]>
Commit | Line | Data |
---|---|---|
93b22c78 | 1 | # encoding: 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, | |
55b3e45b | 19 | RegexNotFoundError, |
67dda517 | 20 | sanitized_Request, |
30965ac6 | 21 | smuggle_url, |
b3d14cbf | 22 | std_headers, |
3c6f2450 | 23 | unified_strdate, |
9d4660ca | 24 | unsmuggle_url, |
a980bc43 | 25 | urlencode_postdata, |
b407e173 | 26 | unescapeHTML, |
eb4f2740 | 27 | parse_filesize, |
6a55bb66 | 28 | try_get, |
b3d14cbf PH |
29 | ) |
30 | ||
bbafbe20 | 31 | |
efb7e119 JMF |
32 | class VimeoBaseInfoExtractor(InfoExtractor): |
33 | _NETRC_MACHINE = 'vimeo' | |
34 | _LOGIN_REQUIRED = False | |
f6c3664d | 35 | _LOGIN_URL = 'https://vimeo.com/log_in' |
efb7e119 JMF |
36 | |
37 | def _login(self): | |
38 | (username, password) = self._get_login_info() | |
39 | if username is None: | |
40 | if self._LOGIN_REQUIRED: | |
4f3e9430 | 41 | raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) |
efb7e119 JMF |
42 | return |
43 | self.report_login() | |
f6c3664d | 44 | webpage = self._download_webpage(self._LOGIN_URL, None, False) |
7c845629 | 45 | token, vuid = self._extract_xsrft_and_vuid(webpage) |
15707c7e | 46 | data = urlencode_postdata({ |
f6c3664d | 47 | 'action': 'login', |
efb7e119 JMF |
48 | 'email': username, |
49 | 'password': password, | |
efb7e119 JMF |
50 | 'service': 'vimeo', |
51 | 'token': token, | |
15707c7e | 52 | }) |
67dda517 | 53 | login_request = sanitized_Request(self._LOGIN_URL, data) |
efb7e119 | 54 | login_request.add_header('Content-Type', 'application/x-www-form-urlencoded') |
f6c3664d | 55 | login_request.add_header('Referer', self._LOGIN_URL) |
9eab37dc | 56 | self._set_vimeo_cookie('vuid', vuid) |
efb7e119 JMF |
57 | self._download_webpage(login_request, None, False, 'Wrong login info') |
58 | ||
7c845629 S |
59 | def _extract_xsrft_and_vuid(self, webpage): |
60 | xsrft = self._search_regex( | |
b826035d | 61 | r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)', |
f6c3664d | 62 | webpage, 'login token', group='xsrft') |
7c845629 S |
63 | vuid = self._search_regex( |
64 | r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1', | |
65 | webpage, 'vuid', group='vuid') | |
66 | return xsrft, vuid | |
f6c3664d | 67 | |
9eab37dc S |
68 | def _set_vimeo_cookie(self, name, value): |
69 | self._set_cookie('vimeo.com', name, value) | |
70 | ||
531a7496 YCH |
71 | def _vimeo_sort_formats(self, formats): |
72 | # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps | |
73 | # at the same time without actual units specified. This lead to wrong sorting. | |
74 | self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'format_id')) | |
75 | ||
76 | def _parse_config(self, config, video_id): | |
77 | # Extract title | |
78 | video_title = config['video']['title'] | |
79 | ||
80 | # Extract uploader, uploader_url and uploader_id | |
81 | video_uploader = config['video'].get('owner', {}).get('name') | |
82 | video_uploader_url = config['video'].get('owner', {}).get('url') | |
83 | video_uploader_id = video_uploader_url.split('/')[-1] if video_uploader_url else None | |
84 | ||
85 | # Extract video thumbnail | |
86 | video_thumbnail = config['video'].get('thumbnail') | |
87 | if video_thumbnail is None: | |
88 | video_thumbs = config['video'].get('thumbs') | |
89 | if video_thumbs and isinstance(video_thumbs, dict): | |
90 | _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1] | |
91 | ||
92 | # Extract video duration | |
93 | video_duration = int_or_none(config['video'].get('duration')) | |
94 | ||
95 | formats = [] | |
96 | config_files = config['video'].get('files') or config['request'].get('files', {}) | |
97 | for f in config_files.get('progressive', []): | |
98 | video_url = f.get('url') | |
99 | if not video_url: | |
100 | continue | |
101 | formats.append({ | |
102 | 'url': video_url, | |
103 | 'format_id': 'http-%s' % f.get('quality'), | |
104 | 'width': int_or_none(f.get('width')), | |
105 | 'height': int_or_none(f.get('height')), | |
106 | 'fps': int_or_none(f.get('fps')), | |
107 | 'tbr': int_or_none(f.get('bitrate')), | |
108 | }) | |
109 | m3u8_url = config_files.get('hls', {}).get('url') | |
110 | if m3u8_url: | |
111 | formats.extend(self._extract_m3u8_formats( | |
112 | m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)) | |
113 | ||
114 | subtitles = {} | |
115 | text_tracks = config['request'].get('text_tracks') | |
116 | if text_tracks: | |
117 | for tt in text_tracks: | |
118 | subtitles[tt['lang']] = [{ | |
119 | 'ext': 'vtt', | |
120 | 'url': 'https://vimeo.com' + tt['url'], | |
121 | }] | |
122 | ||
123 | return { | |
124 | 'title': video_title, | |
125 | 'uploader': video_uploader, | |
126 | 'uploader_id': video_uploader_id, | |
127 | 'uploader_url': video_uploader_url, | |
