]>
Commit | Line | Data |
---|---|---|
dcdb292f | 1 | # coding: utf-8 |
9148eb00 PH |
2 | from __future__ import unicode_literals |
3 | ||
b3d14cbf PH |
4 | import json |
5 | import re | |
caeefc29 | 6 | import itertools |
b3d14cbf PH |
7 | |
8 | from .common import InfoExtractor | |
8c25f81b | 9 | from ..compat import ( |
1060425c | 10 | compat_HTTPError, |
6a55bb66 | 11 | compat_str, |
9c44d242 | 12 | compat_urlparse, |
8c25f81b PH |
13 | ) |
14 | from ..utils import ( | |
d5f071af | 15 | determine_ext, |
b3d14cbf | 16 | ExtractorError, |
9c44d242 PH |
17 | InAdvancePagedList, |
18 | int_or_none, | |
c1ff6e1a | 19 | NO_DEFAULT, |
55b3e45b | 20 | RegexNotFoundError, |
67dda517 | 21 | sanitized_Request, |
30965ac6 | 22 | smuggle_url, |
b3d14cbf | 23 | std_headers, |
3c6f2450 | 24 | unified_strdate, |
9d4660ca | 25 | unsmuggle_url, |
a980bc43 | 26 | urlencode_postdata, |
b407e173 | 27 | unescapeHTML, |
eb4f2740 | 28 | parse_filesize, |
6a55bb66 | 29 | try_get, |
b3d14cbf PH |
30 | ) |
31 | ||
bbafbe20 | 32 | |
efb7e119 JMF |
33 | class VimeoBaseInfoExtractor(InfoExtractor): |
34 | _NETRC_MACHINE = 'vimeo' | |
35 | _LOGIN_REQUIRED = False | |
f6c3664d | 36 | _LOGIN_URL = 'https://vimeo.com/log_in' |
efb7e119 JMF |
37 | |
38 | def _login(self): | |
39 | (username, password) = self._get_login_info() | |
40 | if username is None: | |
41 | if self._LOGIN_REQUIRED: | |
4f3e9430 | 42 | raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) |
efb7e119 JMF |
43 | return |
44 | self.report_login() | |
f6c3664d | 45 | webpage = self._download_webpage(self._LOGIN_URL, None, False) |
7c845629 | 46 | token, vuid = self._extract_xsrft_and_vuid(webpage) |
15707c7e | 47 | data = urlencode_postdata({ |
f6c3664d | 48 | 'action': 'login', |
efb7e119 JMF |
49 | 'email': username, |
50 | 'password': password, | |
efb7e119 JMF |
51 | 'service': 'vimeo', |
52 | 'token': token, | |
15707c7e | 53 | }) |
67dda517 | 54 | login_request = sanitized_Request(self._LOGIN_URL, data) |
efb7e119 | 55 | login_request.add_header('Content-Type', 'application/x-www-form-urlencoded') |
f6c3664d | 56 | login_request.add_header('Referer', self._LOGIN_URL) |
9eab37dc | 57 | self._set_vimeo_cookie('vuid', vuid) |
efb7e119 JMF |
58 | self._download_webpage(login_request, None, False, 'Wrong login info') |
59 | ||
c1ff6e1a YCH |
60 | def _verify_video_password(self, url, video_id, webpage): |
61 | password = self._downloader.params.get('videopassword') | |
62 | if password is None: | |
63 | raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True) | |
64 | token, vuid = self._extract_xsrft_and_vuid(webpage) | |
65 | data = urlencode_postdata({ | |
66 | 'password': password, | |
67 | 'token': token, | |
68 | }) | |
69 | if url.startswith('http://'): | |
70 | # vimeo only supports https now, but the user can give an http url | |
71 | url = url.replace('http://', 'https://') | |
72 | password_request = sanitized_Request(url + '/password', data) | |
73 | password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') | |
74 | password_request.add_header('Referer', url) | |
75 | self._set_vimeo_cookie('vuid', vuid) | |
76 | return self._download_webpage( | |
77 | password_request, video_id, | |
78 | 'Verifying the password', 'Wrong password') | |
79 | ||
7c845629 S |
80 | def _extract_xsrft_and_vuid(self, webpage): |
81 | xsrft = self._search_regex( | |
b826035d | 82 | r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)', |
f6c3664d | 83 | webpage, 'login token', group='xsrft') |
7c845629 S |
84 | vuid = self._search_regex( |
85 | r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1', | |
86 | webpage, 'vuid', group='vuid') | |
87 | return xsrft, vuid | |
f6c3664d | 88 | |
9eab37dc S |
89 | def _set_vimeo_cookie(self, name, value): |
90 | self._set_cookie('vimeo.com', name, value) | |
91 | ||
531a7496 YCH |
92 | def _vimeo_sort_formats(self, formats): |
93 | # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps | |
94 | # at the same time without actual units specified. This lead to wrong sorting. | |
d8c507c9 | 95 | self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'tbr', 'format_id')) |
531a7496 YCH |
96 | |
97 | def _parse_config(self, config, video_id): | |
d8c507c9 | 98 | video_data = config['video'] |
531a7496 | 99 | # Extract title |
d8c507c9 | 100 | video_title = video_data['title'] |
531a7496 YCH |
101 | |
102 | # Extract uploader, uploader_url and uploader_id | |
d8c507c9 RA |
103 | video_uploader = video_data.get('owner', {}).get('name') |
104 | video_uploader_url = video_data.get('owner', {}).get('url') | |
531a7496 YCH |
105 | video_uploader_id = video_uploader_url.split('/')[-1] if video_uploader_url else None |
106 | ||
107 | # Extract video thumbnail | |
d8c507c9 | 108 | video_thumbnail = video_data.get('thumbnail') |
531a7496 | 109 | if video_thumbnail is None: |
d8c507c9 | 110 | video_thumbs = video_data.get('thumbs') |
531a7496 YCH |
111 | if video_thumbs and isinstance(video_thumbs, dict): |
112 | _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1] | |
113 | ||
114 | # Extract video duration | |
d8c507c9 | 115 | video_duration = int_or_none(video_data.get('duration')) |
531a7496 YCH |
116 | |
117 | formats = [] | |
d8c507c9 | 118 | config_files = video_data.get('files') or config['request'].get('files', {}) |
531a7496 YCH |
119 | for f in config_files.get('progressive', []): |
