _id not in ids] | |
2790 | if not new_ids: | |
2791 | break | |
2792 | ids.extend(new_ids) | |
2793 | last_id = ids[-1] | |
2794 | ||
2795 | url_results = self._ids_to_results(ids) | |
2796 | ||
bc2f773b | 2797 | search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage) |
c9cc0bf5 | 2798 | title_span = ( |
3089bc74 S |
2799 | search_title('playlist-title') |
2800 | or search_title('title long-title') | |
2801 | or search_title('title')) | |
76d1700b | 2802 | title = clean_html(title_span) |
652cdaa2 JMF |
2803 | |
2804 | return self.playlist_result(url_results, playlist_id, title) | |
2805 | ||
448830ce | 2806 | def _extract_playlist(self, playlist_id): |
dbb94fb0 S |
2807 | url = self._TEMPLATE_URL % playlist_id |
2808 | page = self._download_webpage(url, playlist_id) | |
dbb94fb0 | 2809 | |
067aa17e | 2810 | # the yt-alert-message now has tabindex attribute (see https://github.com/ytdl-org/youtube-dl/issues/11604) |
8bc0800d | 2811 | for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page): |
39b62db1 YCH |
2812 | match = match.strip() |
2813 | # Check if the playlist exists or is private | |
4201ba13 S |
2814 | mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match) |
2815 | if mobj: | |
2816 | reason = mobj.group('reason') | |
2817 | message = 'This playlist %s' % reason | |
2818 | if 'private' in reason: | |
2819 | message += ', use --username or --netrc to access it' | |
2820 | message += '.' | |
2821 | raise ExtractorError(message, expected=True) | |
39b62db1 YCH |
2822 | elif re.match(r'[^<]*Invalid parameters[^<]*', match): |
2823 | raise ExtractorError( | |
2824 | 'Invalid parameters. Maybe URL is incorrect.', | |
2825 | expected=True) | |
2826 | elif re.match(r'[^<]*Choose your language[^<]*', match): | |
2827 | continue | |
2828 | else: | |
2829 | self.report_warning('Youtube gives an alert message: ' + match) | |
10c0e2d8 | 2830 | |
dbb94fb0 | 2831 | playlist_title = self._html_search_regex( |
63b4295d | 2832 | r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>', |
dacb3a86 | 2833 | page, 'title', default=None) |
c5e8d7af | 2834 | |
07aeced6 | 2835 | _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref=' |
4e3f1f04 | 2836 | uploader = self._html_search_regex( |
07aeced6 S |
2837 | r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE, |
2838 | page, 'uploader', default=None) | |
2839 | mobj = re.search( | |
2840 | r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE, | |
2841 | page) | |
2842 | if mobj: | |
2843 | uploader_id = mobj.group('uploader_id') | |
2844 | uploader_url = compat_urlparse.urljoin(url, mobj.group('path')) | |
2845 | else: | |
2846 | uploader_id = uploader_url = None | |
2847 | ||
dacb3a86 S |
2848 | has_videos = True |
2849 | ||
2850 | if not playlist_title: | |
2851 | try: | |
2852 | # Some playlist URLs don't actually serve a playlist (e.g. | |
2853 | # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4) | |
2854 | next(self._entries(page, playlist_id)) | |
2855 | except StopIteration: | |
2856 | has_videos = False | |
2857 | ||
07aeced6 | 2858 | playlist = self.playlist_result( |
dacb3a86 | 2859 | self._entries(page, playlist_id), playlist_id, playlist_title) |
07aeced6 S |
2860 | playlist.update({ |
2861 | 'uploader': uploader, | |
2862 | 'uploader_id': uploader_id, | |
2863 | 'uploader_url': uploader_url, | |
2864 | }) | |
2865 | ||
2866 | return has_videos, playlist | |
c5e8d7af | 2867 | |
ebf1b291 | 2868 | def _check_download_just_video(self, url, playlist_id): |
448830ce S |
2869 | # Check if it's a video-specific URL |
2870 | query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) | |
481cc733 | 2871 | video_id = query_dict.get('v', [None])[0] or self._search_regex( |
87dadd45 | 2872 | r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url, |
481cc733 S |
2873 | 'video id', default=None) |