128 | 'thumbnail': video_thumbnail, | |
129 | 'duration': video_duration, | |
130 | 'formats': formats, | |
131 | 'subtitles': subtitles, | |
132 | } | |
133 | ||
efb7e119 | 134 | |
65469a7f | 135 | class VimeoIE(VimeoBaseInfoExtractor): |
b3d14cbf PH |
136 | """Information extractor for vimeo.com.""" |
137 | ||
138 | # _VALID_URL matches Vimeo URLs | |
bbafbe20 | 139 | _VALID_URL = r'''(?x) |
74278def S |
140 | https?:// |
141 | (?: | |
142 | (?: | |
143 | www| | |
144 | (?P<player>player) | |
145 | ) | |
146 | \. | |
147 | )? | |
148 | vimeo(?P<pro>pro)?\.com/ | |
c8e3e097 | 149 | (?!(?:channels|album)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/) |
74278def S |
150 | (?:.*?/)? |
151 | (?: | |
152 | (?: | |
153 | play_redirect_hls| | |
154 | moogaloop\.swf)\?clip_id= | |
155 | )? | |
156 | (?:videos?/)? | |
157 | (?P<id>[0-9]+) | |
241a318f | 158 | (?:/[\da-f]+)? |
74278def S |
159 | /?(?:[?&].*)?(?:[#].*)?$ |
160 | ''' | |
9148eb00 | 161 | IE_NAME = 'vimeo' |
a91b954b JMF |
162 | _TESTS = [ |
163 | { | |
9148eb00 | 164 | 'url': 'http://vimeo.com/56015672#at=0', |
9148eb00 PH |
165 | 'md5': '8879b6cc097e987f02484baf890129e5', |
166 | 'info_dict': { | |
ad5976b4 PH |
167 | 'id': '56015672', |
168 | 'ext': 'mp4', | |
68f3b61f S |
169 | 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", |
170 | 'description': 'md5:2d3305bad981a06ff79f027f19865021', | |
171 | 'upload_date': '20121220', | |
a2d7797c | 172 | 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user7108434', |
68f3b61f S |
173 | 'uploader_id': 'user7108434', |
174 | 'uploader': 'Filippo Valsorda', | |
175 | 'duration': 10, | |
a91b954b JMF |
176 | }, |
177 | }, | |
178 | { | |
9148eb00 | 179 | 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876', |
9148eb00 PH |
180 | 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82', |
181 | 'note': 'Vimeo Pro video (#1197)', | |
182 | 'info_dict': { | |
4f3e9430 JMF |
183 | 'id': '68093876', |
184 | 'ext': 'mp4', | |
a2d7797c | 185 | 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/openstreetmapus', |
9148eb00 PH |
186 | 'uploader_id': 'openstreetmapus', |
187 | 'uploader': 'OpenStreetMap US', | |
188 | 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography', | |
68f3b61f | 189 | 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30', |
69c8fb9e | 190 | 'duration': 1595, |
a91b954b JMF |
191 | }, |
192 | }, | |
aa32314d | 193 | { |
9148eb00 | 194 | 'url': 'http://player.vimeo.com/video/54469442', |
9148eb00 PH |
195 | 'md5': '619b811a4417aa4abe78dc653becf511', |
196 | 'note': 'Videos that embed the url in the player page', | |
197 | 'info_dict': { | |
4f3e9430 JMF |
198 | 'id': '54469442', |
199 | 'ext': 'mp4', | |
0e6ebc13 | 200 | 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012', |
9148eb00 | 201 | 'uploader': 'The BLN & Business of Software', |
a2d7797c | 202 | 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware', |
9148eb00 | 203 | 'uploader_id': 'theblnbusinessofsoftware', |
69c8fb9e | 204 | 'duration': 3610, |
58ea7ec8 | 205 | 'description': None, |
aa32314d | 206 | }, |
93b22c78 JMF |
207 | }, |
208 | { | |
9148eb00 | 209 | 'url': 'http://vimeo.com/68375962', |
9148eb00 PH |
210 | 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7', |
211 | 'note': 'Video protected with password', | |
212 | 'info_dict': { | |
4f3e9430 JMF |
213 | 'id': '68375962', |
214 | 'ext': 'mp4', | |
9148eb00 PH |
215 | 'title': 'youtube-dl password protected test video', |
216 | 'upload_date': '20130614', | |
a2d7797c | 217 | 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user18948128', |
9148eb00 PH |
218 | 'uploader_id': 'user18948128', |
219 | 'uploader': 'Jaime Marquínez Ferrándiz', | |
69c8fb9e | 220 | 'duration': 10, |
531a7496 | 221 | '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 | 222 | }, |
9148eb00 PH |
223 | 'params': { |
224 | 'videopassword': 'youtube-dl', | |
93b22c78 JMF |
225 | }, |
226 | }, | |
548f31d9 S |
227 | { |
228 | 'url': 'http://vimeo.com/channels/keypeele/75629013', | |
229 | 'md5': '2f86a05afe9d7abc0b9126d229bbe15d', | |
548f31d9 S |
230 | 'info_dict': { |
231 | 'id': '75629013', | |
232 | 'ext': 'mp4', | |
233 | 'title': 'Key & Peele: Terrorist Interrogation', | |
234 | 'description': 'md5:8678b246399b070816b12313e8b4eb5c', | |
a2d7797c | 235 | 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/atencio', |
548f31d9 S |
236 | 'uploader_id': 'atencio', |
237 | 'uploader': 'Peter Atencio', | |
3c6f2450 | 238 | 'upload_date': '20130927', |
548f31d9 S |
239 | 'duration': 187, |
240 | }, | |
241 | }, | |
1eac553e S |
242 | { |
243 | 'url': 'http://vimeo.com/76979871', | |
1eac553e S |
244 | 'note': 'Video with subtitles', |
245 | 'info_dict': { | |