120 | video_url = f.get('url') | |
121 | if not video_url: | |
122 | continue | |
123 | formats.append({ | |
124 | 'url': video_url, | |
125 | 'format_id': 'http-%s' % f.get('quality'), | |
126 | 'width': int_or_none(f.get('width')), | |
127 | 'height': int_or_none(f.get('height')), | |
128 | 'fps': int_or_none(f.get('fps')), | |
129 | 'tbr': int_or_none(f.get('bitrate')), | |
130 | }) | |
d8c507c9 RA |
131 | |
132 | for files_type in ('hls', 'dash'): | |
133 | for cdn_name, cdn_data in config_files.get(files_type, {}).get('cdns', {}).items(): | |
134 | manifest_url = cdn_data.get('url') | |
135 | if not manifest_url: | |
136 | continue | |
137 | format_id = '%s-%s' % (files_type, cdn_name) | |
138 | if files_type == 'hls': | |
139 | formats.extend(self._extract_m3u8_formats( | |
140 | manifest_url, video_id, 'mp4', | |
141 | 'm3u8_native', m3u8_id=format_id, | |
142 | note='Downloading %s m3u8 information' % cdn_name, | |
143 | fatal=False)) | |
144 | elif files_type == 'dash': | |
145 | formats.extend(self._extract_mpd_formats( | |
146 | manifest_url.replace('/master.json', '/master.mpd'), video_id, format_id, | |
147 | 'Downloading %s MPD information' % cdn_name, | |
148 | fatal=False)) | |
531a7496 YCH |
149 | |
150 | subtitles = {} | |
151 | text_tracks = config['request'].get('text_tracks') | |
152 | if text_tracks: | |
153 | for tt in text_tracks: | |
154 | subtitles[tt['lang']] = [{ | |
155 | 'ext': 'vtt', | |
156 | 'url': 'https://vimeo.com' + tt['url'], | |
157 | }] | |
158 | ||
159 | return { | |
160 | 'title': video_title, | |
161 | 'uploader': video_uploader, | |
162 | 'uploader_id': video_uploader_id, | |
163 | 'uploader_url': video_uploader_url, | |
164 | 'thumbnail': video_thumbnail, | |
165 | 'duration': video_duration, | |
166 | 'formats': formats, | |
167 | 'subtitles': subtitles, | |
168 | } | |
169 | ||
efb7e119 | 170 | |
65469a7f | 171 | class VimeoIE(VimeoBaseInfoExtractor): |
b3d14cbf PH |
172 | """Information extractor for vimeo.com.""" |
173 | ||
174 | # _VALID_URL matches Vimeo URLs | |
bbafbe20 | 175 | _VALID_URL = r'''(?x) |
74278def S |
176 | https?:// |
177 | (?: | |
178 | (?: | |
179 | www| | |
180 | (?P<player>player) | |
181 | ) | |
182 | \. | |
183 | )? | |
184 | vimeo(?P<pro>pro)?\.com/ | |
c8e3e097 | 185 | (?!(?:channels|album)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/) |
74278def S |
186 | (?:.*?/)? |
187 | (?: | |
188 | (?: | |
189 | play_redirect_hls| | |
190 | moogaloop\.swf)\?clip_id= | |
191 | )? | |
192 | (?:videos?/)? | |
193 | (?P<id>[0-9]+) | |
241a318f | 194 | (?:/[\da-f]+)? |
74278def S |
195 | /?(?:[?&].*)?(?:[#].*)?$ |
196 | ''' | |
9148eb00 | 197 | IE_NAME = 'vimeo' |
a91b954b JMF |
198 | _TESTS = [ |
199 | { | |
9148eb00 | 200 | 'url': 'http://vimeo.com/56015672#at=0', |
9148eb00 PH |
201 | 'md5': '8879b6cc097e987f02484baf890129e5', |
202 | 'info_dict': { | |
ad5976b4 PH |
203 | 'id': '56015672', |
204 | 'ext': 'mp4', | |
68f3b61f S |
205 | 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", |
206 | 'description': 'md5:2d3305bad981a06ff79f027f19865021', | |
207 | 'upload_date': '20121220', | |
ec85ded8 | 208 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434', |
68f3b61f S |
209 | 'uploader_id': 'user7108434', |
210 | 'uploader': 'Filippo Valsorda', | |
211 | 'duration': 10, | |
a91b954b JMF |
212 | }, |
213 | }, | |
214 | { | |
9148eb00 | 215 | 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876', |
9148eb00 PH |
216 | 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82', |
217 | 'note': 'Vimeo Pro video (#1197)', | |
218 | 'info_dict': { | |
4f3e9430 JMF |
219 | 'id': '68093876', |
220 | 'ext': 'mp4', | |
ec85ded8 | 221 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus', |
9148eb00 PH |
222 | 'uploader_id': 'openstreetmapus', |
223 | 'uploader': 'OpenStreetMap US', | |
224 | 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography', | |
68f3b61f | 225 | 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30', |
69c8fb9e | 226 | 'duration': 1595, |
a91b954b JMF |
227 | }, |
228 | }, | |
aa32314d | 229 | { |
9148eb00 | 230 | 'url': 'http://player.vimeo.com/video/54469442', |
9148eb00 PH |
231 | 'md5': '619b811a4417aa4abe78dc653becf511', |
232 | 'note': 'Videos that embed the url in the player page', | |
233 | 'info_dict': { | |
4f3e9430 JMF |
234 | 'id': '54469442', |
235 | 'ext': 'mp4', | |
0e6ebc13 | 236 | 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012', |
9148eb00 | 237 | 'uploader': 'The BLN & Business of Software', |
ec85ded8 | 238 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware', |
9148eb00 | 239 | 'uploader_id': 'theblnbusinessofsoftware', |
69c8fb9e | 240 | 'duration': 3610, |
58ea7ec8 | 241 | 'description': None, |
aa32314d | 242 | }, |
93b22c78 JMF |
243 | }, |
244 | { | |
9148eb00 | 245 | 'url': 'http://vimeo.com/68375962', |
9148eb00 PH |
246 | 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7', |
247 | 'note': 'Video protected with password', | |
248 | 'info_dict': { | |
4f3e9430 JMF |
249 | 'id': '68375962', |
250 | 'ext': 'mp4', | |
9148eb00 PH |
251 | 'title': 'youtube-dl password protected test video', |
252 | 'upload_date': '20130614', | |
ec85ded8 | 253 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128', |
9148eb00 PH |
254 | 'uploader_id': 'user18948128', |
255 | 'uploader': 'Jaime Marquínez Ferrándiz', | |
69c8fb9e | 256 | 'duration': 10, |
