]>
Commit | Line | Data |
---|---|---|
dcdb292f | 1 | # coding: utf-8 |
9148eb00 PH |
2 | from __future__ import unicode_literals |
3 | ||
79fec976 | 4 | import base64 |
b3d14cbf PH |
5 | import json |
6 | import re | |
caeefc29 | 7 | import itertools |
b3d14cbf PH |
8 | |
9 | from .common import InfoExtractor | |
8c25f81b | 10 | from ..compat import ( |
1060425c | 11 | compat_HTTPError, |
6a55bb66 | 12 | compat_str, |
9c44d242 | 13 | compat_urlparse, |
8c25f81b PH |
14 | ) |
15 | from ..utils import ( | |
d5f071af | 16 | determine_ext, |
b3d14cbf | 17 | ExtractorError, |
ca01d178 | 18 | js_to_json, |
9c44d242 PH |
19 | InAdvancePagedList, |
20 | int_or_none, | |
ae1c585c | 21 | merge_dicts, |
c1ff6e1a | 22 | NO_DEFAULT, |
ca01d178 RA |
23 | parse_filesize, |
24 | qualities, | |
55b3e45b | 25 | RegexNotFoundError, |
67dda517 | 26 | sanitized_Request, |
30965ac6 | 27 | smuggle_url, |
b3d14cbf | 28 | std_headers, |
c15cd296 | 29 | try_get, |
c15cd296 | 30 | unified_timestamp, |
9d4660ca | 31 | unsmuggle_url, |
a980bc43 | 32 | urlencode_postdata, |
b407e173 | 33 | unescapeHTML, |
b3d14cbf PH |
34 | ) |
35 | ||
bbafbe20 | 36 | |
efb7e119 JMF |
37 | class VimeoBaseInfoExtractor(InfoExtractor): |
38 | _NETRC_MACHINE = 'vimeo' | |
39 | _LOGIN_REQUIRED = False | |
f6c3664d | 40 | _LOGIN_URL = 'https://vimeo.com/log_in' |
efb7e119 JMF |
41 | |
42 | def _login(self): | |
68217024 | 43 | username, password = self._get_login_info() |
efb7e119 JMF |
44 | if username is None: |
45 | if self._LOGIN_REQUIRED: | |
4f3e9430 | 46 | raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) |
efb7e119 | 47 | return |
26ad6bcd S |
48 | webpage = self._download_webpage( |
49 | self._LOGIN_URL, None, 'Downloading login page') | |
7c845629 | 50 | token, vuid = self._extract_xsrft_and_vuid(webpage) |
26ad6bcd | 51 | data = { |
f6c3664d | 52 | 'action': 'login', |
efb7e119 JMF |
53 | 'email': username, |
54 | 'password': password, | |
efb7e119 JMF |
55 | 'service': 'vimeo', |
56 | 'token': token, | |
26ad6bcd | 57 | } |
9eab37dc | 58 | self._set_vimeo_cookie('vuid', vuid) |
26ad6bcd S |
59 | try: |
60 | self._download_webpage( | |
61 | self._LOGIN_URL, None, 'Logging in', | |
62 | data=urlencode_postdata(data), headers={ | |
63 | 'Content-Type': 'application/x-www-form-urlencoded', | |
64 | 'Referer': self._LOGIN_URL, | |
65 | }) | |
66 | except ExtractorError as e: | |
67 | if isinstance(e.cause, compat_HTTPError) and e.cause.code == 418: | |
68 | raise ExtractorError( | |
69 | 'Unable to log in: bad username or password', | |
70 | expected=True) | |
71 | raise ExtractorError('Unable to log in') | |
efb7e119 | 72 | |
c1ff6e1a YCH |
73 | def _verify_video_password(self, url, video_id, webpage): |
74 | password = self._downloader.params.get('videopassword') | |
75 | if password is None: | |
76 | raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True) | |
77 | token, vuid = self._extract_xsrft_and_vuid(webpage) | |
78 | data = urlencode_postdata({ | |
79 | 'password': password, | |
80 | 'token': token, | |
81 | }) | |
82 | if url.startswith('http://'): | |
83 | # vimeo only supports https now, but the user can give an http url | |
84 | url = url.replace('http://', 'https://') | |
85 | password_request = sanitized_Request(url + '/password', data) | |
86 | password_request.add_header('Content-Type', 'application/x-www-form-urlencoded') | |
87 | password_request.add_header('Referer', url) | |
88 | self._set_vimeo_cookie('vuid', vuid) | |
89 | return self._download_webpage( | |
90 | password_request, video_id, | |
91 | 'Verifying the password', 'Wrong password') | |
92 | ||
7c845629 S |
93 | def _extract_xsrft_and_vuid(self, webpage): |
94 | xsrft = self._search_regex( | |
b826035d | 95 | r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)', |
f6c3664d | 96 | webpage, 'login token', group='xsrft') |
7c845629 S |
97 | vuid = self._search_regex( |
98 | r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1', | |
99 | webpage, 'vuid', group='vuid') | |
100 | return xsrft, vuid | |
f6c3664d | 101 | |
9eab37dc S |
102 | def _set_vimeo_cookie(self, name, value): |
103 | self._set_cookie('vimeo.com', name, value) | |
104 | ||
531a7496 YCH |
105 | def _vimeo_sort_formats(self, formats): |
106 | # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps | |
107 | # at the same time without actual units specified. This lead to wrong sorting. | |
d8c507c9 | 108 | self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'tbr', 'format_id')) |
531a7496 YCH |
109 | |
110 | def _parse_config(self, config, video_id): | |
d8c507c9 | 111 | video_data = config['video'] |
531a7496 | 112 | # Extract title |
d8c507c9 | 113 | video_title = video_data['title'] |
531a7496 YCH |
114 | |
115 | # Extract uploader, uploader_url and uploader_id | |
d8c507c9 RA |
116 | video_uploader = video_data.get('owner', {}).get('name') |
117 | video_uploader_url = video_data.get('owner', {}).get('url') | |
531a7496 YCH |
118 | video_uploader_id = video_uploader_url.split('/')[-1] if video_uploader_url else None |
119 | ||
120 | # Extract video thumbnail | |
d8c507c9 | 121 | video_thumbnail = video_data.get('thumbnail') |
531a7496 | 122 | if video_thumbnail is None: |
d8c507c9 | 123 | video_thumbs = video_data.get('thumbs') |
531a7496 YCH |
124 | if video_thumbs and isinstance(video_thumbs, dict): |
125 | _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1] | |
126 | ||
127 | # Extract video duration | |
d8c507c9 | 128 | video_duration = int_or_none(video_data.get('duration')) |
531a7496 YCH |
129 | |
130 | formats = [] | |
d8c507c9 | 131 | config_files = video_data.get('files') or config['request'].get('files', {}) |
531a7496 YCH |
132 | for f in config_files.get('progressive', []): |
133 | video_url = f.get('url') | |
134 | if not video_url: | |
135 | continue | |
136 | formats.append({ | |
137 | 'url': video_url, | |
138 | 'format_id': 'http-%s' % f.get('quality'), | |
139 | 'width': int_or_none(f.get('width')), | |
140 | 'height': int_or_none(f.get('height')), | |
141 | 'fps': int_or_none(f.get('fps')), | |
142 | 'tbr': int_or_none(f.get('bitrate')), | |
143 | }) | |
d8c507c9 RA |
144 | |
145 | for files_type in ('hls', 'dash'): | |
146 | for cdn_name, cdn_data in config_files.get(files_type, {}).get('cdns', {}).items(): | |
147 | manifest_url = cdn_data.get('url') | |
148 | if not manifest_url: | |
149 | continue | |
150 | format_id = '%s-%s' % (files_type, cdn_name) | |
151 | if files_type == 'hls': | |
152 | formats.extend(self._extract_m3u8_formats( | |