246 | 'id': '76979871', | |
247 | 'ext': 'mp4', | |
248 | 'title': 'The New Vimeo Player (You Know, For Videos)', | |
249 | 'description': 'md5:2ec900bf97c3f389378a96aee11260ea', | |
250 | 'upload_date': '20131015', | |
a2d7797c | 251 | 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/staff', |
1eac553e S |
252 | 'uploader_id': 'staff', |
253 | 'uploader': 'Vimeo Staff', | |
69c8fb9e | 254 | 'duration': 62, |
1eac553e S |
255 | } |
256 | }, | |
4698f0d8 JMF |
257 | { |
258 | # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/ | |
259 | 'url': 'https://player.vimeo.com/video/98044508', | |
260 | 'note': 'The js code contains assignments to the same variable as the config', | |
261 | 'info_dict': { | |
262 | 'id': '98044508', | |
263 | 'ext': 'mp4', | |
264 | 'title': 'Pier Solar OUYA Official Trailer', | |
265 | 'uploader': 'Tulio Gonçalves', | |
a2d7797c | 266 | 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user28849593', |
4698f0d8 JMF |
267 | 'uploader_id': 'user28849593', |
268 | }, | |
269 | }, | |
323f82a7 | 270 | { |
271 | # contains original format | |
272 | 'url': 'https://vimeo.com/33951933', | |
c143ddce | 273 | 'md5': '2d9f5475e0537f013d0073e812ab89e6', |
323f82a7 | 274 | 'info_dict': { |
275 | 'id': '33951933', | |
276 | 'ext': 'mp4', | |
277 | 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute', | |
278 | 'uploader': 'The DMCI', | |
a2d7797c | 279 | 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/dmci', |
323f82a7 | 280 | 'uploader_id': 'dmci', |
281 | 'upload_date': '20111220', | |
282 | 'description': 'md5:ae23671e82d05415868f7ad1aec21147', | |
283 | }, | |
284 | }, | |
c143ddce S |
285 | { |
286 | # only available via https://vimeo.com/channels/tributes/6213729 and | |
287 | # not via https://vimeo.com/6213729 | |
288 | 'url': 'https://vimeo.com/channels/tributes/6213729', | |
289 | 'info_dict': { | |
290 | 'id': '6213729', | |
291 | 'ext': 'mp4', | |
292 | 'title': 'Vimeo Tribute: The Shining', | |
293 | 'uploader': 'Casey Donahue', | |
294 | 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/caseydonahue', | |
295 | 'uploader_id': 'caseydonahue', | |
296 | 'upload_date': '20090821', | |
297 | 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6', | |
298 | }, | |
299 | 'params': { | |
300 | 'skip_download': True, | |
301 | }, | |
302 | 'expected_warnings': ['Unable to download JSON metadata'], | |
303 | }, | |
304 | { | |
305 | 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741', | |
306 | 'only_matching': True, | |
307 | }, | |
8bea039b LL |
308 | { |
309 | 'url': 'https://vimeo.com/109815029', | |
310 | 'note': 'Video not completely processed, "failed" seed status', | |
311 | 'only_matching': True, | |
312 | }, | |
6b7ceee1 S |
313 | { |
314 | 'url': 'https://vimeo.com/groups/travelhd/videos/22439234', | |
315 | 'only_matching': True, | |
316 | }, | |
c8e3e097 S |
317 | { |
318 | 'url': 'https://vimeo.com/album/2632481/video/79010983', | |
319 | 'only_matching': True, | |
320 | }, | |
16f1131a S |
321 | { |
322 | # source file returns 403: Forbidden | |
323 | 'url': 'https://vimeo.com/7809605', | |
324 | 'only_matching': True, | |
325 | }, | |
241a318f S |
326 | { |
327 | 'url': 'https://vimeo.com/160743502/abd0e13fb4', | |
328 | 'only_matching': True, | |
329 | } | |
a91b954b | 330 | ] |
b3d14cbf | 331 | |
b407e173 YCH |
332 | @staticmethod |
333 | def _extract_vimeo_url(url, webpage): | |
334 | # Look for embedded (iframe) Vimeo player | |
335 | mobj = re.search( | |
336 | r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage) | |
337 | if mobj: | |
338 | player_url = unescapeHTML(mobj.group('url')) | |
5dbe81a1 | 339 | surl = smuggle_url(player_url, {'http_headers': {'Referer': url}}) |
b407e173 YCH |
340 | return surl |
341 | # Look for embedded (swf embed) Vimeo player | |
342 | mobj = re.search( | |
343 | r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage) | |
344 | if mobj: | |
345 | return mobj.group(1) | |
346 | ||
b3d14cbf | 347 | def _verify_video_password(self, url, video_id, webpage): |
d800609c | 348 | password = self._downloader.params.get('videopassword') |
b3d14cbf | 349 | if password is None: |
93a16ba2 | 350 | raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True) |
7c845629 | 351 | token, vuid = self._extract_xsrft_and_vuid(webpage) |
15707c7e | 352 | data = urlencode_postdata({ |
4f3e9430 JMF |
353 | 'password': password, |
354 | 'token': token, | |
15707c7e | 355 | }) |
9c85b537 JMF |
356 | if url.startswith('http://'): |
357 | # vimeo only supports https now, but the user can give an http url | |
358 | url = url.replace('http://', 'https://') | |
67dda517 | 359 | password_request = sanitized_Request(url + '/password', data) |