2874 | if video_id: | |
448830ce S |
2875 | if self._downloader.params.get('noplaylist'): |
2876 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
dacb3a86 | 2877 | return video_id, self.url_result(video_id, 'Youtube', video_id=video_id) |
448830ce S |
2878 | else: |
2879 | self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) | |
dacb3a86 S |
2880 | return video_id, None |
2881 | return None, None | |
448830ce | 2882 | |
ebf1b291 S |
2883 | def _real_extract(self, url): |
2884 | # Extract playlist id | |
2885 | mobj = re.match(self._VALID_URL, url) | |
2886 | if mobj is None: | |
2887 | raise ExtractorError('Invalid URL: %s' % url) | |
2888 | playlist_id = mobj.group(1) or mobj.group(2) | |
2889 | ||
dacb3a86 | 2890 | video_id, video = self._check_download_just_video(url, playlist_id) |
ebf1b291 S |
2891 | if video: |
2892 | return video | |
2893 | ||
466a6145 | 2894 | if playlist_id.startswith(('RD', 'UL', 'PU')): |
448830ce S |
2895 | # Mixes require a custom extraction process |
2896 | return self._extract_mix(playlist_id) | |
2897 | ||
dacb3a86 S |
2898 | has_videos, playlist = self._extract_playlist(playlist_id) |
2899 | if has_videos or not video_id: | |
2900 | return playlist | |
2901 | ||
2902 | # Some playlist URLs don't actually serve a playlist (see | |
067aa17e | 2903 | # https://github.com/ytdl-org/youtube-dl/issues/10537). |
dacb3a86 S |
2904 | # Fallback to plain video extraction if there is a video id |
2905 | # along with playlist id. | |
2906 | return self.url_result(video_id, 'Youtube', video_id=video_id) | |
448830ce | 2907 | |
c5e8d7af | 2908 | |
648e6a1f | 2909 | class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor): |
78caa52a | 2910 | IE_DESC = 'YouTube.com channels' |
66b48727 | 2911 | _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie|kids)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)' |
eb0f3e7e | 2912 | _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos' |
648e6a1f | 2913 | _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?' |
78caa52a | 2914 | IE_NAME = 'youtube:channel' |
cdc628a4 PH |
2915 | _TESTS = [{ |
2916 | 'note': 'paginated channel', | |
2917 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
2918 | 'playlist_mincount': 91, | |
acf757f4 | 2919 | 'info_dict': { |
9170ca5b JMF |
2920 | 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w', |
2921 | 'title': 'Uploads from lex will', | |
13a75688 S |
2922 | 'uploader': 'lex will', |
2923 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
acf757f4 | 2924 | } |
5c43afd4 JMF |
2925 | }, { |
2926 | 'note': 'Age restricted channel', | |
2927 | # from https://www.youtube.com/user/DeusExOfficial | |
2928 | 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w', | |
2929 | 'playlist_mincount': 64, | |
2930 | 'info_dict': { | |
2931 | 'id': 'UUs0ifCMCm1icqRbqhUINa0w', | |
2932 | 'title': 'Uploads from Deus Ex', | |
13a75688 S |
2933 | 'uploader': 'Deus Ex', |
2934 | 'uploader_id': 'DeusExOfficial', | |
5c43afd4 | 2935 | }, |
cd5a74a2 S |
2936 | }, { |
2937 | 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA', | |
2938 | 'only_matching': True, | |
66b48727 RA |
2939 | }, { |
2940 | 'url': 'https://www.youtubekids.com/channel/UCyu8StPfZWapR6rfW_JgqcA', | |
2941 | 'only_matching': True, | |
cdc628a4 | 2942 | }] |
c5e8d7af | 2943 | |
e462474e S |
2944 | @classmethod |
2945 | def suitable(cls, url): | |
f07e276a S |
2946 | return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url) |
2947 | else super(YoutubeChannelIE, cls).suitable(url)) | |
e462474e | 2948 | |
9558dcec S |
2949 | def _build_template_url(self, url, channel_id): |
2950 | return self._TEMPLATE_URL % channel_id | |
2951 | ||
c5e8d7af | 2952 | def _real_extract(self, url): |
9ff67727 | 2953 | channel_id = self._match_id(url) |
c5e8d7af | 2954 | |
9558dcec | 2955 | url = self._build_template_url(url, channel_id) |