153 | manifest_url, video_id, 'mp4', | |
154 | 'm3u8_native', m3u8_id=format_id, | |
155 | note='Downloading %s m3u8 information' % cdn_name, | |
156 | fatal=False)) | |
157 | elif files_type == 'dash': | |
ae9a173b RA |
158 | mpd_pattern = r'/%s/(?:sep/)?video/' % video_id |
159 | mpd_manifest_urls = [] | |
160 | if re.search(mpd_pattern, manifest_url): | |
161 | for suffix, repl in (('', 'video'), ('_sep', 'sep/video')): | |
162 | mpd_manifest_urls.append((format_id + suffix, re.sub( | |
163 | mpd_pattern, '/%s/%s/' % (video_id, repl), manifest_url))) | |
164 | else: | |
165 | mpd_manifest_urls = [(format_id, manifest_url)] | |
166 | for f_id, m_url in mpd_manifest_urls: | |
e834f044 | 167 | mpd_formats = self._extract_mpd_formats( |
ae9a173b RA |
168 | m_url.replace('/master.json', '/master.mpd'), video_id, f_id, |
169 | 'Downloading %s MPD information' % cdn_name, | |
e834f044 S |
170 | fatal=False) |
171 | for f in mpd_formats: | |
172 | if f.get('vcodec') == 'none': | |
173 | f['preference'] = -50 | |
174 | elif f.get('acodec') == 'none': | |
175 | f['preference'] = -40 | |
176 | formats.extend(mpd_formats) | |
531a7496 YCH |
177 | |
178 | subtitles = {} | |
179 | text_tracks = config['request'].get('text_tracks') | |
180 | if text_tracks: | |
181 | for tt in text_tracks: | |
182 | subtitles[tt['lang']] = [{ | |
183 | 'ext': 'vtt', | |
184 | 'url': 'https://vimeo.com' + tt['url'], | |
185 | }] | |
186 | ||
187 | return { | |
188 | 'title': video_title, | |
189 | 'uploader': video_uploader, | |
190 | 'uploader_id': video_uploader_id, | |
191 | 'uploader_url': video_uploader_url, | |
192 | 'thumbnail': video_thumbnail, | |
193 | 'duration': video_duration, | |
194 | 'formats': formats, | |
195 | 'subtitles': subtitles, | |
196 | } | |
197 | ||
27655037 RA |
198 | def _extract_original_format(self, url, video_id): |
199 | download_data = self._download_json( | |
200 | url, video_id, fatal=False, | |
201 | query={'action': 'load_download_config'}, | |
202 | headers={'X-Requested-With': 'XMLHttpRequest'}) | |
203 | if download_data: | |
204 | source_file = download_data.get('source_file') | |
205 | if isinstance(source_file, dict): | |
206 | download_url = source_file.get('download_url') | |
207 | if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'): | |
208 | source_name = source_file.get('public_name', 'Original') | |
209 | if self._is_valid_url(download_url, video_id, '%s video' % source_name): | |
210 | ext = (try_get( | |
211 | source_file, lambda x: x['extension'], | |
212 | compat_str) or determine_ext( | |
213 | download_url, None) or 'mp4').lower() | |
214 | return { | |
215 | 'url': download_url, | |
216 | 'ext': ext, | |
217 | 'width': int_or_none(source_file.get('width')), | |
218 | 'height': int_or_none(source_file.get('height')), | |
219 | 'filesize': parse_filesize(source_file.get('size')), | |
220 | 'format_id': source_name, | |
221 | 'preference': 1, | |
222 | } | |
223 | ||
efb7e119 | 224 | |
65469a7f | 225 | class VimeoIE(VimeoBaseInfoExtractor): |
b3d14cbf PH |
226 | """Information extractor for vimeo.com.""" |
227 | ||
228 | # _VALID_URL matches Vimeo URLs | |
bbafbe20 | 229 | _VALID_URL = r'''(?x) |
74278def S |
230 | https?:// |
231 | (?: | |
232 | (?: | |
233 | www| | |
234 | (?P<player>player) | |
235 | ) | |
236 | \. | |
237 | )? | |
238 | vimeo(?P<pro>pro)?\.com/ | |
c8e3e097 | 239 | (?!(?:channels|album)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/) |
74278def S |
240 | (?:.*?/)? |
241 | (?: | |
242 | (?: | |
243 | play_redirect_hls| | |
244 | moogaloop\.swf)\?clip_id= | |
245 | )? | |
246 | (?:videos?/)? | |
247 | (?P<id>[0-9]+) | |
241a318f | 248 | (?:/[\da-f]+)? |
74278def S |
249 | /?(?:[?&].*)?(?:[#].*)?$ |
250 | ''' | |
9148eb00 | 251 | IE_NAME = 'vimeo' |
a91b954b JMF |
252 | _TESTS = [ |
253 | { | |
9148eb00 | 254 | 'url': 'http://vimeo.com/56015672#at=0', |
9148eb00 PH |
255 | 'md5': '8879b6cc097e987f02484baf890129e5', |
256 | 'info_dict': { | |
ad5976b4 PH |
257 | 'id': '56015672', |
258 | 'ext': 'mp4', | |
68f3b61f | 259 | 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", |
73af6e22 | 260 | 'description': 'md5:509a9ad5c9bf97c60faee9203aca4479', |
c15cd296 | 261 | 'timestamp': 1355990239, |
68f3b61f | 262 | 'upload_date': '20121220', |
ec85ded8 | 263 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434', |
68f3b61f S |
264 | 'uploader_id': 'user7108434', |
265 | 'uploader': 'Filippo Valsorda', | |
266 | 'duration': 10, | |
c38a67bc | 267 | 'license': 'by-sa', |
a91b954b JMF |
268 | }, |
269 | }, | |
270 | { | |
9148eb00 | 271 | 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876', |
9148eb00 PH |
272 | 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82', |
273 | 'note': 'Vimeo Pro video (#1197)', | |
274 | 'info_dict': { | |
4f3e9430 JMF |
275 | 'id': '68093876', |
276 | 'ext': 'mp4', | |
ec85ded8 | 277 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus', |
9148eb00 PH |
278 | 'uploader_id': 'openstreetmapus', |
279 | 'uploader': 'OpenStreetMap US', | |
280 | 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography', | |
68f3b61f | 281 | 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30', |
69c8fb9e | 282 | 'duration': 1595, |
a91b954b JMF |
283 | }, |
284 | }, | |
aa32314d | 285 | { |
9148eb00 | 286 | 'url': 'http://player.vimeo.com/video/54469442', |
9148eb00 PH |
287 | 'md5': '619b811a4417aa4abe78dc653becf511', |
288 | 'note': 'Videos that embed the url in the player page', | |
289 | 'info_dict': { | |
4f3e9430 JMF |
290 | 'id': '54469442', |
291 | 'ext': 'mp4', | |
0e6ebc13 | 292 | 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012', |
9148eb00 | 293 | 'uploader': 'The BLN & Business of Software', |
ec85ded8 | 294 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware', |
9148eb00 | 295 | 'uploader_id': 'theblnbusinessofsoftware', |
69c8fb9e | 296 | 'duration': 3610, |
58ea7ec8 | 297 | 'description': None, |
aa32314d | 298 | }, |
93b22c78 JMF |
299 | }, |
300 | { | |
9148eb00 | 301 | 'url': 'http://vimeo.com/68375962', |
9148eb00 PH |
302 | 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7', |
303 | 'note': 'Video protected with password', | |
304 | 'info_dict': { | |
4f3e9430 JMF |
305 | 'id': '68375962', |
306 | 'ext': 'mp4', | |
9148eb00 | 307 | 'title': 'youtube-dl password protected test video', |
c15cd296 | 308 | 'timestamp': 1371200155, |
9148eb00 | 309 | 'upload_date': '20130614', |
ec85ded8 | 310 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128', |
9148eb00 PH |
311 | 'uploader_id': 'user18948128', |