b3d14cbf | 360 | password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') |
12bb392a | 361 | password_request.add_header('Referer', url) |
9eab37dc | 362 | self._set_vimeo_cookie('vuid', vuid) |
bf8f082a PH |
363 | return self._download_webpage( |
364 | password_request, video_id, | |
365 | 'Verifying the password', 'Wrong password') | |
b3d14cbf | 366 | |
0eecc6a4 | 367 | def _verify_player_video_password(self, url, video_id): |
d800609c | 368 | password = self._downloader.params.get('videopassword') |
0eecc6a4 PH |
369 | if password is None: |
370 | raise ExtractorError('This video is protected by a password, use the --video-password option') | |
15707c7e | 371 | data = urlencode_postdata({'password': password}) |
0eecc6a4 | 372 | pass_url = url + '/check-password' |
67dda517 | 373 | password_request = sanitized_Request(pass_url, data) |
0eecc6a4 | 374 | password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') |
bdbb8530 | 375 | password_request.add_header('Referer', url) |
0eecc6a4 PH |
376 | return self._download_json( |
377 | password_request, video_id, | |
bdbb8530 | 378 | 'Verifying the password', 'Wrong password') |
0eecc6a4 | 379 | |
fc79158d JMF |
380 | def _real_initialize(self): |
381 | self._login() | |
382 | ||
a0088bdf | 383 | def _real_extract(self, url): |
5dbe81a1 | 384 | url, data = unsmuggle_url(url, {}) |
0f56a4b4 | 385 | headers = std_headers.copy() |
5dbe81a1 | 386 | if 'http_headers' in data: |
5dbe81a1 | 387 | headers.update(data['http_headers']) |
ba5d51b3 PH |
388 | if 'Referer' not in headers: |
389 | headers['Referer'] = url | |
9d4660ca | 390 | |
b3d14cbf PH |
391 | # Extract ID from URL |
392 | mobj = re.match(self._VALID_URL, url) | |
b3d14cbf | 393 | video_id = mobj.group('id') |
58ea7ec8 | 394 | orig_url = url |
9103bbc5 | 395 | if mobj.group('pro') or mobj.group('player'): |
61e00a97 | 396 | url = 'https://player.vimeo.com/video/' + video_id |
c143ddce | 397 | elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')): |
10831b5e | 398 | url = 'https://vimeo.com/' + video_id |
b3d14cbf PH |
399 | |
400 | # Retrieve video webpage to extract further information | |
0f56a4b4 | 401 | request = sanitized_Request(url, headers=headers) |
1060425c PH |
402 | try: |
403 | webpage = self._download_webpage(request, video_id) | |
404 | except ExtractorError as ee: | |
405 | if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: | |
406 | errmsg = ee.cause.read() | |
407 | if b'Because of its privacy settings, this video cannot be played here' in errmsg: | |
408 | raise ExtractorError( | |
409 | 'Cannot download embed-only video without embedding ' | |
410 | 'URL. Please call youtube-dl with the URL of the page ' | |
411 | 'that embeds this video.', | |
412 | expected=True) | |
413 | raise | |
b3d14cbf PH |
414 | |
415 | # Now we begin extracting as much information as we can from what we | |
416 | # retrieved. First we extract the information common to all extractors, | |
417 | # and latter we extract those that are Vimeo specific. | |
418 | self.report_extraction(video_id) | |
419 | ||
998e6cdb | 420 | vimeo_config = self._search_regex( |
b6aa99af | 421 | r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage, |
998e6cdb S |
422 | 'vimeo config', default=None) |
423 | if vimeo_config: | |
424 | seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {}) | |
425 | if seed_status.get('state') == 'failed': | |
426 | raise ExtractorError( | |
b6aa99af | 427 | '%s said: %s' % (self.IE_NAME, seed_status['title']), |
998e6cdb S |
428 | expected=True) |
429 | ||
b3d14cbf PH |
430 | # Extract the config JSON |
431 | try: | |
93b22c78 JMF |
432 | try: |
433 | config_url = self._html_search_regex( | |
41a7b00f LL |
434 | r' data-config-url="(.+?)"', webpage, |
435 | 'config URL', default=None) | |
436 | if not config_url: | |
dd841752 S |
437 | # Sometimes new react-based page is served instead of old one that require |
438 | # different config URL extraction approach (see | |
439 | # https://github.com/rg3/youtube-dl/pull/7209) | |
41a7b00f LL |
440 | vimeo_clip_page_config = self._search_regex( |
441 | r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage, | |
442 | 'vimeo clip page config') | |
dd841752 S |
443 | config_url = self._parse_json( |
444 | vimeo_clip_page_config, video_id)['player']['config_url'] | |
93b22c78 JMF |
445 | config_json = self._download_webpage(config_url, video_id) |
446 | config = json.loads(config_json) | |
447 | except RegexNotFoundError: | |
448 | # For pro videos or player.vimeo.com urls | |
48ad51b2 JMF |
449 | # We try to find out to which variable is assigned the config dic |
450 | m_variable_name = re.search('(\w)\.video\.id', webpage) | |
451 | if m_variable_name is not None: | |