531a7496 | 257 | 'description': 'This is "youtube-dl password protected test video" by on Vimeo, the home for high quality videos and the people who love them.', |
93b22c78 | 258 | }, |
9148eb00 PH |
259 | 'params': { |
260 | 'videopassword': 'youtube-dl', | |
93b22c78 JMF |
261 | }, |
262 | }, | |
548f31d9 S |
263 | { |
264 | 'url': 'http://vimeo.com/channels/keypeele/75629013', | |
265 | 'md5': '2f86a05afe9d7abc0b9126d229bbe15d', | |
548f31d9 S |
266 | 'info_dict': { |
267 | 'id': '75629013', | |
268 | 'ext': 'mp4', | |
269 | 'title': 'Key & Peele: Terrorist Interrogation', | |
270 | 'description': 'md5:8678b246399b070816b12313e8b4eb5c', | |
ec85ded8 | 271 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio', |
548f31d9 S |
272 | 'uploader_id': 'atencio', |
273 | 'uploader': 'Peter Atencio', | |
3c6f2450 | 274 | 'upload_date': '20130927', |
548f31d9 S |
275 | 'duration': 187, |
276 | }, | |
277 | }, | |
1eac553e S |
278 | { |
279 | 'url': 'http://vimeo.com/76979871', | |
1eac553e S |
280 | 'note': 'Video with subtitles', |
281 | 'info_dict': { | |
282 | 'id': '76979871', | |
283 | 'ext': 'mp4', | |
284 | 'title': 'The New Vimeo Player (You Know, For Videos)', | |
285 | 'description': 'md5:2ec900bf97c3f389378a96aee11260ea', | |
286 | 'upload_date': '20131015', | |
ec85ded8 | 287 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff', |
1eac553e S |
288 | 'uploader_id': 'staff', |
289 | 'uploader': 'Vimeo Staff', | |
69c8fb9e | 290 | 'duration': 62, |
1eac553e S |
291 | } |
292 | }, | |
4698f0d8 JMF |
293 | { |
294 | # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/ | |
295 | 'url': 'https://player.vimeo.com/video/98044508', | |
296 | 'note': 'The js code contains assignments to the same variable as the config', | |
297 | 'info_dict': { | |
298 | 'id': '98044508', | |
299 | 'ext': 'mp4', | |
300 | 'title': 'Pier Solar OUYA Official Trailer', | |
301 | 'uploader': 'Tulio Gonçalves', | |
ec85ded8 | 302 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593', |
4698f0d8 JMF |
303 | 'uploader_id': 'user28849593', |
304 | }, | |
305 | }, | |
323f82a7 | 306 | { |
307 | # contains original format | |
308 | 'url': 'https://vimeo.com/33951933', | |
c143ddce | 309 | 'md5': '2d9f5475e0537f013d0073e812ab89e6', |
323f82a7 | 310 | 'info_dict': { |
311 | 'id': '33951933', | |
312 | 'ext': 'mp4', | |
313 | 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute', | |
314 | 'uploader': 'The DMCI', | |
ec85ded8 | 315 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci', |
323f82a7 | 316 | 'uploader_id': 'dmci', |
317 | 'upload_date': '20111220', | |
318 | 'description': 'md5:ae23671e82d05415868f7ad1aec21147', | |
319 | }, | |
320 | }, | |
c143ddce S |
321 | { |
322 | # only available via https://vimeo.com/channels/tributes/6213729 and | |
323 | # not via https://vimeo.com/6213729 | |
324 | 'url': 'https://vimeo.com/channels/tributes/6213729', | |
325 | 'info_dict': { | |
326 | 'id': '6213729', | |
327 | 'ext': 'mp4', | |
328 | 'title': 'Vimeo Tribute: The Shining', | |
329 | 'uploader': 'Casey Donahue', | |
ec85ded8 | 330 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue', |
c143ddce S |
331 | 'uploader_id': 'caseydonahue', |
332 | 'upload_date': '20090821', | |
333 | 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6', | |
334 | }, | |
335 | 'params': { | |
336 | 'skip_download': True, | |
337 | }, | |
338 | 'expected_warnings': ['Unable to download JSON metadata'], | |
339 | }, | |
f16f8505 S |
340 | { |
341 | # redirects to ondemand extractor and should be passed throught it | |
342 | # for successful extraction | |
343 | 'url': 'https://vimeo.com/73445910', | |
344 | 'info_dict': { | |
345 | 'id': '73445910', | |
346 | 'ext': 'mp4', | |
347 | 'title': 'The Reluctant Revolutionary', | |
348 | 'uploader': '10Ft Films', | |
ec85ded8 | 349 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms', |
f16f8505 S |
350 | 'uploader_id': 'tenfootfilms', |
351 | }, | |
352 | 'params': { | |
353 | 'skip_download': True, | |
354 | }, | |
355 | }, | |
c143ddce S |
356 | { |
357 | 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741', | |
358 | 'only_matching': True, | |
359 | }, | |
8bea039b LL |
360 | { |
361 | 'url': 'https://vimeo.com/109815029', | |
362 | 'note': 'Video not completely processed, "failed" seed status', | |
363 | 'only_matching': True, | |
364 | }, | |
6b7ceee1 S |
365 | { |
366 | 'url': 'https://vimeo.com/groups/travelhd/videos/22439234', | |
367 | 'only_matching': True, | |
368 | }, | |
c8e3e097 S |
369 | { |
370 | 'url': 'https://vimeo.com/album/2632481/video/79010983', | |
371 | 'only_matching': True, | |
372 | }, | |
16f1131a S |
373 | { |
374 | # source file returns 403: Forbidden | |
375 | 'url': 'https://vimeo.com/7809605', | |
376 | 'only_matching': True, | |
377 | }, | |
241a318f S |
378 | { |
379 | 'url': 'https://vimeo.com/160743502/abd0e13fb4', | |
380 | 'only_matching': True, | |
381 | } | |
a91b954b | 382 | ] |
b3d14cbf | 383 | |
d002e919 S |
384 | @staticmethod |
385 | def _smuggle_referrer(url, referrer_url): | |
386 | return smuggle_url(url, {'http_headers': {'Referer': referrer_url}}) | |
387 | ||
b407e173 | 388 | @staticmethod |
09b9c45e S |
389 | def _extract_urls(url, webpage): |
390 | urls = [] | |
b407e173 | 391 | # Look for embedded (iframe) Vimeo player |
09b9c45e | 392 | for mobj in re.finditer( |
f475e881 S |