386bdfa6 S |
2956 | |
2957 | # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778) | |
2958 | # Workaround by extracting as a playlist if managed to obtain channel playlist URL | |
2959 | # otherwise fallback on channel by page extraction | |
2960 | channel_page = self._download_webpage( | |
2961 | url + '?view=57', channel_id, | |
2962 | 'Downloading channel page', fatal=False) | |
2b3c2546 PH |
2963 | if channel_page is False: |
2964 | channel_playlist_id = False | |
2965 | else: | |
2966 | channel_playlist_id = self._html_search_meta( | |
2967 | 'channelId', channel_page, 'channel id', default=None) | |
2968 | if not channel_playlist_id: | |
73c4ac2c S |
2969 | channel_url = self._html_search_meta( |
2970 | ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'), | |
2971 | channel_page, 'channel url', default=None) | |
2972 | if channel_url: | |
2973 | channel_playlist_id = self._search_regex( | |
2974 | r'vnd\.youtube://user/([0-9A-Za-z_-]+)', | |
2975 | channel_url, 'channel id', default=None) | |
386bdfa6 S |
2976 | if channel_playlist_id and channel_playlist_id.startswith('UC'): |
2977 | playlist_id = 'UU' + channel_playlist_id[2:] | |
d2a9de78 IK |
2978 | return self.url_result( |
2979 | compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist') | |
386bdfa6 | 2980 | |
60bf45c8 | 2981 | channel_page = self._download_webpage(url, channel_id, 'Downloading page #1') |
31812a9e PH |
2982 | autogenerated = re.search(r'''(?x) |
2983 | class="[^"]*?(?: | |
2984 | channel-header-autogenerated-label| | |
2985 | yt-channel-title-autogenerated | |
2986 | )[^"]*"''', channel_page) is not None | |
c5e8d7af | 2987 | |
b9643eed JMF |
2988 | if autogenerated: |
2989 | # The videos are contained in a single page | |
2990 | # the ajax pages can't be used, they are empty | |
b82f815f | 2991 | entries = [ |
fb69240c S |
2992 | self.url_result( |
2993 | video_id, 'Youtube', video_id=video_id, | |
2994 | video_title=video_title) | |
8f02ad4f | 2995 | for video_id, video_title in self.extract_videos_from_page(channel_page)] |
b82f815f PH |
2996 | return self.playlist_result(entries, channel_id) |
2997 | ||
73c4ac2c S |
2998 | try: |
2999 | next(self._entries(channel_page, channel_id)) | |
3000 | except StopIteration: | |
3001 | alert_message = self._html_search_regex( | |
3002 | r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>', | |
3003 | channel_page, 'alert', default=None, group='alert') | |
3004 | if alert_message: | |
3005 | raise ExtractorError('Youtube said: %s' % alert_message, expected=True) | |
3006 | ||
648e6a1f | 3007 | return self.playlist_result(self._entries(channel_page, channel_id), channel_id) |
c5e8d7af PH |
3008 | |
3009 | ||
eb0f3e7e | 3010 | class YoutubeUserIE(YoutubeChannelIE): |
78caa52a | 3011 | IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)' |
67171ed7 | 3012 | _VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:(?P<user>user|c)/)?(?!(?:attribution_link|watch|results|shared)(?:$|[^a-z_A-Z0-9%-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_%-]+)' |
9558dcec | 3013 | _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos' |
78caa52a | 3014 | IE_NAME = 'youtube:user' |
c5e8d7af | 3015 | |
cdc628a4 PH |
3016 | _TESTS = [{ |
3017 | 'url': 'https://www.youtube.com/user/TheLinuxFoundation', | |
3018 | 'playlist_mincount': 320, | |
3019 | 'info_dict': { | |
73c4ac2c S |
3020 | 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ', |
3021 | 'title': 'Uploads from The Linux Foundation', | |
13a75688 S |
3022 | 'uploader': 'The Linux Foundation', |
3023 | 'uploader_id': 'TheLinuxFoundation', | |
cdc628a4 | 3024 | } |
9558dcec S |
3025 | }, { |
3026 | # Only available via https://www.youtube.com/c/12minuteathlete/videos | |
3027 | # but not https://www.youtube.com/user/12minuteathlete/videos | |
3028 | 'url': 'https://www.youtube.com/c/12minuteathlete/videos', | |