312 | 'uploader': 'Jaime Marquínez Ferrándiz', | |
69c8fb9e | 313 | 'duration': 10, |
365d136b | 314 | 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f', |
93b22c78 | 315 | }, |
9148eb00 PH |
316 | 'params': { |
317 | 'videopassword': 'youtube-dl', | |
93b22c78 JMF |
318 | }, |
319 | }, | |
548f31d9 S |
320 | { |
321 | 'url': 'http://vimeo.com/channels/keypeele/75629013', | |
322 | 'md5': '2f86a05afe9d7abc0b9126d229bbe15d', | |
548f31d9 S |
323 | 'info_dict': { |
324 | 'id': '75629013', | |
325 | 'ext': 'mp4', | |
326 | 'title': 'Key & Peele: Terrorist Interrogation', | |
327 | 'description': 'md5:8678b246399b070816b12313e8b4eb5c', | |
ec85ded8 | 328 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio', |
548f31d9 S |
329 | 'uploader_id': 'atencio', |
330 | 'uploader': 'Peter Atencio', | |
d03beddf S |
331 | 'channel_id': 'keypeele', |
332 | 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele', | |
c15cd296 S |
333 | 'timestamp': 1380339469, |
334 | 'upload_date': '20130928', | |
548f31d9 S |
335 | 'duration': 187, |
336 | }, | |
d03beddf | 337 | 'expected_warnings': ['Unable to download JSON metadata'], |
548f31d9 | 338 | }, |
1eac553e S |
339 | { |
340 | 'url': 'http://vimeo.com/76979871', | |
1eac553e S |
341 | 'note': 'Video with subtitles', |
342 | 'info_dict': { | |
343 | 'id': '76979871', | |
344 | 'ext': 'mp4', | |
345 | 'title': 'The New Vimeo Player (You Know, For Videos)', | |
346 | 'description': 'md5:2ec900bf97c3f389378a96aee11260ea', | |
c15cd296 | 347 | 'timestamp': 1381846109, |
1eac553e | 348 | 'upload_date': '20131015', |
ec85ded8 | 349 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff', |
1eac553e S |
350 | 'uploader_id': 'staff', |
351 | 'uploader': 'Vimeo Staff', | |
69c8fb9e | 352 | 'duration': 62, |
1eac553e S |
353 | } |
354 | }, | |
4698f0d8 JMF |
355 | { |
356 | # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/ | |
357 | 'url': 'https://player.vimeo.com/video/98044508', | |
358 | 'note': 'The js code contains assignments to the same variable as the config', | |
359 | 'info_dict': { | |
360 | 'id': '98044508', | |
361 | 'ext': 'mp4', | |
362 | 'title': 'Pier Solar OUYA Official Trailer', | |
363 | 'uploader': 'Tulio Gonçalves', | |
ec85ded8 | 364 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593', |
4698f0d8 JMF |
365 | 'uploader_id': 'user28849593', |
366 | }, | |
367 | }, | |
323f82a7 | 368 | { |
369 | # contains original format | |
370 | 'url': 'https://vimeo.com/33951933', | |
365d136b | 371 | 'md5': '53c688fa95a55bf4b7293d37a89c5c53', |
323f82a7 | 372 | 'info_dict': { |
373 | 'id': '33951933', | |
374 | 'ext': 'mp4', | |
375 | 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute', | |
376 | 'uploader': 'The DMCI', | |
ec85ded8 | 377 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci', |
323f82a7 | 378 | 'uploader_id': 'dmci', |
c15cd296 | 379 | 'timestamp': 1324343742, |
323f82a7 | 380 | 'upload_date': '20111220', |
381 | 'description': 'md5:ae23671e82d05415868f7ad1aec21147', | |
382 | }, | |
383 | }, | |
c143ddce S |
384 | { |
385 | # only available via https://vimeo.com/channels/tributes/6213729 and | |
386 | # not via https://vimeo.com/6213729 | |
387 | 'url': 'https://vimeo.com/channels/tributes/6213729', | |
388 | 'info_dict': { | |
389 | 'id': '6213729', | |
d03beddf | 390 | 'ext': 'mp4', |
c143ddce S |
391 | 'title': 'Vimeo Tribute: The Shining', |
392 | 'uploader': 'Casey Donahue', | |
ec85ded8 | 393 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue', |
c143ddce | 394 | 'uploader_id': 'caseydonahue', |
d03beddf S |
395 | 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes', |
396 | 'channel_id': 'tributes', | |
c15cd296 | 397 | 'timestamp': 1250886430, |
c143ddce S |
398 | 'upload_date': '20090821', |
399 | 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6', | |
400 | }, | |
401 | 'params': { | |
402 | 'skip_download': True, | |
403 | }, | |
404 | 'expected_warnings': ['Unable to download JSON metadata'], | |
405 | }, | |
f16f8505 | 406 | { |
cccd70a2 | 407 | # redirects to ondemand extractor and should be passed through it |
f16f8505 S |
408 | # for successful extraction |
409 | 'url': 'https://vimeo.com/73445910', | |
410 | 'info_dict': { | |
411 | 'id': '73445910', | |
412 | 'ext': 'mp4', | |
413 | 'title': 'The Reluctant Revolutionary', | |
414 | 'uploader': '10Ft Films', | |
ec85ded8 | 415 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms', |
f16f8505 S |
416 | 'uploader_id': 'tenfootfilms', |
417 | }, | |
418 | 'params': { | |
419 | 'skip_download': True, | |
420 | }, | |
421 | }, | |
79fec976 RA |
422 | { |
423 | 'url': 'http://player.vimeo.com/video/68375962', | |
424 | 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7', | |
425 | 'info_dict': { | |
426 | 'id': '68375962', | |
427 | 'ext': 'mp4', | |
428 | 'title': 'youtube-dl password protected test video', | |
429 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128', | |
430 | 'uploader_id': 'user18948128', | |
431 | 'uploader': 'Jaime Marquínez Ferrándiz', | |
432 | 'duration': 10, | |
433 | }, | |
434 | 'params': { | |
435 | 'videopassword': 'youtube-dl', | |
436 | }, | |
437 | }, | |
c143ddce S |
438 | { |
439 | 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741', | |
440 | 'only_matching': True, | |
441 | }, | |
8bea039b LL |
442 | { |
443 | 'url': 'https://vimeo.com/109815029', | |
444 | 'note': 'Video not completely processed, "failed" seed status', | |
445 | 'only_matching': True, | |
446 | }, | |
6b7ceee1 S |
447 | { |
448 | 'url': 'https://vimeo.com/groups/travelhd/videos/22439234', | |
449 | 'only_matching': True, | |
450 | }, | |
c8e3e097 S |
451 | { |
452 | 'url': 'https://vimeo.com/album/2632481/video/79010983', | |
453 | 'only_matching': True, | |
454 | }, | |
16f1131a S |
455 | { |
456 | # source file returns 403: Forbidden | |
457 | 'url': 'https://vimeo.com/7809605', | |
458 | 'only_matching': True, | |
459 | }, | |
241a318f S |
460 | { |
461 | 'url': 'https://vimeo.com/160743502/abd0e13fb4', | |
462 | 'only_matching': True, | |
463 | } | |
a1a46075 S |
464 | # https://gettingthingsdone.com/workflowmap/ |
465 | # vimeo embed with check-password page protected by Referer header | |
a91b954b | 466 | ] |
b3d14cbf | 467 | |
d002e919 S |
468 | @staticmethod |
469 | def _smuggle_referrer(url, referrer_url): | |
470 | return smuggle_url(url, {'http_headers': {'Referer': referrer_url}}) | |
471 | ||
b407e173 | 472 | @staticmethod |
09b9c45e S |
473 | def _extract_urls(url, webpage): |
474 | urls = [] | |