4698f0d8 | 452 | config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1)) |
48ad51b2 JMF |
453 | else: |
454 | config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});'] | |
9148eb00 | 455 | config = self._search_regex(config_re, webpage, 'info section', |
9e1a5b84 | 456 | flags=re.DOTALL) |
93b22c78 | 457 | config = json.loads(config) |
71907db3 | 458 | except Exception as e: |
b3d14cbf | 459 | if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage): |
9148eb00 | 460 | raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option') |
b3d14cbf | 461 | |
bf8f082a | 462 | if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None: |
5dbe81a1 | 463 | if '_video_password_verified' in data: |
30965ac6 | 464 | raise ExtractorError('video password verification failed!') |
b3d14cbf | 465 | self._verify_video_password(url, video_id, webpage) |
30965ac6 PH |
466 | return self._real_extract( |
467 | smuggle_url(url, {'_video_password_verified': 'verified'})) | |
b3d14cbf | 468 | else: |
9148eb00 | 469 | raise ExtractorError('Unable to extract info section', |
71907db3 | 470 | cause=e) |
559e370f PH |
471 | else: |
472 | if config.get('view') == 4: | |
0eecc6a4 | 473 | config = self._verify_player_video_password(url, video_id) |
b3d14cbf | 474 | |
6a55bb66 S |
475 | def is_rented(): |
476 | if '>You rented this title.<' in webpage: | |
477 | return True | |
478 | if config.get('user', {}).get('purchased'): | |
479 | return True | |
480 | label = try_get( | |
481 | config, lambda x: x['video']['vod']['purchase_options'][0]['label_string'], compat_str) | |
482 | if label and label.startswith('You rented this'): | |
483 | return True | |
484 | return False | |
485 | ||
486 | if is_rented(): | |
5dbe81a1 S |
487 | feature_id = config.get('video', {}).get('vod', {}).get('feature_id') |
488 | if feature_id and not data.get('force_feature_id', False): | |
489 | return self.url_result(smuggle_url( | |
490 | 'https://player.vimeo.com/player/%s' % feature_id, | |
491 | {'force_feature_id': True}), 'Vimeo') | |
492 | ||
b3d14cbf | 493 | # Extract video description |
58ea7ec8 | 494 | |
25930395 | 495 | video_description = self._html_search_regex( |
58ea7ec8 PH |
496 | r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>', |
497 | webpage, 'description', default=None) | |
498 | if not video_description: | |
499 | video_description = self._html_search_meta( | |
500 | 'description', webpage, default=None) | |
501 | if not video_description and mobj.group('pro'): | |
502 | orig_webpage = self._download_webpage( | |
503 | orig_url, video_id, | |
504 | note='Downloading webpage for description', | |
505 | fatal=False) | |
506 | if orig_webpage: | |
507 | video_description = self._html_search_meta( | |
508 | 'description', orig_webpage, default=None) | |
509 | if not video_description and not mobj.group('player'): | |
510 | self._downloader.report_warning('Cannot find video description') | |
b3d14cbf PH |
511 | |
512 | # Extract upload date | |
513 | video_upload_date = None | |
3c6f2450 | 514 | mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage) |
b3d14cbf | 515 | if mobj is not None: |
3c6f2450 | 516 | video_upload_date = unified_strdate(mobj.group(1)) |
b3d14cbf | 517 | |
4e761794 | 518 | try: |
9148eb00 PH |
519 | view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count')) |
520 | like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count')) | |
521 | comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count')) | |
4e761794 JMF |
522 | except RegexNotFoundError: |
523 | # This info is only available in vimeo.com/{id} urls | |
524 | view_count = None | |
525 | like_count = None | |
526 | comment_count = None | |
527 | ||
a6387bfd | 528 | formats = [] |
eb4f2740 | 529 | download_request = sanitized_Request('https://vimeo.com/%s?action=load_download_config' % video_id, headers={ |
530 | 'X-Requested-With': 'XMLHttpRequest'}) | |
531 | download_data = self._download_json(download_request, video_id, fatal=False) | |
532 | if download_data: | |
533 | source_file = download_data.get('source_file') | |
d5f071af S |
534 | if isinstance(source_file, dict): |
535 | download_url = source_file.get('download_url') | |
536 | if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'): | |
537 | source_name = source_file.get('public_name', 'Original') | |
538 | if self._is_valid_url(download_url, video_id, '%s video' % source_name): | |
4519c1f4 | 539 | ext = source_file.get('extension', determine_ext(download_url)).lower() |
d5f071af S |
540 | formats.append({ |
541 | 'url': download_url, | |
542 | 'ext': ext, | |
543 | 'width': int_or_none(source_file.get('width')), | |
544 | 'height': int_or_none(source_file.get('height')), | |
545 | 'filesize': parse_filesize(source_file.get('size')), | |