3029 | 'playlist_mincount': 249, | |
3030 | 'info_dict': { | |
3031 | 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ', | |
3032 | 'title': 'Uploads from 12 Minute Athlete', | |
13a75688 S |
3033 | 'uploader': '12 Minute Athlete', |
3034 | 'uploader_id': 'the12minuteathlete', | |
9558dcec | 3035 | } |
cdc628a4 PH |
3036 | }, { |
3037 | 'url': 'ytuser:phihag', | |
3038 | 'only_matching': True, | |
daa0df9e YCH |
3039 | }, { |
3040 | 'url': 'https://www.youtube.com/c/gametrailers', | |
3041 | 'only_matching': True, | |
67171ed7 S |
3042 | }, { |
3043 | 'url': 'https://www.youtube.com/c/Pawe%C5%82Zadro%C5%BCniak', | |
3044 | 'only_matching': True, | |
9558dcec S |
3045 | }, { |
3046 | 'url': 'https://www.youtube.com/gametrailers', | |
3047 | 'only_matching': True, | |
73c4ac2c | 3048 | }, { |
0e879f43 | 3049 | # This channel is not available, geo restricted to JP |
73c4ac2c S |
3050 | 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos', |
3051 | 'only_matching': True, | |
cdc628a4 PH |
3052 | }] |
3053 | ||
e3ea4790 | 3054 | @classmethod |
f4b05232 | 3055 | def suitable(cls, url): |
e3ea4790 JMF |
3056 | # Don't return True if the url can be extracted with other youtube |
3057 | # extractor, the regex would is too permissive and it would match. | |
f3a58d46 | 3058 | other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls) |
3059 | if any(ie.suitable(url) for ie in other_yt_ies): | |
5f6a1245 JW |
3060 | return False |
3061 | else: | |
3062 | return super(YoutubeUserIE, cls).suitable(url) | |
f4b05232 | 3063 | |
9558dcec S |
3064 | def _build_template_url(self, url, channel_id): |
3065 | mobj = re.match(self._VALID_URL, url) | |
3066 | return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id')) | |
3067 | ||
b05654f0 | 3068 | |
f07e276a S |
3069 | class YoutubeLiveIE(YoutubeBaseInfoExtractor): |
3070 | IE_DESC = 'YouTube.com live streams' | |
073d5bf5 | 3071 | _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live' |
f07e276a S |
3072 | IE_NAME = 'youtube:live' |
3073 | ||
3074 | _TESTS = [{ | |
2d3d2997 | 3075 | 'url': 'https://www.youtube.com/user/TheYoungTurks/live', |
f07e276a S |
3076 | 'info_dict': { |
3077 | 'id': 'a48o2S1cPoo', | |
3078 | 'ext': 'mp4', | |
3079 | 'title': 'The Young Turks - Live Main Show', | |
3080 | 'uploader': 'The Young Turks', | |
3081 | 'uploader_id': 'TheYoungTurks', | |
ec85ded8 | 3082 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks', |
f07e276a S |
3083 | 'upload_date': '20150715', |
3084 | 'license': 'Standard YouTube License', | |
3085 | 'description': 'md5:438179573adcdff3c97ebb1ee632b891', | |
3086 | 'categories': ['News & Politics'], | |
3087 | 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'], | |
3088 | 'like_count': int, | |
3089 | 'dislike_count': int, | |
3090 | }, | |
3091 | 'params': { | |
3092 | 'skip_download': True, | |
3093 | }, | |
3094 | }, { | |
2d3d2997 | 3095 | 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live', |
f07e276a | 3096 | 'only_matching': True, |
c1b2a085 S |
3097 | }, { |
3098 | 'url': 'https://www.youtube.com/c/CommanderVideoHq/live', | |
3099 | 'only_matching': True, | |
073d5bf5 S |
3100 | }, { |
3101 | 'url': 'https://www.youtube.com/TheYoungTurks/live', | |
3102 | 'only_matching': True, | |
f07e276a S |
3103 | }] |
3104 | ||
3105 | def _real_extract(self, url): | |
3106 | mobj = re.match(self._VALID_URL, url) | |
3107 | channel_id = mobj.group('id') | |
3108 | base_url = mobj.group('base_url') | |
3109 | webpage = self._download_webpage(url, channel_id, fatal=False) | |
3110 | if webpage: | |
3111 | page_type = self._og_search_property( | |
e7f3529f | 3112 | 'type', webpage, 'page type', default='') |
f07e276a S |
3113 | video_id = self._html_search_meta( |
3114 | 'videoId', webpage, 'video id', default=None) | |
e7f3529f S |