b407e173 | 475 | # Look for embedded (iframe) Vimeo player |
09b9c45e | 476 | for mobj in re.finditer( |
7c1f4193 | 477 | r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1', |
f475e881 | 478 | webpage): |
09b9c45e S |
479 | urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url')), url)) |
480 | PLAIN_EMBED_RE = ( | |
481 | # Look for embedded (swf embed) Vimeo player | |
482 | r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1', | |
483 | # Look more for non-standard embedded Vimeo player | |
484 | r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1', | |
485 | ) | |
486 | for embed_re in PLAIN_EMBED_RE: | |
487 | for mobj in re.finditer(embed_re, webpage): | |
488 | urls.append(mobj.group('url')) | |
489 | return urls | |
490 | ||
491 | @staticmethod | |
492 | def _extract_url(url, webpage): | |
493 | urls = VimeoIE._extract_urls(url, webpage) | |
494 | return urls[0] if urls else None | |
b407e173 | 495 | |
a1a46075 | 496 | def _verify_player_video_password(self, url, video_id, headers): |
d800609c | 497 | password = self._downloader.params.get('videopassword') |
0eecc6a4 PH |
498 | if password is None: |
499 | raise ExtractorError('This video is protected by a password, use the --video-password option') | |
79fec976 RA |
500 | data = urlencode_postdata({ |
501 | 'password': base64.b64encode(password.encode()), | |
502 | }) | |
a1a46075 S |
503 | headers = merge_dicts(headers, { |
504 | 'Content-Type': 'application/x-www-form-urlencoded', | |
505 | }) | |
506 | checked = self._download_json( | |
507 | url + '/check-password', video_id, | |
508 | 'Verifying the password', data=data, headers=headers) | |
509 | if checked is False: | |
510 | raise ExtractorError('Wrong video password', expected=True) | |
511 | return checked | |
0eecc6a4 | 512 | |
fc79158d JMF |
513 | def _real_initialize(self): |
514 | self._login() | |
515 | ||
a0088bdf | 516 | def _real_extract(self, url): |
5dbe81a1 | 517 | url, data = unsmuggle_url(url, {}) |
0f56a4b4 | 518 | headers = std_headers.copy() |
5dbe81a1 | 519 | if 'http_headers' in data: |
5dbe81a1 | 520 | headers.update(data['http_headers']) |
ba5d51b3 PH |
521 | if 'Referer' not in headers: |
522 | headers['Referer'] = url | |
9d4660ca | 523 | |
d03beddf S |
524 | channel_id = self._search_regex( |
525 | r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None) | |
526 | ||
b3d14cbf PH |
527 | # Extract ID from URL |
528 | mobj = re.match(self._VALID_URL, url) | |
b3d14cbf | 529 | video_id = mobj.group('id') |
58ea7ec8 | 530 | orig_url = url |
06242d44 RA |
531 | if mobj.group('pro'): |
532 | # some videos require portfolio_id to be present in player url | |
067aa17e | 533 | # https://github.com/ytdl-org/youtube-dl/issues/20070 |
06242d44 RA |
534 | url = self._extract_url(url, self._download_webpage(url, video_id)) |
535 | elif mobj.group('player'): | |
61e00a97 | 536 | url = 'https://player.vimeo.com/video/' + video_id |
c143ddce | 537 | elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')): |
10831b5e | 538 | url = 'https://vimeo.com/' + video_id |
b3d14cbf PH |
539 | |
540 | # Retrieve video webpage to extract further information | |
0f56a4b4 | 541 | request = sanitized_Request(url, headers=headers) |
1060425c | 542 | try: |
f16f8505 | 543 | webpage, urlh = self._download_webpage_handle(request, video_id) |
580f3c79 | 544 | redirect_url = compat_str(urlh.geturl()) |
f16f8505 S |
545 | # Some URLs redirect to ondemand can't be extracted with |
546 | # this extractor right away thus should be passed through | |
547 | # ondemand extractor (e.g. https://vimeo.com/73445910) | |
580f3c79 S |
548 | if VimeoOndemandIE.suitable(redirect_url): |
549 | return self.url_result(redirect_url, VimeoOndemandIE.ie_key()) | |
1060425c PH |
550 | except ExtractorError as ee: |
551 | if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: | |
552 | errmsg = ee.cause.read() | |
553 | if b'Because of its privacy settings, this video cannot be played here' in errmsg: | |
554 | raise ExtractorError( | |
555 | 'Cannot download embed-only video without embedding ' | |
556 | 'URL. Please call youtube-dl with the URL of the page ' | |
557 | 'that embeds this video.', | |
558 | expected=True) | |
559 | raise | |
b3d14cbf PH |
560 | |
561 | # Now we begin extracting as much information as we can from what we | |
562 | # retrieved. First we extract the information common to all extractors, | |
563 | # and latter we extract those that are Vimeo specific. | |
564 | self.report_extraction(video_id) | |
565 | ||
998e6cdb | 566 | vimeo_config = self._search_regex( |
b6aa99af | 567 | r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage, |
998e6cdb S |
568 | 'vimeo config', default=None) |
569 | if vimeo_config: | |
570 | seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {}) | |
571 | if seed_status.get('state') == 'failed': | |
572 | raise ExtractorError( | |
b6aa99af | 573 | '%s said: %s' % (self.IE_NAME, seed_status['title']), |
998e6cdb S |
574 | expected=True) |
575 | ||
c38a67bc | 576 | cc_license = None |
c15cd296 | 577 | timestamp = None |
c38a67bc | 578 | |
b3d14cbf PH |
579 | # Extract the config JSON |
580 | try: | |
93b22c78 JMF |
581 | try: |
582 | config_url = self._html_search_regex( | |
41a7b00f LL |
583 | r' data-config-url="(.+?)"', webpage, |
584 | 'config URL', default=None) | |
585 | if not config_url: | |
dd841752 S |
586 | # Sometimes new react-based page is served instead of old one that require |
587 | # different config URL extraction approach (see | |
067aa17e | 588 | # https://github.com/ytdl-org/youtube-dl/pull/7209) |
41a7b00f LL |
589 | vimeo_clip_page_config = self._search_regex( |
590 | r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage, | |
591 | 'vimeo clip page config') | |
c38a67bc S |
592 | page_config = self._parse_json(vimeo_clip_page_config, video_id) |
593 | config_url = page_config['player']['config_url'] | |
594 | cc_license = page_config.get('cc_license') | |
c15cd296 S |
595 | timestamp = try_get( |
596 | page_config, lambda x: x['clip']['uploaded_on'], | |
597 | compat_str) | |
93b22c78 JMF |
598 | config_json = self._download_webpage(config_url, video_id) |
599 | config = json.loads(config_json) | |
600 | except RegexNotFoundError: | |
601 | # For pro videos or player.vimeo.com urls | |
48ad51b2 | 602 | # We try to find out to which variable is assigned the config dic |
ec85ded8 | 603 | m_variable_name = re.search(r'(\w)\.video\.id', webpage) |
48ad51b2 | 604 | if m_variable_name is not None: |