393 | r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', |
394 | webpage): | |
09b9c45e S |
395 | urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url')), url)) |
396 | PLAIN_EMBED_RE = ( | |
397 | # Look for embedded (swf embed) Vimeo player | |
398 | r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1', | |
399 | # Look more for non-standard embedded Vimeo player | |
400 | r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1', | |
401 | ) | |
402 | for embed_re in PLAIN_EMBED_RE: | |
403 | for mobj in re.finditer(embed_re, webpage): | |
404 | urls.append(mobj.group('url')) | |
405 | return urls | |
406 | ||
407 | @staticmethod | |
408 | def _extract_url(url, webpage): | |
409 | urls = VimeoIE._extract_urls(url, webpage) | |
410 | return urls[0] if urls else None | |
b407e173 | 411 | |
0eecc6a4 | 412 | def _verify_player_video_password(self, url, video_id): |
d800609c | 413 | password = self._downloader.params.get('videopassword') |
0eecc6a4 PH |
414 | if password is None: |
415 | raise ExtractorError('This video is protected by a password, use the --video-password option') | |
15707c7e | 416 | data = urlencode_postdata({'password': password}) |
0eecc6a4 | 417 | pass_url = url + '/check-password' |
67dda517 | 418 | password_request = sanitized_Request(pass_url, data) |
0eecc6a4 | 419 | password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') |
bdbb8530 | 420 | password_request.add_header('Referer', url) |
0eecc6a4 PH |
421 | return self._download_json( |
422 | password_request, video_id, | |
bdbb8530 | 423 | 'Verifying the password', 'Wrong password') |
0eecc6a4 | 424 | |
fc79158d JMF |
425 | def _real_initialize(self): |
426 | self._login() | |
427 | ||
a0088bdf | 428 | def _real_extract(self, url): |
5dbe81a1 | 429 | url, data = unsmuggle_url(url, {}) |
0f56a4b4 | 430 | headers = std_headers.copy() |
5dbe81a1 | 431 | if 'http_headers' in data: |
5dbe81a1 | 432 | headers.update(data['http_headers']) |
ba5d51b3 PH |
433 | if 'Referer' not in headers: |
434 | headers['Referer'] = url | |
9d4660ca | 435 | |
b3d14cbf PH |
436 | # Extract ID from URL |
437 | mobj = re.match(self._VALID_URL, url) | |
b3d14cbf | 438 | video_id = mobj.group('id') |
58ea7ec8 | 439 | orig_url = url |
9103bbc5 | 440 | if mobj.group('pro') or mobj.group('player'): |
61e00a97 | 441 | url = 'https://player.vimeo.com/video/' + video_id |
c143ddce | 442 | elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')): |
10831b5e | 443 | url = 'https://vimeo.com/' + video_id |
b3d14cbf PH |
444 | |
445 | # Retrieve video webpage to extract further information | |
0f56a4b4 | 446 | request = sanitized_Request(url, headers=headers) |
1060425c | 447 | try: |
f16f8505 S |
448 | webpage, urlh = self._download_webpage_handle(request, video_id) |
449 | # Some URLs redirect to ondemand can't be extracted with | |
450 | # this extractor right away thus should be passed through | |
451 | # ondemand extractor (e.g. https://vimeo.com/73445910) | |
452 | if VimeoOndemandIE.suitable(urlh.geturl()): | |
453 | return self.url_result(urlh.geturl(), VimeoOndemandIE.ie_key()) | |
1060425c PH |
454 | except ExtractorError as ee: |
455 | if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: | |
456 | errmsg = ee.cause.read() | |
457 | if b'Because of its privacy settings, this video cannot be played here' in errmsg: | |
458 | raise ExtractorError( | |
459 | 'Cannot download embed-only video without embedding ' | |
460 | 'URL. Please call youtube-dl with the URL of the page ' | |
461 | 'that embeds this video.', | |
462 | expected=True) | |
463 | raise | |
b3d14cbf PH |
464 | |
465 | # Now we begin extracting as much information as we can from what we | |
466 | # retrieved. First we extract the information common to all extractors, | |
467 | # and latter we extract those that are Vimeo specific. | |
468 | self.report_extraction(video_id) | |
469 | ||
998e6cdb | 470 | vimeo_config = self._search_regex( |
b6aa99af | 471 | r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage, |
998e6cdb S |
472 | 'vimeo config', default=None) |
473 | if vimeo_config: | |
474 | seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {}) | |
475 | if seed_status.get('state') == 'failed': | |
476 | raise ExtractorError( | |
b6aa99af | 477 | '%s said: %s' % (self.IE_NAME, seed_status['title']), |
998e6cdb S |
478 | expected=True) |
479 | ||
b3d14cbf PH |
480 | # Extract the config JSON |
481 | try: | |
93b22c78 JMF |
482 | try: |
483 | config_url = self._html_search_regex( | |
41a7b00f LL |
484 | r' data-config-url="(.+?)"', webpage, |
485 | 'config URL', default=None) | |
486 | if not config_url: | |
dd841752 S |
487 | # Sometimes new react-based page is served instead of old one that require |
488 | # different config URL extraction approach (see | |
489 | # https://github.com/rg3/youtube-dl/pull/7209) | |
41a7b00f LL |
490 | vimeo_clip_page_config = self._search_regex( |
491 | r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage, | |
492 | 'vimeo clip page config') | |
dd841752 S |
493 | config_url = self._parse_json( |
494 | vimeo_clip_page_config, video_id)['player']['config_url'] | |
93b22c78 JMF |
495 | config_json = self._download_webpage(config_url, video_id) |
496 | config = json.loads(config_json) | |
497 | except RegexNotFoundError: | |
498 | # For pro videos or player.vimeo.com urls | |