3115 | if page_type.startswith('video') and video_id and re.match( |
3116 | r'^[0-9A-Za-z_-]{11}$', video_id): | |
f07e276a S |
3117 | return self.url_result(video_id, YoutubeIE.ie_key()) |
3118 | return self.url_result(base_url) | |
3119 | ||
3120 | ||
e462474e S |
3121 | class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor): |
3122 | IE_DESC = 'YouTube.com user/channel playlists' | |
e942cfd1 | 3123 | _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel|c)/(?P<id>[^/]+)/playlists' |
e462474e | 3124 | IE_NAME = 'youtube:playlists' |
0c148415 | 3125 | |
e568c223 | 3126 | _TESTS = [{ |
2d3d2997 | 3127 | 'url': 'https://www.youtube.com/user/ThirstForScience/playlists', |
0c148415 S |
3128 | 'playlist_mincount': 4, |
3129 | 'info_dict': { | |
3130 | 'id': 'ThirstForScience', | |
13a75688 | 3131 | 'title': 'ThirstForScience', |
0c148415 | 3132 | }, |
e568c223 S |
3133 | }, { |
3134 | # with "Load more" button | |
2d3d2997 | 3135 | 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd', |
e568c223 S |
3136 | 'playlist_mincount': 70, |
3137 | 'info_dict': { | |
3138 | 'id': 'igorkle1', | |
3139 | 'title': 'Игорь Клейнер', | |
3140 | }, | |
e462474e S |
3141 | }, { |
3142 | 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists', | |
3143 | 'playlist_mincount': 17, | |
3144 | 'info_dict': { | |
3145 | 'id': 'UCiU1dHvZObB2iP6xkJ__Icw', | |
3146 | 'title': 'Chem Player', | |
3147 | }, | |
13a75688 | 3148 | 'skip': 'Blocked', |
e942cfd1 S |
3149 | }, { |
3150 | 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists', | |
3151 | 'only_matching': True, | |
e568c223 | 3152 | }] |
0c148415 S |
3153 | |
3154 | ||
870f3bfc | 3155 | class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor): |
b948643f | 3156 | _PLAYLIST_DATA = r'window\[\"ytInitialData\"\]\W?=\W?({.*?});' |
3157 | ||
3158 | def extract_videos_from_page_impl(self, page, ids_in_page, titles_in_page): | |
3159 | playlist_json = self._search_regex(self._PLAYLIST_DATA, page, 'ytInitialData') | |
3160 | playlist_response = self._parse_json(playlist_json, None) | |
3161 | ||
3162 | result_items = try_get( | |
3163 | playlist_response, | |
3164 | lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'][0]['itemSectionRenderer']['contents']) | |
3165 | ||
3166 | # plobj either contains a 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'shelfRenderer' or 'searchPyvRenderer' (promoted video/ad) | |
3167 | for plobj in result_items: | |
3168 | video_id = try_get(plobj, lambda x: x['videoRenderer']['videoId']) | |
3169 | video_title = try_get(plobj, lambda x: x['videoRenderer']['title']['runs'][0]['text']) | |
3170 | ||
3171 | if video_id is None or video_title is None: | |
3172 | # we do not have a videoRenderer or it is empty | |
3173 | continue | |
3174 | ||
3175 | video_title = video_title.strip() | |
3176 | ||
3177 | try: | |
3178 | idx = ids_in_page.index(video_id) | |
3179 | if video_title and not titles_in_page[idx]: | |
3180 | titles_in_page[idx] = video_title | |
3181 | except ValueError: | |
3182 | ids_in_page.append(video_id) | |
3183 | titles_in_page.append(video_title) | |
3184 | ||
3185 | def extract_videos_from_page(self, page): | |
3186 | ids_in_page = [] | |
3187 | titles_in_page = [] | |
3188 | self.extract_videos_from_page_impl(page, ids_in_page, titles_in_page) | |
3189 | return zip(ids_in_page, titles_in_page) | |
870f3bfc S |
3190 | |
3191 | ||
3192 | class YoutubeSearchIE(SearchInfoExtractor, YoutubeSearchBaseInfoExtractor): | |
78caa52a | 3193 | IE_DESC = 'YouTube.com searches' |
b4c08069 JMF |
3194 | # there doesn't appear to be a real limit, for example if you search for |
3195 | # 'python' you get more than 8.000.000 results | |
3196 | _MAX_RESULTS = float('inf') | |
78caa52a | 3197 | IE_NAME = 'youtube:search' |
b05654f0 | 3198 | _SEARCH_KEY = 'ytsearch' |
b4c08069 | 3199 | _EXTRA_QUERY_ARGS = {} |