6fc09f01 | 605 | config_re = [r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))] |
48ad51b2 JMF |
606 | else: |
607 | config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});'] | |
6fc09f01 | 608 | config_re.append(r'\bvar\s+r\s*=\s*({.+?})\s*;') |
85fa80d5 | 609 | config_re.append(r'\bconfig\s*=\s*({.+?})\s*;') |
9148eb00 | 610 | config = self._search_regex(config_re, webpage, 'info section', |
9e1a5b84 | 611 | flags=re.DOTALL) |
93b22c78 | 612 | config = json.loads(config) |
71907db3 | 613 | except Exception as e: |
b3d14cbf | 614 | if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage): |
9148eb00 | 615 | raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option') |
b3d14cbf | 616 | |
bf8f082a | 617 | if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None: |
5dbe81a1 | 618 | if '_video_password_verified' in data: |
30965ac6 | 619 | raise ExtractorError('video password verification failed!') |
580f3c79 | 620 | self._verify_video_password(redirect_url, video_id, webpage) |
30965ac6 | 621 | return self._real_extract( |
580f3c79 | 622 | smuggle_url(redirect_url, {'_video_password_verified': 'verified'})) |
b3d14cbf | 623 | else: |
9148eb00 | 624 | raise ExtractorError('Unable to extract info section', |
71907db3 | 625 | cause=e) |
559e370f PH |
626 | else: |
627 | if config.get('view') == 4: | |
a1a46075 | 628 | config = self._verify_player_video_password(redirect_url, video_id, headers) |
b3d14cbf | 629 | |
8b40c927 RA |
630 | vod = config.get('video', {}).get('vod', {}) |
631 | ||
6a55bb66 S |
632 | def is_rented(): |
633 | if '>You rented this title.<' in webpage: | |
634 | return True | |
635 | if config.get('user', {}).get('purchased'): | |
636 | return True | |
8b40c927 RA |
637 | for purchase_option in vod.get('purchase_options', []): |
638 | if purchase_option.get('purchased'): | |
639 | return True | |
640 | label = purchase_option.get('label_string') | |
641 | if label and (label.startswith('You rented this') or label.endswith(' remaining')): | |
642 | return True | |
6a55bb66 S |
643 | return False |
644 | ||
8b40c927 RA |
645 | if is_rented() and vod.get('is_trailer'): |
646 | feature_id = vod.get('feature_id') | |
5dbe81a1 S |
647 | if feature_id and not data.get('force_feature_id', False): |
648 | return self.url_result(smuggle_url( | |
649 | 'https://player.vimeo.com/player/%s' % feature_id, | |
650 | {'force_feature_id': True}), 'Vimeo') | |
651 | ||
b3d14cbf | 652 | # Extract video description |
58ea7ec8 | 653 | |
25930395 | 654 | video_description = self._html_search_regex( |
58ea7ec8 PH |
655 | r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>', |
656 | webpage, 'description', default=None) | |
657 | if not video_description: | |
658 | video_description = self._html_search_meta( | |
659 | 'description', webpage, default=None) | |
660 | if not video_description and mobj.group('pro'): | |
661 | orig_webpage = self._download_webpage( | |
662 | orig_url, video_id, | |
663 | note='Downloading webpage for description', | |
664 | fatal=False) | |
665 | if orig_webpage: | |
666 | video_description = self._html_search_meta( | |
667 | 'description', orig_webpage, default=None) | |
668 | if not video_description and not mobj.group('player'): | |
669 | self._downloader.report_warning('Cannot find video description') | |
b3d14cbf PH |
670 | |
671 | # Extract upload date | |
c15cd296 S |
672 | if not timestamp: |
673 | timestamp = self._search_regex( | |
674 | r'<time[^>]+datetime="([^"]+)"', webpage, | |
675 | 'timestamp', default=None) | |
b3d14cbf | 676 | |
4e761794 | 677 | try: |
9148eb00 PH |
678 | view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count')) |
679 | like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count')) | |
680 | comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count')) | |
4e761794 JMF |
681 | except RegexNotFoundError: |
682 | # This info is only available in vimeo.com/{id} urls | |
683 | view_count = None | |
684 | like_count = None | |
685 | comment_count = None | |
686 | ||
a6387bfd | 687 | formats = [] |
27655037 RA |
688 | |
689 | source_format = self._extract_original_format( | |
690 | 'https://vimeo.com/' + video_id, video_id) | |
691 | if source_format: | |
692 | formats.append(source_format) | |
1eac553e | 693 | |
ae1c585c S |
694 | info_dict_config = self._parse_config(config, video_id) |
695 | formats.extend(info_dict_config['formats']) | |
531a7496 | 696 | self._vimeo_sort_formats(formats) |
c38a67bc | 697 | |
ae1c585c S |
698 | json_ld = self._search_json_ld(webpage, video_id, default={}) |
699 | ||
c38a67bc S |
700 | if not cc_license: |
701 | cc_license = self._search_regex( | |
702 | r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1', | |
703 | webpage, 'license', default=None, group='license') | |
704 | ||
d03beddf S |
705 | channel_url = 'https://vimeo.com/channels/%s' % channel_id if channel_id else None |
706 | ||
ae1c585c | 707 | info_dict = { |
b0268cb6 | 708 | 'id': video_id, |
531a7496 | 709 | 'formats': formats, |
c15cd296 | 710 | 'timestamp': unified_timestamp(timestamp), |
b0268cb6 | 711 | 'description': video_description, |
9103bbc5 | 712 | 'webpage_url': url, |
4e761794 JMF |
713 | 'view_count': view_count, |
714 | 'like_count': like_count, | |
715 | 'comment_count': comment_count, | |
c38a67bc | 716 | 'license': cc_license, |
d03beddf S |
717 | 'channel_id': channel_id, |
718 | 'channel_url': channel_url, | |
ae1c585c S |
719 | } |
720 | ||
721 | info_dict = merge_dicts(info_dict, info_dict_config, json_ld) | |
531a7496 YCH |
722 | |
723 | return info_dict | |
caeefc29 JMF |
724 | |
725 | ||
74278def | 726 | class VimeoOndemandIE(VimeoBaseInfoExtractor): |
1e501364 | 727 | IE_NAME = 'vimeo:ondemand' |
74278def S |
728 | _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?P<id>[^/?#&]+)' |
729 | _TESTS = [{ | |
730 | # ondemand video not available via https://vimeo.com/id | |
731 | 'url': 'https://vimeo.com/ondemand/20704', | |
732 | 'md5': 'c424deda8c7f73c1dfb3edd7630e2f35', | |
733 | 'info_dict': { | |
734 | 'id': '105442900', | |
735 | 'ext': 'mp4', | |
736 | 'title': 'המעבדה - במאי יותם פלדמן', | |
737 | 'uploader': 'גם סרטים', | |
ec85ded8 | 738 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms', |
74278def S |
739 | 'uploader_id': 'gumfilms', |
740 | }, | |
1fd0fc42 S |
741 | 'params': { |
742 | 'format': 'best[protocol=https]', | |
743 | }, | |
d002e919 S |
744 | }, { |
745 | # requires Referer to be passed along with og:video:url | |
746 | 'url': 'https://vimeo.com/ondemand/36938/126682985', | |
747 | 'info_dict': { | |