48ad51b2 | 499 | # We try to find out to which variable is assigned the config dic |
ec85ded8 | 500 | m_variable_name = re.search(r'(\w)\.video\.id', webpage) |
48ad51b2 | 501 | if m_variable_name is not None: |
4698f0d8 | 502 | config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1)) |
48ad51b2 JMF |
503 | else: |
504 | config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});'] | |
9148eb00 | 505 | config = self._search_regex(config_re, webpage, 'info section', |
9e1a5b84 | 506 | flags=re.DOTALL) |
93b22c78 | 507 | config = json.loads(config) |
71907db3 | 508 | except Exception as e: |
b3d14cbf | 509 | if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage): |
9148eb00 | 510 | raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option') |
b3d14cbf | 511 | |
bf8f082a | 512 | if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None: |
5dbe81a1 | 513 | if '_video_password_verified' in data: |
30965ac6 | 514 | raise ExtractorError('video password verification failed!') |
b3d14cbf | 515 | self._verify_video_password(url, video_id, webpage) |
30965ac6 PH |
516 | return self._real_extract( |
517 | smuggle_url(url, {'_video_password_verified': 'verified'})) | |
b3d14cbf | 518 | else: |
9148eb00 | 519 | raise ExtractorError('Unable to extract info section', |
71907db3 | 520 | cause=e) |
559e370f PH |
521 | else: |
522 | if config.get('view') == 4: | |
0eecc6a4 | 523 | config = self._verify_player_video_password(url, video_id) |
b3d14cbf | 524 | |
6a55bb66 S |
525 | def is_rented(): |
526 | if '>You rented this title.<' in webpage: | |
527 | return True | |
528 | if config.get('user', {}).get('purchased'): | |
529 | return True | |
530 | label = try_get( | |
531 | config, lambda x: x['video']['vod']['purchase_options'][0]['label_string'], compat_str) | |
532 | if label and label.startswith('You rented this'): | |
533 | return True | |
534 | return False | |
535 | ||
536 | if is_rented(): | |
5dbe81a1 S |
537 | feature_id = config.get('video', {}).get('vod', {}).get('feature_id') |
538 | if feature_id and not data.get('force_feature_id', False): | |
539 | return self.url_result(smuggle_url( | |
540 | 'https://player.vimeo.com/player/%s' % feature_id, | |
541 | {'force_feature_id': True}), 'Vimeo') | |
542 | ||
b3d14cbf | 543 | # Extract video description |
58ea7ec8 | 544 | |
25930395 | 545 | video_description = self._html_search_regex( |
58ea7ec8 PH |
546 | r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>', |
547 | webpage, 'description', default=None) | |
548 | if not video_description: | |
549 | video_description = self._html_search_meta( | |
550 | 'description', webpage, default=None) | |
551 | if not video_description and mobj.group('pro'): | |
552 | orig_webpage = self._download_webpage( | |
553 | orig_url, video_id, | |
554 | note='Downloading webpage for description', | |
555 | fatal=False) | |
556 | if orig_webpage: | |
557 | video_description = self._html_search_meta( | |
558 | 'description', orig_webpage, default=None) | |
559 | if not video_description and not mobj.group('player'): | |
560 | self._downloader.report_warning('Cannot find video description') | |
b3d14cbf PH |
561 | |
562 | # Extract upload date | |
563 | video_upload_date = None | |
3c6f2450 | 564 | mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage) |
b3d14cbf | 565 | if mobj is not None: |
3c6f2450 | 566 | video_upload_date = unified_strdate(mobj.group(1)) |
b3d14cbf | 567 | |
4e761794 | 568 | try: |
9148eb00 PH |
569 | view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count')) |
570 | like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count')) | |
571 | comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count')) | |
4e761794 JMF |
572 | except RegexNotFoundError: |
573 | # This info is only available in vimeo.com/{id} urls | |
574 | view_count = None | |
575 | like_count = None | |
576 | comment_count = None | |
577 | ||
a6387bfd | 578 | formats = [] |
eb4f2740 | 579 | download_request = sanitized_Request('https://vimeo.com/%s?action=load_download_config' % video_id, headers={ |
580 | 'X-Requested-With': 'XMLHttpRequest'}) | |
581 | download_data = self._download_json(download_request, video_id, fatal=False) | |
582 | if download_data: | |
583 | source_file = download_data.get('source_file') | |
d5f071af S |
584 | if isinstance(source_file, dict): |
585 | download_url = source_file.get('download_url') | |
586 | if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'): | |
587 | source_name = source_file.get('public_name', 'Original') | |
588 | if self._is_valid_url(download_url, video_id, '%s video' % source_name): | |
4519c1f4 | 589 | ext = source_file.get('extension', determine_ext(download_url)).lower() |
d5f071af S |
590 | formats.append({ |
591 | 'url': download_url, | |
592 | 'ext': ext, | |
593 | 'width': int_or_none(source_file.get('width')), | |
594 | 'height': int_or_none(source_file.get('height')), | |
595 | 'filesize': parse_filesize(source_file.get('size')), | |
596 | 'format_id': source_name, | |
597 | 'preference': 1, | |
598 | }) | |
1eac553e | 599 | |
531a7496 YCH |
600 | info_dict = self._parse_config(config, video_id) |
601 | formats.extend(info_dict['formats']) | |
602 | self._vimeo_sort_formats(formats) | |
603 | info_dict.update({ | |
b0268cb6 | 604 | 'id': video_id, |
531a7496 | 605 | 'formats': formats, |
b0268cb6 | 606 | 'upload_date': video_upload_date, |