9dd8e46a | 3200 | _TESTS = [] |
b05654f0 | 3201 | |
b05654f0 PH |
3202 | def _get_n_results(self, query, n): |
3203 | """Get a specified number of results for a query""" | |
3204 | ||
b4c08069 | 3205 | videos = [] |
b05654f0 PH |
3206 | limit = n |
3207 | ||
a22b2fd1 YCH |
3208 | url_query = { |
3209 | 'search_query': query.encode('utf-8'), | |
3210 | } | |
3211 | url_query.update(self._EXTRA_QUERY_ARGS) | |
3212 | result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query) | |
3213 | ||
b4c08069 | 3214 | for pagenum in itertools.count(1): |
b4c08069 | 3215 | data = self._download_json( |
69ea8ca4 | 3216 | result_url, video_id='query "%s"' % query, |
b4c08069 | 3217 | note='Downloading page %s' % pagenum, |
a22b2fd1 YCH |
3218 | errnote='Unable to download API page', |
3219 | query={'spf': 'navigate'}) | |
b4c08069 | 3220 | html_content = data[1]['body']['content'] |
7cc3570e | 3221 | |
b4c08069 | 3222 | if 'class="search-message' in html_content: |
07ad22b8 | 3223 | raise ExtractorError( |
78caa52a | 3224 | '[youtube] No video results', expected=True) |
b05654f0 | 3225 | |
870f3bfc | 3226 | new_videos = list(self._process_page(html_content)) |
b4c08069 JMF |
3227 | videos += new_videos |
3228 | if not new_videos or len(videos) > limit: | |
3229 | break | |
a22b2fd1 YCH |
3230 | next_link = self._html_search_regex( |
3231 | r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next', | |
3232 | html_content, 'next link', default=None) | |
3233 | if next_link is None: | |
3234 | break | |
3235 | result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link) | |
b05654f0 | 3236 | |
b4c08069 JMF |
3237 | if len(videos) > n: |
3238 | videos = videos[:n] | |
b05654f0 | 3239 | return self.playlist_result(videos, query) |
75dff0ee | 3240 | |
c9ae7b95 | 3241 | |
a3dd9248 | 3242 | class YoutubeSearchDateIE(YoutubeSearchIE): |
cb7fb546 | 3243 | IE_NAME = YoutubeSearchIE.IE_NAME + ':date' |
a3dd9248 | 3244 | _SEARCH_KEY = 'ytsearchdate' |
78caa52a | 3245 | IE_DESC = 'YouTube.com searches, newest videos first' |
b4c08069 | 3246 | _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'} |
75dff0ee | 3247 | |
c9ae7b95 | 3248 | |
870f3bfc | 3249 | class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor): |
78caa52a PH |
3250 | IE_DESC = 'YouTube.com search URLs' |
3251 | IE_NAME = 'youtube:search_url' | |
d2c1f79f | 3252 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)' |
cdc628a4 PH |
3253 | _TESTS = [{ |
3254 | 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', | |
3255 | 'playlist_mincount': 5, | |
3256 | 'info_dict': { | |
3257 | 'title': 'youtube-dl test video', | |
3258 | } | |
d2c1f79f S |
3259 | }, { |
3260 | 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB', | |
3261 | 'only_matching': True, | |
cdc628a4 | 3262 | }] |
c9ae7b95 PH |
3263 | |
3264 | def _real_extract(self, url): | |
3265 | mobj = re.match(self._VALID_URL, url) | |
7fd002c0 | 3266 | query = compat_urllib_parse_unquote_plus(mobj.group('query')) |
c9ae7b95 | 3267 | webpage = self._download_webpage(url, query) |
175c2e9e | 3268 | return self.playlist_result(self._process_page(webpage), playlist_title=query) |
c9ae7b95 PH |
3269 | |
3270 | ||
136dadde | 3271 | class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor): |
78caa52a | 3272 | IE_DESC = 'YouTube.com (multi-season) shows' |
92519402 | 3273 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)' |
78caa52a | 3274 | IE_NAME = 'youtube:show' |
cdc628a4 | 3275 | _TESTS = [{ |
4003bd82 | 3276 | 'url': 'https://www.youtube.com/show/airdisasters', |
8801255d | 3277 | 'playlist_mincount': 5, |
cdc628a4 PH |
3278 | 'info_dict': { |
3279 | 'id': 'airdisasters', | |
3280 | 'title': 'Air Disasters', | |
3281 | } | |
3282 | }] | |
75dff0ee JMF |
3283 | |
3284 | def _real_extract(self, url): | |
136dadde S |
3285 | playlist_id = self._match_id(url) |