748 | 'id': '126682985', | |
749 | 'ext': 'mp4', | |
750 | 'title': 'Rävlock, rätt läte på rätt plats', | |
751 | 'uploader': 'Lindroth & Norin', | |
ec85ded8 | 752 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user14430847', |
d002e919 S |
753 | 'uploader_id': 'user14430847', |
754 | }, | |
755 | 'params': { | |
756 | 'skip_download': True, | |
757 | }, | |
74278def S |
758 | }, { |
759 | 'url': 'https://vimeo.com/ondemand/nazmaalik', | |
760 | 'only_matching': True, | |
761 | }, { | |
762 | 'url': 'https://vimeo.com/ondemand/141692381', | |
763 | 'only_matching': True, | |
764 | }, { | |
765 | 'url': 'https://vimeo.com/ondemand/thelastcolony/150274832', | |
766 | 'only_matching': True, | |
767 | }] | |
768 | ||
769 | def _real_extract(self, url): | |
770 | video_id = self._match_id(url) | |
771 | webpage = self._download_webpage(url, video_id) | |
d002e919 S |
772 | return self.url_result( |
773 | # Some videos require Referer to be passed along with og:video:url | |
774 | # similarly to generic vimeo embeds (e.g. | |
775 | # https://vimeo.com/ondemand/36938/126682985). | |
776 | VimeoIE._smuggle_referrer(self._og_search_video_url(webpage), url), | |
777 | VimeoIE.ie_key()) | |
74278def S |
778 | |
779 | ||
f6c3664d | 780 | class VimeoChannelIE(VimeoBaseInfoExtractor): |
9148eb00 | 781 | IE_NAME = 'vimeo:channel' |
3946864c | 782 | _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])' |
caeefc29 | 783 | _MORE_PAGES_INDICATOR = r'<a.+?rel="next"' |
84458766 | 784 | _TITLE = None |
55a10eab | 785 | _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"' |
2929b3e7 | 786 | _TESTS = [{ |
3946864c | 787 | 'url': 'https://vimeo.com/channels/tributes', |
2929b3e7 | 788 | 'info_dict': { |
a3fa5da4 | 789 | 'id': 'tributes', |
2929b3e7 PH |
790 | 'title': 'Vimeo Tributes', |
791 | }, | |
792 | 'playlist_mincount': 25, | |
793 | }] | |
caeefc29 | 794 | |
5cc14c2f JMF |
795 | def _page_url(self, base_url, pagenum): |
796 | return '%s/videos/page:%d/' % (base_url, pagenum) | |
797 | ||
fb30ec22 | 798 | def _extract_list_title(self, webpage): |
84458766 | 799 | return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title') |
fb30ec22 | 800 | |
bf8f082a PH |
801 | def _login_list_password(self, page_url, list_id, webpage): |
802 | login_form = self._search_regex( | |
803 | r'(?s)<form[^>]+?id="pw_form"(.*?)</form>', | |
804 | webpage, 'login form', default=None) | |
805 | if not login_form: | |
806 | return webpage | |
807 | ||
d800609c | 808 | password = self._downloader.params.get('videopassword') |
bf8f082a PH |
809 | if password is None: |
810 | raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True) | |
f8da79f8 | 811 | fields = self._hidden_inputs(login_form) |
7c845629 | 812 | token, vuid = self._extract_xsrft_and_vuid(webpage) |
bf8f082a PH |
813 | fields['token'] = token |
814 | fields['password'] = password | |
15707c7e | 815 | post = urlencode_postdata(fields) |
bf8f082a PH |
816 | password_path = self._search_regex( |
817 | r'action="([^"]+)"', login_form, 'password URL') | |
818 | password_url = compat_urlparse.urljoin(page_url, password_path) | |
67dda517 | 819 | password_request = sanitized_Request(password_url, post) |
bf8f082a | 820 | password_request.add_header('Content-type', 'application/x-www-form-urlencoded') |
9eab37dc S |
821 | self._set_vimeo_cookie('vuid', vuid) |
822 | self._set_vimeo_cookie('xsrft', token) | |
bf8f082a PH |
823 | |
824 | return self._download_webpage( | |
825 | password_request, list_id, | |
826 | 'Verifying the password', 'Wrong password') | |
827 | ||
2c94198e | 828 | def _title_and_entries(self, list_id, base_url): |
caeefc29 | 829 | for pagenum in itertools.count(1): |
bf8f082a | 830 | page_url = self._page_url(base_url, pagenum) |
55a10eab | 831 | webpage = self._download_webpage( |
bf8f082a | 832 | page_url, list_id, |
9148eb00 | 833 | 'Downloading page %s' % pagenum) |
bf8f082a PH |
834 | |
835 | if pagenum == 1: | |
836 | webpage = self._login_list_password(page_url, list_id, webpage) | |
2c94198e S |
837 | yield self._extract_list_title(webpage) |
838 | ||
c8e3e097 S |
839 | # Try extracting href first since not all videos are available via |
840 | # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729) | |
841 | clips = re.findall( | |
04a3d4d2 | 842 | r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage) |
c8e3e097 | 843 | if clips: |
04a3d4d2 | 844 | for video_id, video_url, video_title in clips: |
c8e3e097 S |
845 | yield self.url_result( |
846 | compat_urlparse.urljoin(base_url, video_url), | |
04a3d4d2 | 847 | VimeoIE.ie_key(), video_id=video_id, video_title=video_title) |
c8e3e097 S |
848 | # More relaxed fallback |
849 | else: | |
850 | for video_id in re.findall(r'id=["\']clip_(\d+)', webpage): | |
851 | yield self.url_result( | |
852 | 'https://vimeo.com/%s' % video_id, | |
853 | VimeoIE.ie_key(), video_id=video_id) | |
bf8f082a | 854 | |
caeefc29 JMF |
855 | if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None: |
856 | break | |
857 | ||
2c94198e S |
858 | def _extract_videos(self, list_id, base_url): |
859 | title_and_entries = self._title_and_entries(list_id, base_url) | |
860 | list_title = next(title_and_entries) | |
861 | return self.playlist_result(title_and_entries, list_id, list_title) | |
55a10eab JMF |
862 | |
863 | def _real_extract(self, url): | |
864 | mobj = re.match(self._VALID_URL, url) | |
4f3e9430 | 865 | channel_id = mobj.group('id') |
3946864c | 866 | return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id) |
55a10eab JMF |
867 | |
868 | ||
869 | class VimeoUserIE(VimeoChannelIE): | |
9148eb00 | 870 | IE_NAME = 'vimeo:user' |
b29440ae | 871 | _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)' |
55a10eab | 872 | _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>' |
2929b3e7 | 873 | _TESTS = [{ |
3946864c | 874 | 'url': 'https://vimeo.com/nkistudio/videos', |
2929b3e7 PH |
875 | 'info_dict': { |
876 | 'title': 'Nki', | |
a3fa5da4 | 877 | 'id': 'nkistudio', |
2929b3e7 PH |
878 | }, |
879 | 'playlist_mincount': 66, | |
880 | }] | |
55a10eab JMF |
881 | |
882 | def _real_extract(self, url): | |
883 | mobj = re.match(self._VALID_URL, url) | |
884 | name = mobj.group('name') | |
3946864c | 885 | return self._extract_videos(name, 'https://vimeo.com/%s' % name) |
5cc14c2f JMF |
886 | |
887 | ||
888 | class VimeoAlbumIE(VimeoChannelIE): | |
9148eb00 | 889 | IE_NAME = 'vimeo:album' |
b5eab86c | 890 | _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)(?:$|[?#]|/(?!video))' |