b0268cb6 | 607 | 'description': video_description, |
9103bbc5 | 608 | 'webpage_url': url, |
4e761794 JMF |
609 | 'view_count': view_count, |
610 | 'like_count': like_count, | |
611 | 'comment_count': comment_count, | |
531a7496 YCH |
612 | }) |
613 | ||
614 | return info_dict | |
caeefc29 JMF |
615 | |
616 | ||
74278def | 617 | class VimeoOndemandIE(VimeoBaseInfoExtractor): |
1e501364 | 618 | IE_NAME = 'vimeo:ondemand' |
74278def S |
619 | _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?P<id>[^/?#&]+)' |
620 | _TESTS = [{ | |
621 | # ondemand video not available via https://vimeo.com/id | |
622 | 'url': 'https://vimeo.com/ondemand/20704', | |
623 | 'md5': 'c424deda8c7f73c1dfb3edd7630e2f35', | |
624 | 'info_dict': { | |
625 | 'id': '105442900', | |
626 | 'ext': 'mp4', | |
627 | 'title': 'המעבדה - במאי יותם פלדמן', | |
628 | 'uploader': 'גם סרטים', | |
ec85ded8 | 629 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms', |
74278def S |
630 | 'uploader_id': 'gumfilms', |
631 | }, | |
d002e919 S |
632 | }, { |
633 | # requires Referer to be passed along with og:video:url | |
634 | 'url': 'https://vimeo.com/ondemand/36938/126682985', | |
635 | 'info_dict': { | |
636 | 'id': '126682985', | |
637 | 'ext': 'mp4', | |
638 | 'title': 'Rävlock, rätt läte på rätt plats', | |
639 | 'uploader': 'Lindroth & Norin', | |
ec85ded8 | 640 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user14430847', |
d002e919 S |
641 | 'uploader_id': 'user14430847', |
642 | }, | |
643 | 'params': { | |
644 | 'skip_download': True, | |
645 | }, | |
74278def S |
646 | }, { |
647 | 'url': 'https://vimeo.com/ondemand/nazmaalik', | |
648 | 'only_matching': True, | |
649 | }, { | |
650 | 'url': 'https://vimeo.com/ondemand/141692381', | |
651 | 'only_matching': True, | |
652 | }, { | |
653 | 'url': 'https://vimeo.com/ondemand/thelastcolony/150274832', | |
654 | 'only_matching': True, | |
655 | }] | |
656 | ||
657 | def _real_extract(self, url): | |
658 | video_id = self._match_id(url) | |
659 | webpage = self._download_webpage(url, video_id) | |
d002e919 S |
660 | return self.url_result( |
661 | # Some videos require Referer to be passed along with og:video:url | |
662 | # similarly to generic vimeo embeds (e.g. | |
663 | # https://vimeo.com/ondemand/36938/126682985). | |
664 | VimeoIE._smuggle_referrer(self._og_search_video_url(webpage), url), | |
665 | VimeoIE.ie_key()) | |
74278def S |
666 | |
667 | ||
f6c3664d | 668 | class VimeoChannelIE(VimeoBaseInfoExtractor): |
9148eb00 | 669 | IE_NAME = 'vimeo:channel' |
3946864c | 670 | _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])' |
caeefc29 | 671 | _MORE_PAGES_INDICATOR = r'<a.+?rel="next"' |
84458766 | 672 | _TITLE = None |
55a10eab | 673 | _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"' |
2929b3e7 | 674 | _TESTS = [{ |
3946864c | 675 | 'url': 'https://vimeo.com/channels/tributes', |
2929b3e7 | 676 | 'info_dict': { |
a3fa5da4 | 677 | 'id': 'tributes', |
2929b3e7 PH |
678 | 'title': 'Vimeo Tributes', |
679 | }, | |
680 | 'playlist_mincount': 25, | |
681 | }] | |
caeefc29 | 682 | |
5cc14c2f JMF |
683 | def _page_url(self, base_url, pagenum): |
684 | return '%s/videos/page:%d/' % (base_url, pagenum) | |
685 | ||
fb30ec22 | 686 | def _extract_list_title(self, webpage): |
84458766 | 687 | return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title') |
fb30ec22 | 688 | |
bf8f082a PH |
689 | def _login_list_password(self, page_url, list_id, webpage): |
690 | login_form = self._search_regex( | |
691 | r'(?s)<form[^>]+?id="pw_form"(.*?)</form>', | |
692 | webpage, 'login form', default=None) | |
693 | if not login_form: | |
694 | return webpage | |
695 | ||
d800609c | 696 | password = self._downloader.params.get('videopassword') |
bf8f082a PH |
697 | if password is None: |
698 | raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True) | |
f8da79f8 | 699 | fields = self._hidden_inputs(login_form) |
7c845629 | 700 | token, vuid = self._extract_xsrft_and_vuid(webpage) |
bf8f082a PH |
701 | fields['token'] = token |
702 | fields['password'] = password | |
15707c7e | 703 | post = urlencode_postdata(fields) |
bf8f082a PH |
704 | password_path = self._search_regex( |
705 | r'action="([^"]+)"', login_form, 'password URL') | |
706 | password_url = compat_urlparse.urljoin(page_url, password_path) | |
67dda517 | 707 | password_request = sanitized_Request(password_url, post) |
bf8f082a | 708 | password_request.add_header('Content-type', 'application/x-www-form-urlencoded') |
9eab37dc S |
709 | self._set_vimeo_cookie('vuid', vuid) |
710 | self._set_vimeo_cookie('xsrft', token) | |
bf8f082a PH |
711 | |
712 | return self._download_webpage( | |
713 | password_request, list_id, | |
714 | 'Verifying the password', 'Wrong password') | |
715 | ||
2c94198e | 716 | def _title_and_entries(self, list_id, base_url): |
caeefc29 | 717 | for pagenum in itertools.count(1): |
bf8f082a | 718 | page_url = self._page_url(base_url, pagenum) |
55a10eab | 719 | webpage = self._download_webpage( |
bf8f082a | 720 | page_url, list_id, |
9148eb00 | 721 | 'Downloading page %s' % pagenum) |
bf8f082a PH |
722 | |
723 | if pagenum == 1: | |
724 | webpage = self._login_list_password(page_url, list_id, webpage) | |
2c94198e S |
725 | yield self._extract_list_title(webpage) |
726 | ||
c8e3e097 S |
727 | # Try extracting href first since not all videos are available via |