3286 | return super(YoutubeShowIE, self)._real_extract( | |
3287 | 'https://www.youtube.com/show/%s/playlists' % playlist_id) | |
04cc9617 JMF |
3288 | |
3289 | ||
b2e8bc1b | 3290 | class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): |
d7ae0639 | 3291 | """ |
25f14e9f | 3292 | Base class for feed extractors |
d7ae0639 JMF |
3293 | Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties. |
3294 | """ | |
b2e8bc1b | 3295 | _LOGIN_REQUIRED = True |
d7ae0639 JMF |
3296 | |
3297 | @property | |
3298 | def IE_NAME(self): | |
78caa52a | 3299 | return 'youtube:%s' % self._FEED_NAME |
04cc9617 | 3300 | |
81f0259b | 3301 | def _real_initialize(self): |
b2e8bc1b | 3302 | self._login() |
81f0259b | 3303 | |
3853309f | 3304 | def _entries(self, page): |
2bc43303 JMF |
3305 | # The extraction process is the same as for playlists, but the regex |
3306 | # for the video ids doesn't contain an index | |
3307 | ids = [] | |
3308 | more_widget_html = content_html = page | |
2bc43303 JMF |
3309 | for page_num in itertools.count(1): |
3310 | matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html) | |
62c95fd5 S |
3311 | |
3312 | # 'recommended' feed has infinite 'load more' and each new portion spins | |
3313 | # the same videos in (sometimes) slightly different order, so we'll check | |
3314 | # for unicity and break when portion has no new videos | |
3853309f | 3315 | new_ids = list(filter(lambda video_id: video_id not in ids, orderedSet(matches))) |
62c95fd5 S |
3316 | if not new_ids: |
3317 | break | |
3318 | ||
2bc43303 JMF |
3319 | ids.extend(new_ids) |
3320 | ||
3853309f S |
3321 | for entry in self._ids_to_results(new_ids): |
3322 | yield entry | |
3323 | ||
2bc43303 JMF |
3324 | mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) |
3325 | if not mobj: | |
3326 | break | |
3327 | ||
3328 | more = self._download_json( | |
07af16b9 | 3329 | 'https://www.youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE, |
2bc43303 | 3330 | 'Downloading page #%s' % page_num, |
d84b21b4 S |
3331 | transform_source=uppercase_escape, |
3332 | headers=self._YOUTUBE_CLIENT_HEADERS) | |
2bc43303 JMF |
3333 | content_html = more['content_html'] |
3334 | more_widget_html = more['load_more_widget_html'] | |
3335 | ||
3853309f S |
3336 | def _real_extract(self, url): |
3337 | page = self._download_webpage( | |
3338 | 'https://www.youtube.com/feed/%s' % self._FEED_NAME, | |
3339 | self._PLAYLIST_TITLE) | |
25f14e9f | 3340 | return self.playlist_result( |
3853309f | 3341 | self._entries(page), playlist_title=self._PLAYLIST_TITLE) |
25f14e9f S |
3342 | |
3343 | ||
3344 | class YoutubeWatchLaterIE(YoutubePlaylistIE): | |
3345 | IE_NAME = 'youtube:watchlater' | |
3346 | IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)' | |
92519402 | 3347 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater' |
25f14e9f | 3348 | |
bc7a9cd8 S |
3349 | _TESTS = [{ |
3350 | 'url': 'https://www.youtube.com/playlist?list=WL', | |
3351 | 'only_matching': True, | |
3352 | }, { | |
3353 | 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL', | |
3354 | 'only_matching': True, | |
3355 | }] | |
25f14e9f S |
3356 | |
3357 | def _real_extract(self, url): | |
7e5dc339 | 3358 | _, video = self._check_download_just_video(url, 'WL') |
ebf1b291 S |
3359 | if video: |
3360 | return video | |
dacb3a86 S |
3361 | _, playlist = self._extract_playlist('WL') |
3362 | return playlist | |
f459d170 | 3363 | |
5f6a1245 | 3364 | |
c626a3d9 | 3365 | class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): |
78caa52a | 3366 | IE_NAME = 'youtube:favorites' |
f3a34072 | 3367 | IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)' |
92519402 | 3368 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?' |
c626a3d9 JMF |
3369 | _LOGIN_REQUIRED = True |
3370 | ||
3371 | def _real_extract(self, url): | |