5cc14c2f | 891 | _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>' |
2929b3e7 | 892 | _TESTS = [{ |
d1508cd6 | 893 | 'url': 'https://vimeo.com/album/2632481', |
2929b3e7 | 894 | 'info_dict': { |
a3fa5da4 | 895 | 'id': '2632481', |
2929b3e7 PH |
896 | 'title': 'Staff Favorites: November 2013', |
897 | }, | |
898 | 'playlist_mincount': 13, | |
bf8f082a PH |
899 | }, { |
900 | 'note': 'Password-protected album', | |
901 | 'url': 'https://vimeo.com/album/3253534', | |
902 | 'info_dict': { | |
903 | 'title': 'test', | |
904 | 'id': '3253534', | |
905 | }, | |
906 | 'playlist_count': 1, | |
907 | 'params': { | |
908 | 'videopassword': 'youtube-dl', | |
909 | } | |
b5eab86c S |
910 | }, { |
911 | 'url': 'https://vimeo.com/album/2632481/sort:plays/format:thumbnail', | |
912 | 'only_matching': True, | |
089657ed S |
913 | }, { |
914 | # TODO: respect page number | |
915 | 'url': 'https://vimeo.com/album/2632481/page:2/sort:plays/format:thumbnail', | |
916 | 'only_matching': True, | |
2929b3e7 | 917 | }] |
5cc14c2f JMF |
918 | |
919 | def _page_url(self, base_url, pagenum): | |
920 | return '%s/page:%d/' % (base_url, pagenum) | |
921 | ||
922 | def _real_extract(self, url): | |
bf8f082a | 923 | album_id = self._match_id(url) |
d1508cd6 | 924 | return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id) |
fb30ec22 JMF |
925 | |
926 | ||
927 | class VimeoGroupsIE(VimeoAlbumIE): | |
9148eb00 | 928 | IE_NAME = 'vimeo:group' |
fdb20a27 | 929 | _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)' |
2929b3e7 | 930 | _TESTS = [{ |
3946864c | 931 | 'url': 'https://vimeo.com/groups/rolexawards', |
2929b3e7 | 932 | 'info_dict': { |
a3fa5da4 | 933 | 'id': 'rolexawards', |
2929b3e7 PH |
934 | 'title': 'Rolex Awards for Enterprise', |
935 | }, | |
936 | 'playlist_mincount': 73, | |
937 | }] | |
fb30ec22 JMF |
938 | |
939 | def _extract_list_title(self, webpage): | |
940 | return self._og_search_title(webpage) | |
941 | ||
942 | def _real_extract(self, url): | |
943 | mobj = re.match(self._VALID_URL, url) | |
944 | name = mobj.group('name') | |
3946864c | 945 | return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name) |
fcea44c6 PH |
946 | |
947 | ||
531a7496 | 948 | class VimeoReviewIE(VimeoBaseInfoExtractor): |
9148eb00 PH |
949 | IE_NAME = 'vimeo:review' |
950 | IE_DESC = 'Review pages on vimeo' | |
27655037 | 951 | _VALID_URL = r'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})' |
d36d3f42 | 952 | _TESTS = [{ |
fcea44c6 | 953 | 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d', |
fcea44c6 PH |
954 | 'md5': 'c507a72f780cacc12b2248bb4006d253', |
955 | 'info_dict': { | |
fc09240e PH |
956 | 'id': '75524534', |
957 | 'ext': 'mp4', | |
fcea44c6 PH |
958 | 'title': "DICK HARDWICK 'Comedian'", |
959 | 'uploader': 'Richard Hardwick', | |
531a7496 | 960 | 'uploader_id': 'user21297594', |
fcea44c6 | 961 | } |
d36d3f42 PH |
962 | }, { |
963 | 'note': 'video player needs Referer', | |
3946864c | 964 | 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053', |
d36d3f42 PH |
965 | 'md5': '6295fdab8f4bf6a002d058b2c6dce276', |
966 | 'info_dict': { | |
967 | 'id': '91613211', | |
968 | 'ext': 'mp4', | |
9dec9930 | 969 | 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn', |
d36d3f42 PH |
970 | 'uploader': 'DevWeek Events', |
971 | 'duration': 2773, | |
ec85ded8 | 972 | 'thumbnail': r're:^https?://.*\.jpg$', |
531a7496 | 973 | 'uploader_id': 'user22258446', |
d36d3f42 | 974 | } |
c1ff6e1a YCH |
975 | }, { |
976 | 'note': 'Password protected', | |
977 | 'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde', | |
978 | 'info_dict': { | |
979 | 'id': '138823582', | |
980 | 'ext': 'mp4', | |
981 | 'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1', | |
982 | 'uploader': 'TMB', | |
983 | 'uploader_id': 'user37284429', | |
984 | }, | |
985 | 'params': { | |
986 | 'videopassword': 'holygrail', | |
987 | }, | |
a093cfc7 | 988 | 'skip': 'video gone', |
d36d3f42 | 989 | }] |
fcea44c6 | 990 | |
c1ff6e1a YCH |
991 | def _real_initialize(self): |
992 | self._login() | |
993 | ||
994 | def _get_config_url(self, webpage_url, video_id, video_password_verified=False): | |
995 | webpage = self._download_webpage(webpage_url, video_id) | |
d61aa5eb S |
996 | config_url = self._html_search_regex( |
997 | r'data-config-url=(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, | |
998 | 'config URL', default=None, group='url') | |
999 | if not config_url: | |
1000 | data = self._parse_json(self._search_regex( | |
1001 | r'window\s*=\s*_extend\(window,\s*({.+?})\);', webpage, 'data', | |
1002 | default=NO_DEFAULT if video_password_verified else '{}'), video_id) | |
27655037 RA |
1003 | config = data.get('vimeo_esi', {}).get('config', {}) |
1004 | config_url = config.get('configUrl') or try_get(config, lambda x: x['clipData']['configUrl']) | |
c1ff6e1a YCH |
1005 | if config_url is None: |
1006 | self._verify_video_password(webpage_url, video_id, webpage) | |
1007 | config_url = self._get_config_url( | |
1008 | webpage_url, video_id, video_password_verified=True) | |
1009 | return config_url | |
1010 | ||
fcea44c6 | 1011 | def _real_extract(self, url): |
27655037 | 1012 | page_url, video_id = re.match(self._VALID_URL, url).groups() |
c1ff6e1a YCH |
1013 | config_url = self._get_config_url(url, video_id) |
1014 | config = self._download_json(config_url, video_id) | |
531a7496 | 1015 | info_dict = self._parse_config(config, video_id) |
27655037 RA |
1016 | source_format = self._extract_original_format(page_url, video_id) |
1017 | if source_format: | |
1018 | info_dict['formats'].append(source_format) | |
531a7496 YCH |
1019 | self._vimeo_sort_formats(info_dict['formats']) |
1020 | info_dict['id'] = video_id | |
1021 | return info_dict | |
efb7e119 JMF |
1022 | |
1023 | ||
f6c3664d | 1024 | class VimeoWatchLaterIE(VimeoChannelIE): |
efb7e119 JMF |
1025 | IE_NAME = 'vimeo:watchlater' |
1026 | IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)' | |
84458766 S |
1027 | _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater' |
1028 | _TITLE = 'Watch Later' | |
efb7e119 | 1029 | _LOGIN_REQUIRED = True |
2929b3e7 | 1030 | _TESTS = [{ |
84458766 | 1031 | 'url': 'https://vimeo.com/watchlater', |
2929b3e7 PH |
1032 | 'only_matching': True, |
1033 | }] | |
efb7e119 JMF |
1034 | |
1035 | def _real_initialize(self): | |
1036 | self._login() | |
1037 | ||
1038 | def _page_url(self, base_url, pagenum): | |
1039 | url = '%s/page:%d/' % (base_url, pagenum) | |
67dda517 | 1040 | request = sanitized_Request(url) |
efb7e119 JMF |