728 | # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729) | |
729 | clips = re.findall( | |
730 | r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)', webpage) | |
731 | if clips: | |
732 | for video_id, video_url in clips: | |
733 | yield self.url_result( | |
734 | compat_urlparse.urljoin(base_url, video_url), | |
735 | VimeoIE.ie_key(), video_id=video_id) | |
736 | # More relaxed fallback | |
737 | else: | |
738 | for video_id in re.findall(r'id=["\']clip_(\d+)', webpage): | |
739 | yield self.url_result( | |
740 | 'https://vimeo.com/%s' % video_id, | |
741 | VimeoIE.ie_key(), video_id=video_id) | |
bf8f082a | 742 | |
caeefc29 JMF |
743 | if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None: |
744 | break | |
745 | ||
2c94198e S |
746 | def _extract_videos(self, list_id, base_url): |
747 | title_and_entries = self._title_and_entries(list_id, base_url) | |
748 | list_title = next(title_and_entries) | |
749 | return self.playlist_result(title_and_entries, list_id, list_title) | |
55a10eab JMF |
750 | |
751 | def _real_extract(self, url): | |
752 | mobj = re.match(self._VALID_URL, url) | |
4f3e9430 | 753 | channel_id = mobj.group('id') |
3946864c | 754 | return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id) |
55a10eab JMF |
755 | |
756 | ||
757 | class VimeoUserIE(VimeoChannelIE): | |
9148eb00 | 758 | IE_NAME = 'vimeo:user' |
b29440ae | 759 | _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)' |
55a10eab | 760 | _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>' |
2929b3e7 | 761 | _TESTS = [{ |
3946864c | 762 | 'url': 'https://vimeo.com/nkistudio/videos', |
2929b3e7 PH |
763 | 'info_dict': { |
764 | 'title': 'Nki', | |
a3fa5da4 | 765 | 'id': 'nkistudio', |
2929b3e7 PH |
766 | }, |
767 | 'playlist_mincount': 66, | |
768 | }] | |
55a10eab JMF |
769 | |
770 | def _real_extract(self, url): | |
771 | mobj = re.match(self._VALID_URL, url) | |
772 | name = mobj.group('name') | |
3946864c | 773 | return self._extract_videos(name, 'https://vimeo.com/%s' % name) |
5cc14c2f JMF |
774 | |
775 | ||
776 | class VimeoAlbumIE(VimeoChannelIE): | |
9148eb00 | 777 | IE_NAME = 'vimeo:album' |
b5eab86c | 778 | _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)(?:$|[?#]|/(?!video))' |
5cc14c2f | 779 | _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>' |
2929b3e7 | 780 | _TESTS = [{ |
d1508cd6 | 781 | 'url': 'https://vimeo.com/album/2632481', |
2929b3e7 | 782 | 'info_dict': { |
a3fa5da4 | 783 | 'id': '2632481', |
2929b3e7 PH |
784 | 'title': 'Staff Favorites: November 2013', |
785 | }, | |
786 | 'playlist_mincount': 13, | |
bf8f082a PH |
787 | }, { |
788 | 'note': 'Password-protected album', | |
789 | 'url': 'https://vimeo.com/album/3253534', | |
790 | 'info_dict': { | |
791 | 'title': 'test', | |
792 | 'id': '3253534', | |
793 | }, | |
794 | 'playlist_count': 1, | |
795 | 'params': { | |
796 | 'videopassword': 'youtube-dl', | |
797 | } | |
b5eab86c S |
798 | }, { |
799 | 'url': 'https://vimeo.com/album/2632481/sort:plays/format:thumbnail', | |
800 | 'only_matching': True, | |
089657ed S |
801 | }, { |
802 | # TODO: respect page number | |
803 | 'url': 'https://vimeo.com/album/2632481/page:2/sort:plays/format:thumbnail', | |
804 | 'only_matching': True, | |
2929b3e7 | 805 | }] |
5cc14c2f JMF |
806 | |
807 | def _page_url(self, base_url, pagenum): | |
808 | return '%s/page:%d/' % (base_url, pagenum) | |
809 | ||
810 | def _real_extract(self, url): | |
bf8f082a | 811 | album_id = self._match_id(url) |
d1508cd6 | 812 | return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id) |
fb30ec22 JMF |
813 | |
814 | ||
815 | class VimeoGroupsIE(VimeoAlbumIE): | |
9148eb00 | 816 | IE_NAME = 'vimeo:group' |
fdb20a27 | 817 | _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)' |
2929b3e7 | 818 | _TESTS = [{ |
3946864c | 819 | 'url': 'https://vimeo.com/groups/rolexawards', |
2929b3e7 | 820 | 'info_dict': { |
a3fa5da4 | 821 | 'id': 'rolexawards', |
2929b3e7 PH |
822 | 'title': 'Rolex Awards for Enterprise', |
823 | }, | |
824 | 'playlist_mincount': 73, | |
825 | }] | |
fb30ec22 JMF |
826 | |
827 | def _extract_list_title(self, webpage): | |
828 | return self._og_search_title(webpage) | |
829 | ||
830 | def _real_extract(self, url): | |
831 | mobj = re.match(self._VALID_URL, url) | |
832 | name = mobj.group('name') | |
3946864c | 833 | return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name) |
fcea44c6 PH |
834 | |
835 | ||
531a7496 | 836 | class VimeoReviewIE(VimeoBaseInfoExtractor): |
9148eb00 PH |
837 | IE_NAME = 'vimeo:review' |
838 | IE_DESC = 'Review pages on vimeo' | |
3946864c | 839 | _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)' |
d36d3f42 | 840 | _TESTS = [{ |
fcea44c6 | 841 | 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d', |
fcea44c6 PH |
842 | 'md5': 'c507a72f780cacc12b2248bb4006d253', |
843 | 'info_dict': { | |
fc09240e PH |
844 | 'id': '75524534', |
845 | 'ext': 'mp4', | |
fcea44c6 PH |
846 | 'title': "DICK HARDWICK 'Comedian'", |
847 | 'uploader': 'Richard Hardwick', | |
531a7496 | 848 | 'uploader_id': 'user21297594', |
fcea44c6 | 849 | } |
d36d3f42 PH |
850 | }, { |
851 | 'note': 'video player needs Referer', | |
3946864c | 852 | 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053', |
d36d3f42 PH |
853 | 'md5': '6295fdab8f4bf6a002d058b2c6dce276', |
854 | 'info_dict': { | |
855 | 'id': '91613211', | |
856 | 'ext': 'mp4', | |