3372 | webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos') | |
78caa52a | 3373 | playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id') |
c626a3d9 | 3374 | return self.url_result(playlist_id, 'YoutubePlaylist') |
15870e90 PH |
3375 | |
3376 | ||
25f14e9f S |
3377 | class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): |
3378 | IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)' | |
92519402 | 3379 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?' |
25f14e9f S |
3380 | _FEED_NAME = 'recommended' |
3381 | _PLAYLIST_TITLE = 'Youtube Recommended videos' | |
1ed5b5c9 | 3382 | |
1ed5b5c9 | 3383 | |
25f14e9f S |
3384 | class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): |
3385 | IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)' | |
92519402 | 3386 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?' |
25f14e9f S |
3387 | _FEED_NAME = 'subscriptions' |
3388 | _PLAYLIST_TITLE = 'Youtube Subscriptions' | |
1ed5b5c9 | 3389 | |
1ed5b5c9 | 3390 | |
25f14e9f S |
3391 | class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): |
3392 | IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)' | |
92519402 | 3393 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory' |
25f14e9f S |
3394 | _FEED_NAME = 'history' |
3395 | _PLAYLIST_TITLE = 'Youtube History' | |
1ed5b5c9 JMF |
3396 | |
3397 | ||
15870e90 PH |
3398 | class YoutubeTruncatedURLIE(InfoExtractor): |
3399 | IE_NAME = 'youtube:truncated_url' | |
3400 | IE_DESC = False # Do not list | |
975d35db | 3401 | _VALID_URL = r'''(?x) |
b95aab84 PH |
3402 | (?:https?://)? |
3403 | (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/ | |
3404 | (?:watch\?(?: | |
c4808c60 | 3405 | feature=[a-z_]+| |
b95aab84 PH |
3406 | annotation_id=annotation_[^&]+| |
3407 | x-yt-cl=[0-9]+| | |
c1708b89 | 3408 | hl=[^&]*| |
287be8c6 | 3409 | t=[0-9]+ |
b95aab84 PH |
3410 | )? |
3411 | | | |
3412 | attribution_link\?a=[^&]+ | |
3413 | ) | |
3414 | $ | |
975d35db | 3415 | ''' |
15870e90 | 3416 | |
c4808c60 | 3417 | _TESTS = [{ |
2d3d2997 | 3418 | 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041', |
c4808c60 | 3419 | 'only_matching': True, |
dc2fc736 | 3420 | }, { |
2d3d2997 | 3421 | 'url': 'https://www.youtube.com/watch?', |
dc2fc736 | 3422 | 'only_matching': True, |
b95aab84 PH |
3423 | }, { |
3424 | 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534', | |
3425 | 'only_matching': True, | |
3426 | }, { | |
3427 | 'url': 'https://www.youtube.com/watch?feature=foo', | |
3428 | 'only_matching': True, | |
c1708b89 PH |
3429 | }, { |
3430 | 'url': 'https://www.youtube.com/watch?hl=en-GB', | |
3431 | 'only_matching': True, | |
287be8c6 PH |
3432 | }, { |
3433 | 'url': 'https://www.youtube.com/watch?t=2372', | |
3434 | 'only_matching': True, | |
c4808c60 PH |
3435 | }] |
3436 | ||
15870e90 PH |
3437 | def _real_extract(self, url): |
3438 | raise ExtractorError( | |
78caa52a PH |
3439 | 'Did you forget to quote the URL? Remember that & is a meta ' |
3440 | 'character in most shells, so you want to put the URL in quotes, ' | |
3441 | 'like youtube-dl ' | |
2d3d2997 | 3442 | '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' |
78caa52a | 3443 | ' or simply youtube-dl BaW_jenozKc .', |
15870e90 | 3444 | expected=True) |
772fd5cc PH |
3445 | |
3446 | ||
3447 | class YoutubeTruncatedIDIE(InfoExtractor): | |
3448 | IE_NAME = 'youtube:truncated_id' | |
3449 | IE_DESC = False # Do not list | |
b95aab84 | 3450 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$' |
772fd5cc PH |
3451 | |
3452 | _TESTS = [{ | |
3453 | 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob', | |
3454 | 'only_matching': True, | |
3455 | }] | |
3456 | ||
3457 | def _real_extract(self, url): | |
3458 | video_id = self._match_id(url) | |
3459 | raise ExtractorError( | |
3460 | 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url), | |
3461 | expected=True) |