546 | 'format_id': source_name, | |
547 | 'preference': 1, | |
548 | }) | |
1eac553e | 549 | |
531a7496 YCH |
550 | info_dict = self._parse_config(config, video_id) |
551 | formats.extend(info_dict['formats']) | |
552 | self._vimeo_sort_formats(formats) | |
553 | info_dict.update({ | |
b0268cb6 | 554 | 'id': video_id, |
531a7496 | 555 | 'formats': formats, |
b0268cb6 | 556 | 'upload_date': video_upload_date, |
b0268cb6 | 557 | 'description': video_description, |
9103bbc5 | 558 | 'webpage_url': url, |
4e761794 JMF |
559 | 'view_count': view_count, |
560 | 'like_count': like_count, | |
561 | 'comment_count': comment_count, | |
531a7496 YCH |
562 | }) |
563 | ||
564 | return info_dict | |
caeefc29 JMF |
565 | |
566 | ||
74278def | 567 | class VimeoOndemandIE(VimeoBaseInfoExtractor): |
1e501364 | 568 | IE_NAME = 'vimeo:ondemand' |
74278def S |
569 | _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?P<id>[^/?#&]+)' |
570 | _TESTS = [{ | |
571 | # ondemand video not available via https://vimeo.com/id | |
572 | 'url': 'https://vimeo.com/ondemand/20704', | |
573 | 'md5': 'c424deda8c7f73c1dfb3edd7630e2f35', | |
574 | 'info_dict': { | |
575 | 'id': '105442900', | |
576 | 'ext': 'mp4', | |
577 | 'title': 'המעבדה - במאי יותם פלדמן', | |
578 | 'uploader': 'גם סרטים', | |
579 | 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/gumfilms', | |
580 | 'uploader_id': 'gumfilms', | |
581 | }, | |
582 | }, { | |
583 | 'url': 'https://vimeo.com/ondemand/nazmaalik', | |
584 | 'only_matching': True, | |
585 | }, { | |
586 | 'url': 'https://vimeo.com/ondemand/141692381', | |
587 | 'only_matching': True, | |
588 | }, { | |
589 | 'url': 'https://vimeo.com/ondemand/thelastcolony/150274832', | |
590 | 'only_matching': True, | |
591 | }] | |
592 | ||
593 | def _real_extract(self, url): | |
594 | video_id = self._match_id(url) | |
595 | webpage = self._download_webpage(url, video_id) | |
596 | return self.url_result(self._og_search_video_url(webpage), VimeoIE.ie_key()) | |
597 | ||
598 | ||
f6c3664d | 599 | class VimeoChannelIE(VimeoBaseInfoExtractor): |
9148eb00 | 600 | IE_NAME = 'vimeo:channel' |
3946864c | 601 | _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])' |
caeefc29 | 602 | _MORE_PAGES_INDICATOR = r'<a.+?rel="next"' |
84458766 | 603 | _TITLE = None |
55a10eab | 604 | _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"' |
2929b3e7 | 605 | _TESTS = [{ |
3946864c | 606 | 'url': 'https://vimeo.com/channels/tributes', |
2929b3e7 | 607 | 'info_dict': { |
a3fa5da4 | 608 | 'id': 'tributes', |
2929b3e7 PH |
609 | 'title': 'Vimeo Tributes', |
610 | }, | |
611 | 'playlist_mincount': 25, | |
612 | }] | |
caeefc29 | 613 | |
5cc14c2f JMF |
614 | def _page_url(self, base_url, pagenum): |
615 | return '%s/videos/page:%d/' % (base_url, pagenum) | |
616 | ||
fb30ec22 | 617 | def _extract_list_title(self, webpage): |
84458766 | 618 | return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title') |
fb30ec22 | 619 | |
bf8f082a PH |
620 | def _login_list_password(self, page_url, list_id, webpage): |
621 | login_form = self._search_regex( | |
622 | r'(?s)<form[^>]+?id="pw_form"(.*?)</form>', | |
623 | webpage, 'login form', default=None) | |
624 | if not login_form: | |
625 | return webpage | |
626 | ||
d800609c | 627 | password = self._downloader.params.get('videopassword') |
bf8f082a PH |
628 | if password is None: |
629 | raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True) | |
f8da79f8 | 630 | fields = self._hidden_inputs(login_form) |
7c845629 | 631 | token, vuid = self._extract_xsrft_and_vuid(webpage) |
bf8f082a PH |
632 | fields['token'] = token |
633 | fields['password'] = password | |
15707c7e | 634 | post = urlencode_postdata(fields) |
bf8f082a PH |
635 | password_path = self._search_regex( |
636 | r'action="([^"]+)"', login_form, 'password URL') | |
637 | password_url = compat_urlparse.urljoin(page_url, password_path) | |
67dda517 | 638 | password_request = sanitized_Request(password_url, post) |
bf8f082a | 639 | password_request.add_header('Content-type', 'application/x-www-form-urlencoded') |
9eab37dc S |
640 | self._set_vimeo_cookie('vuid', vuid) |
641 | self._set_vimeo_cookie('xsrft', token) | |
bf8f082a PH |
642 | |
643 | return self._download_webpage( | |
644 | password_request, list_id, | |
645 | 'Verifying the password', 'Wrong password') | |
646 | ||
2c94198e | 647 | def _title_and_entries(self, list_id, base_url): |
caeefc29 | 648 | for pagenum in itertools.count(1): |
bf8f082a | 649 | page_url = self._page_url(base_url, pagenum) |
55a10eab | 650 | webpage = self._download_webpage( |
bf8f082a | 651 | page_url, list_id, |
9148eb00 | 652 | 'Downloading page %s' % pagenum) |
bf8f082a PH |
653 | |
654 | if pagenum == 1: | |