9dec9930 | 857 | 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn', |
d36d3f42 PH |
858 | 'uploader': 'DevWeek Events', |
859 | 'duration': 2773, | |
ec85ded8 | 860 | 'thumbnail': r're:^https?://.*\.jpg$', |
531a7496 | 861 | 'uploader_id': 'user22258446', |
d36d3f42 | 862 | } |
c1ff6e1a YCH |
863 | }, { |
864 | 'note': 'Password protected', | |
865 | 'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde', | |
866 | 'info_dict': { | |
867 | 'id': '138823582', | |
868 | 'ext': 'mp4', | |
869 | 'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1', | |
870 | 'uploader': 'TMB', | |
871 | 'uploader_id': 'user37284429', | |
872 | }, | |
873 | 'params': { | |
874 | 'videopassword': 'holygrail', | |
875 | }, | |
a093cfc7 | 876 | 'skip': 'video gone', |
d36d3f42 | 877 | }] |
fcea44c6 | 878 | |
c1ff6e1a YCH |
879 | def _real_initialize(self): |
880 | self._login() | |
881 | ||
882 | def _get_config_url(self, webpage_url, video_id, video_password_verified=False): | |
883 | webpage = self._download_webpage(webpage_url, video_id) | |
a093cfc7 YCH |
884 | data = self._parse_json(self._search_regex( |
885 | r'window\s*=\s*_extend\(window,\s*({.+?})\);', webpage, 'data', | |
886 | default=NO_DEFAULT if video_password_verified else '{}'), video_id) | |
887 | config_url = data.get('vimeo_esi', {}).get('config', {}).get('configUrl') | |
c1ff6e1a YCH |
888 | if config_url is None: |
889 | self._verify_video_password(webpage_url, video_id, webpage) | |
890 | config_url = self._get_config_url( | |
891 | webpage_url, video_id, video_password_verified=True) | |
892 | return config_url | |
893 | ||
fcea44c6 | 894 | def _real_extract(self, url): |
531a7496 | 895 | video_id = self._match_id(url) |
c1ff6e1a YCH |
896 | config_url = self._get_config_url(url, video_id) |
897 | config = self._download_json(config_url, video_id) | |
531a7496 YCH |
898 | info_dict = self._parse_config(config, video_id) |
899 | self._vimeo_sort_formats(info_dict['formats']) | |
900 | info_dict['id'] = video_id | |
901 | return info_dict | |
efb7e119 JMF |
902 | |
903 | ||
f6c3664d | 904 | class VimeoWatchLaterIE(VimeoChannelIE): |
efb7e119 JMF |
905 | IE_NAME = 'vimeo:watchlater' |
906 | IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)' | |
84458766 S |
907 | _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater' |
908 | _TITLE = 'Watch Later' | |
efb7e119 | 909 | _LOGIN_REQUIRED = True |
2929b3e7 | 910 | _TESTS = [{ |
84458766 | 911 | 'url': 'https://vimeo.com/watchlater', |
2929b3e7 PH |
912 | 'only_matching': True, |
913 | }] | |
efb7e119 JMF |
914 | |
915 | def _real_initialize(self): | |
916 | self._login() | |
917 | ||
918 | def _page_url(self, base_url, pagenum): | |
919 | url = '%s/page:%d/' % (base_url, pagenum) | |
67dda517 | 920 | request = sanitized_Request(url) |
efb7e119 JMF |
921 | # Set the header to get a partial html page with the ids, |
922 | # the normal page doesn't contain them. | |
923 | request.add_header('X-Requested-With', 'XMLHttpRequest') | |
924 | return request | |
925 | ||
926 | def _real_extract(self, url): | |
84458766 | 927 | return self._extract_videos('watchlater', 'https://vimeo.com/watchlater') |
d6e6a422 PH |
928 | |
929 | ||
930 | class VimeoLikesIE(InfoExtractor): | |
3946864c | 931 | _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)' |
d6e6a422 PH |
932 | IE_NAME = 'vimeo:likes' |
933 | IE_DESC = 'Vimeo user likes' | |
934 | _TEST = { | |
9c44d242 PH |
935 | 'url': 'https://vimeo.com/user755559/likes/', |
936 | 'playlist_mincount': 293, | |
611c1dd9 | 937 | 'info_dict': { |
a3fa5da4 | 938 | 'id': 'user755559_likes', |
611c1dd9 S |
939 | 'description': 'See all the videos urza likes', |
940 | 'title': 'Videos urza likes', | |
d6e6a422 PH |
941 | }, |
942 | } | |
943 | ||
944 | def _real_extract(self, url): | |
945 | user_id = self._match_id(url) | |
9c44d242 PH |
946 | webpage = self._download_webpage(url, user_id) |
947 | page_count = self._int( | |
948 | self._search_regex( | |
949 | r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)"> | |
950 | .*?</a></li>\s*<li\s+class="pagination_next"> | |
951 | ''', webpage, 'page count'), | |
952 | 'page count', fatal=True) | |
953 | PAGE_SIZE = 12 | |
954 | title = self._html_search_regex( | |
955 | r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False) | |
956 | description = self._html_search_meta('description', webpage) | |
957 | ||
958 | def _get_page(idx): | |
3946864c JMF |
959 | page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % ( |
960 | user_id, idx + 1) | |
9c44d242 PH |
961 | webpage = self._download_webpage( |
962 | page_url, user_id, | |
963 | note='Downloading page %d/%d' % (idx + 1, page_count)) | |
964 | video_list = self._search_regex( | |
965 | r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>', | |
966 | webpage, 'video content') | |
967 | paths = re.findall( | |
968 | r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list) | |
969 | for path in paths: | |
970 | yield { | |
971 | '_type': 'url', | |
972 | 'url': compat_urlparse.urljoin(page_url, path), | |
973 | } | |
974 | ||
975 | pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE) | |
d6e6a422 PH |
976 | |
977 | return { | |
9c44d242 PH |
978 | '_type': 'playlist', |
979 | 'id': 'user%s_likes' % user_id, | |
980 | 'title': title, | |
981 | 'description': description, | |
982 | 'entries': pl, | |
d6e6a422 | 983 | } |