1041 | # Set the header to get a partial html page with the ids, |
1042 | # the normal page doesn't contain them. | |
1043 | request.add_header('X-Requested-With', 'XMLHttpRequest') | |
1044 | return request | |
1045 | ||
1046 | def _real_extract(self, url): | |
84458766 | 1047 | return self._extract_videos('watchlater', 'https://vimeo.com/watchlater') |
d6e6a422 PH |
1048 | |
1049 | ||
1050 | class VimeoLikesIE(InfoExtractor): | |
361a965b | 1051 | _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)' |
d6e6a422 PH |
1052 | IE_NAME = 'vimeo:likes' |
1053 | IE_DESC = 'Vimeo user likes' | |
361a965b | 1054 | _TESTS = [{ |
9c44d242 PH |
1055 | 'url': 'https://vimeo.com/user755559/likes/', |
1056 | 'playlist_mincount': 293, | |
611c1dd9 | 1057 | 'info_dict': { |
a3fa5da4 | 1058 | 'id': 'user755559_likes', |
611c1dd9 S |
1059 | 'description': 'See all the videos urza likes', |
1060 | 'title': 'Videos urza likes', | |
d6e6a422 | 1061 | }, |
361a965b S |
1062 | }, { |
1063 | 'url': 'https://vimeo.com/stormlapse/likes', | |
1064 | 'only_matching': True, | |
1065 | }] | |
d6e6a422 PH |
1066 | |
1067 | def _real_extract(self, url): | |
1068 | user_id = self._match_id(url) | |
9c44d242 PH |
1069 | webpage = self._download_webpage(url, user_id) |
1070 | page_count = self._int( | |
1071 | self._search_regex( | |
1072 | r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)"> | |
1073 | .*?</a></li>\s*<li\s+class="pagination_next"> | |
361a965b | 1074 | ''', webpage, 'page count', default=1), |
9c44d242 PH |
1075 | 'page count', fatal=True) |
1076 | PAGE_SIZE = 12 | |
1077 | title = self._html_search_regex( | |
1078 | r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False) | |
1079 | description = self._html_search_meta('description', webpage) | |
1080 | ||
1081 | def _get_page(idx): | |
361a965b | 1082 | page_url = 'https://vimeo.com/%s/likes/page:%d/sort:date' % ( |
3946864c | 1083 | user_id, idx + 1) |
9c44d242 PH |
1084 | webpage = self._download_webpage( |
1085 | page_url, user_id, | |
1086 | note='Downloading page %d/%d' % (idx + 1, page_count)) | |
1087 | video_list = self._search_regex( | |
1088 | r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>', | |
1089 | webpage, 'video content') | |
1090 | paths = re.findall( | |
1091 | r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list) | |
1092 | for path in paths: | |
1093 | yield { | |
1094 | '_type': 'url', | |
1095 | 'url': compat_urlparse.urljoin(page_url, path), | |
1096 | } | |
1097 | ||
1098 | pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE) | |
d6e6a422 PH |
1099 | |
1100 | return { | |
9c44d242 | 1101 | '_type': 'playlist', |
361a965b | 1102 | 'id': '%s_likes' % user_id, |
9c44d242 PH |
1103 | 'title': title, |
1104 | 'description': description, | |
1105 | 'entries': pl, | |
d6e6a422 | 1106 | } |
ca01d178 RA |
1107 | |
1108 | ||
1109 | class VHXEmbedIE(InfoExtractor): | |
1110 | IE_NAME = 'vhx:embed' | |
1111 | _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)' | |
1112 | ||
1113 | def _call_api(self, video_id, access_token, path='', query=None): | |
1114 | return self._download_json( | |
1115 | 'https://api.vhx.tv/videos/' + video_id + path, video_id, headers={ | |
1116 | 'Authorization': 'Bearer ' + access_token, | |
1117 | }, query=query) | |
1118 | ||
1119 | def _real_extract(self, url): | |
1120 | video_id = self._match_id(url) | |
1121 | webpage = self._download_webpage(url, video_id) | |
1122 | credentials = self._parse_json(self._search_regex( | |
1123 | r'(?s)credentials\s*:\s*({.+?}),', webpage, | |
1124 | 'config'), video_id, js_to_json) | |
1125 | access_token = credentials['access_token'] | |
1126 | ||
1127 | query = {} | |
1128 | for k, v in credentials.items(): | |
1129 | if k in ('authorization', 'authUserToken', 'ticket') and v and v != 'undefined': | |
1130 | if k == 'authUserToken': | |
1131 | query['auth_user_token'] = v | |
1132 | else: | |
1133 | query[k] = v | |
1134 | files = self._call_api(video_id, access_token, '/files', query) | |
1135 | ||
1136 | formats = [] | |
1137 | for f in files: | |
1138 | href = try_get(f, lambda x: x['_links']['source']['href']) | |
1139 | if not href: | |
1140 | continue | |
1141 | method = f.get('method') | |
1142 | if method == 'hls': | |
1143 | formats.extend(self._extract_m3u8_formats( | |
1144 | href, video_id, 'mp4', 'm3u8_native', | |
1145 | m3u8_id='hls', fatal=False)) | |
1146 | elif method == 'dash': | |
1147 | formats.extend(self._extract_mpd_formats( | |
1148 | href, video_id, mpd_id='dash', fatal=False)) | |
1149 | else: | |
1150 | fmt = { | |
1151 | 'filesize': int_or_none(try_get(f, lambda x: x['size']['bytes'])), | |
1152 | 'format_id': 'http', | |
1153 | 'preference': 1, | |
1154 | 'url': href, | |
1155 | 'vcodec': f.get('codec'), | |
1156 | } | |
1157 | quality = f.get('quality') | |
1158 | if quality: | |
1159 | fmt.update({ | |
1160 | 'format_id': 'http-' + quality, | |
1161 | 'height': int_or_none(self._search_regex(r'(\d+)p', quality, 'height', default=None)), | |
1162 | }) | |
1163 | formats.append(fmt) | |
1164 | self._sort_formats(formats) | |
1165 | ||
1166 | video_data = self._call_api(video_id, access_token) | |
1167 | title = video_data.get('title') or video_data['name'] | |
1168 | ||
d9df8f12 RA |
1169 | subtitles = {} |
1170 | for subtitle in try_get(video_data, lambda x: x['tracks']['subtitles'], list) or []: | |
1171 | lang = subtitle.get('srclang') or subtitle.get('label') | |
1172 | for _link in subtitle.get('_links', {}).values(): | |
1173 | href = _link.get('href') | |
1174 | if not href: | |
1175 | continue | |
1176 | subtitles.setdefault(lang, []).append({ | |
1177 | 'url': href, | |
1178 | }) | |
1179 | ||
ca01d178 RA |
1180 | q = qualities(['small', 'medium', 'large', 'source']) |
1181 | thumbnails = [] | |
1182 | for thumbnail_id, thumbnail_url in video_data.get('thumbnail', {}).items(): | |
1183 | thumbnails.append({ | |
1184 | 'id': thumbnail_id, | |
1185 | 'url': thumbnail_url, | |
1186 | 'preference': q(thumbnail_id), | |
1187 | }) | |
1188 | ||
1189 | return { | |
1190 | 'id': video_id, | |
1191 | 'title': title, | |
1192 | 'description': video_data.get('description'), | |
1193 | 'duration': int_or_none(try_get(video_data, lambda x: x['duration']['seconds'])), | |
1194 | 'formats': formats, | |
d9df8f12 | 1195 | 'subtitles': subtitles, |
ca01d178 RA |
1196 | 'thumbnails': thumbnails, |
1197 | 'timestamp': unified_timestamp(video_data.get('created_at')), | |
1198 | 'view_count': int_or_none(video_data.get('plays_count')), | |
1199 | } |