655 | webpage = self._login_list_password(page_url, list_id, webpage) | |
2c94198e S |
656 | yield self._extract_list_title(webpage) |
657 | ||
c8e3e097 S |
658 | # Try extracting href first since not all videos are available via |
659 | # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729) | |
660 | clips = re.findall( | |
661 | r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)', webpage) | |
662 | if clips: | |
663 | for video_id, video_url in clips: | |
664 | yield self.url_result( | |
665 | compat_urlparse.urljoin(base_url, video_url), | |
666 | VimeoIE.ie_key(), video_id=video_id) | |
667 | # More relaxed fallback | |
668 | else: | |
669 | for video_id in re.findall(r'id=["\']clip_(\d+)', webpage): | |
670 | yield self.url_result( | |
671 | 'https://vimeo.com/%s' % video_id, | |
672 | VimeoIE.ie_key(), video_id=video_id) | |
bf8f082a | 673 | |
caeefc29 JMF |
674 | if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None: |
675 | break | |
676 | ||
2c94198e S |
677 | def _extract_videos(self, list_id, base_url): |
678 | title_and_entries = self._title_and_entries(list_id, base_url) | |
679 | list_title = next(title_and_entries) | |
680 | return self.playlist_result(title_and_entries, list_id, list_title) | |
55a10eab JMF |
681 | |
682 | def _real_extract(self, url): | |
683 | mobj = re.match(self._VALID_URL, url) | |
4f3e9430 | 684 | channel_id = mobj.group('id') |
3946864c | 685 | return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id) |
55a10eab JMF |
686 | |
687 | ||
688 | class VimeoUserIE(VimeoChannelIE): | |
9148eb00 | 689 | IE_NAME = 'vimeo:user' |
b29440ae | 690 | _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)' |
55a10eab | 691 | _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>' |
2929b3e7 | 692 | _TESTS = [{ |
3946864c | 693 | 'url': 'https://vimeo.com/nkistudio/videos', |
2929b3e7 PH |
694 | 'info_dict': { |
695 | 'title': 'Nki', | |
a3fa5da4 | 696 | 'id': 'nkistudio', |
2929b3e7 PH |
697 | }, |
698 | 'playlist_mincount': 66, | |
699 | }] | |
55a10eab JMF |
700 | |
701 | def _real_extract(self, url): | |
702 | mobj = re.match(self._VALID_URL, url) | |
703 | name = mobj.group('name') | |
3946864c | 704 | return self._extract_videos(name, 'https://vimeo.com/%s' % name) |
5cc14c2f JMF |
705 | |
706 | ||
707 | class VimeoAlbumIE(VimeoChannelIE): | |
9148eb00 | 708 | IE_NAME = 'vimeo:album' |
b5eab86c | 709 | _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)(?:$|[?#]|/(?!video))' |
5cc14c2f | 710 | _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>' |
2929b3e7 | 711 | _TESTS = [{ |
d1508cd6 | 712 | 'url': 'https://vimeo.com/album/2632481', |
2929b3e7 | 713 | 'info_dict': { |
a3fa5da4 | 714 | 'id': '2632481', |
2929b3e7 PH |
715 | 'title': 'Staff Favorites: November 2013', |
716 | }, | |
717 | 'playlist_mincount': 13, | |
bf8f082a PH |
718 | }, { |
719 | 'note': 'Password-protected album', | |
720 | 'url': 'https://vimeo.com/album/3253534', | |
721 | 'info_dict': { | |
722 | 'title': 'test', | |
723 | 'id': '3253534', | |
724 | }, | |
725 | 'playlist_count': 1, | |
726 | 'params': { | |
727 | 'videopassword': 'youtube-dl', | |
728 | } | |
b5eab86c S |
729 | }, { |
730 | 'url': 'https://vimeo.com/album/2632481/sort:plays/format:thumbnail', | |
731 | 'only_matching': True, | |
2929b3e7 | 732 | }] |
5cc14c2f JMF |
733 | |
734 | def _page_url(self, base_url, pagenum): | |
735 | return '%s/page:%d/' % (base_url, pagenum) | |
736 | ||
737 | def _real_extract(self, url): | |
bf8f082a | 738 | album_id = self._match_id(url) |
d1508cd6 | 739 | return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id) |
fb30ec22 JMF |
740 | |
741 | ||
742 | class VimeoGroupsIE(VimeoAlbumIE): | |
9148eb00 | 743 | IE_NAME = 'vimeo:group' |
fdb20a27 | 744 | _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)' |
2929b3e7 | 745 | _TESTS = [{ |
3946864c | 746 | 'url': 'https://vimeo.com/groups/rolexawards', |
2929b3e7 | 747 | 'info_dict': { |
a3fa5da4 | 748 | 'id': 'rolexawards', |
2929b3e7 PH |
749 | 'title': 'Rolex Awards for Enterprise', |
750 | }, | |
751 | 'playlist_mincount': 73, | |
752 | }] | |
fb30ec22 JMF |
753 | |
754 | def _extract_list_title(self, webpage): | |
755 | return self._og_search_title(webpage) | |
756 | ||
757 | def _real_extract(self, url): | |
758 | mobj = re.match(self._VALID_URL, url) | |
759 | name = mobj.group('name') | |
3946864c | 760 | return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name) |
fcea44c6 PH |
761 | |
762 | ||
531a7496 | 763 | class VimeoReviewIE(VimeoBaseInfoExtractor): |
9148eb00 PH |
764 | IE_NAME = 'vimeo:review' |
765 | IE_DESC = 'Review pages on vimeo' | |
3946864c | 766 | _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)' |
d36d3f42 | 767 | _TESTS = [{ |
fcea44c6 | 768 | 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d', |
fcea44c6 PH |
769 | 'md5': 'c507a72f780cacc12b2248bb4006d253', |
770 | 'info_dict': { | |
fc09240e PH |
771 | 'id': '75524534', |
772 | 'ext': 'mp4', | |
fcea44c6 PH |
773 | 'title': "DICK HARDWICK 'Comedian'", |
774 | 'uploader': 'Richard Hardwick', | |
531a7496 | 775 | 'uploader_id': 'user21297594', |
fcea44c6 | 776 | } |
d36d3f42 PH |
777 | }, { |
778 | 'note': 'video player needs Referer', | |
3946864c | 779 | 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053', |
d36d3f42 PH |
780 | 'md5': '6295fdab8f4bf6a002d058b2c6dce276', |
781 | 'info_dict': { | |
782 | 'id': '91613211', | |
783 | 'ext': 'mp4', | |
9dec9930 | 784 | 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn', |
d36d3f42 PH |
785 | 'uploader': 'DevWeek Events', |
786 | 'duration': 2773, | |
787 | 'thumbnail': 're:^https?://.*\.jpg$', | |
531a7496 | 788 | 'uploader_id': 'user22258446', |
d36d3f42 PH |
789 | } |
790 | }] | |
fcea44c6 PH |
791 | |
792 | def _real_extract(self, url): | |
531a7496 YCH |
793 | video_id = self._match_id(url) |
794 | config = self._download_json( | |
795 | 'https://player.vimeo.com/video/%s/config' % video_id, video_id) | |
796 | info_dict = self._parse_config(config, video_id) | |
797 | self._vimeo_sort_formats(info_dict['formats']) | |
798 | info_dict['id'] = video_id | |
799 | return info_dict | |
efb7e119 JMF |
800 | |
801 | ||
f6c3664d | 802 | class VimeoWatchLaterIE(VimeoChannelIE): |
efb7e119 JMF |
803 | IE_NAME = 'vimeo:watchlater' |
804 | IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)' | |
84458766 S |
805 | _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater' |
806 | _TITLE = 'Watch Later' | |
efb7e119 | 807 | _LOGIN_REQUIRED = True |
2929b3e7 | 808 | _TESTS = [{ |
84458766 | 809 | 'url': 'https://vimeo.com/watchlater', |
2929b3e7 PH |
810 | 'only_matching': True, |
811 | }] | |
efb7e119 JMF |
812 | |
813 | def _real_initialize(self): | |
814 | self._login() | |
815 | ||
816 | def _page_url(self, base_url, pagenum): | |
817 | url = '%s/page:%d/' % (base_url, pagenum) | |
67dda517 | 818 | request = sanitized_Request(url) |
efb7e119 JMF |
819 | # Set the header to get a partial html page with the ids, |
820 | # the normal page doesn't contain them. | |
821 | request.add_header('X-Requested-With', 'XMLHttpRequest') | |
822 | return request | |
823 | ||
824 | def _real_extract(self, url): | |
84458766 | 825 | return self._extract_videos('watchlater', 'https://vimeo.com/watchlater') |
d6e6a422 PH |
826 | |
827 | ||
828 | class VimeoLikesIE(InfoExtractor): | |
3946864c | 829 | _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)' |
d6e6a422 PH |
830 | IE_NAME = 'vimeo:likes' |
831 | IE_DESC = 'Vimeo user likes' | |
832 | _TEST = { | |
9c44d242 PH |
833 | 'url': 'https://vimeo.com/user755559/likes/', |
834 | 'playlist_mincount': 293, | |
611c1dd9 | 835 | 'info_dict': { |
a3fa5da4 | 836 | 'id': 'user755559_likes', |
611c1dd9 S |
837 | 'description': 'See all the videos urza likes', |
838 | 'title': 'Videos urza likes', | |
d6e6a422 PH |
839 | }, |
840 | } | |
841 | ||
842 | def _real_extract(self, url): | |
843 | user_id = self._match_id(url) | |
9c44d242 PH |
844 | webpage = self._download_webpage(url, user_id) |
845 | page_count = self._int( | |
846 | self._search_regex( | |
847 | r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)"> | |
848 | .*?</a></li>\s*<li\s+class="pagination_next"> | |
849 | ''', webpage, 'page count'), | |
850 | 'page count', fatal=True) | |
851 | PAGE_SIZE = 12 | |
852 | title = self._html_search_regex( | |
853 | r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False) | |
854 | description = self._html_search_meta('description', webpage) | |
855 | ||
856 | def _get_page(idx): | |
3946864c JMF |
857 | page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % ( |
858 | user_id, idx + 1) | |
9c44d242 PH |
859 | webpage = self._download_webpage( |
860 | page_url, user_id, | |
861 | note='Downloading page %d/%d' % (idx + 1, page_count)) | |
862 | video_list = self._search_regex( | |
863 | r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>', | |
864 | webpage, 'video content') | |
865 | paths = re.findall( | |
866 | r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list) | |
867 | for path in paths: | |
868 | yield { | |
869 | '_type': 'url', | |
870 | 'url': compat_urlparse.urljoin(page_url, path), | |
871 | } | |
872 | ||
873 | pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE) | |
d6e6a422 PH |
874 | |
875 | return { | |
9c44d242 PH |
876 | '_type': 'playlist', |
877 | 'id': 'user%s_likes' % user_id, | |
878 | 'title': title, | |
879 | 'description': description, | |
880 | 'entries': pl, | |
d6e6a422 | 881 | } |