]>
Commit | Line | Data |
---|---|---|
dcdb292f | 1 | # coding: utf-8 |
9148eb00 PH |
2 | from __future__ import unicode_literals |
3 | ||
79fec976 | 4 | import base64 |
eb9c9c74 | 5 | import functools |
b3d14cbf | 6 | import re |
caeefc29 | 7 | import itertools |
b3d14cbf PH |
8 | |
9 | from .common import InfoExtractor | |
8c25f81b | 10 | from ..compat import ( |
eb9c9c74 | 11 | compat_kwargs, |
1060425c | 12 | compat_HTTPError, |
6a55bb66 | 13 | compat_str, |
9c44d242 | 14 | compat_urlparse, |
8c25f81b PH |
15 | ) |
16 | from ..utils import ( | |
681ac7c9 | 17 | clean_html, |
d5f071af | 18 | determine_ext, |
b3d14cbf | 19 | ExtractorError, |
58ab5cbc | 20 | get_element_by_class, |
9cb070f9 | 21 | HEADRequest, |
ca01d178 | 22 | js_to_json, |
9c44d242 | 23 | int_or_none, |
ae1c585c | 24 | merge_dicts, |
eb9c9c74 | 25 | OnDemandPagedList, |
ca01d178 | 26 | parse_filesize, |
cce889b9 | 27 | parse_iso8601, |
4dfbf869 | 28 | parse_qs, |
67dda517 | 29 | sanitized_Request, |
30965ac6 | 30 | smuggle_url, |
b3d14cbf | 31 | std_headers, |
681ac7c9 | 32 | str_or_none, |
c15cd296 | 33 | try_get, |
c15cd296 | 34 | unified_timestamp, |
9d4660ca | 35 | unsmuggle_url, |
a980bc43 | 36 | urlencode_postdata, |
1c45ff55 | 37 | urljoin, |
b407e173 | 38 | unescapeHTML, |
9cb070f9 | 39 | urlhandle_detect_ext, |
b3d14cbf PH |
40 | ) |
41 | ||
bbafbe20 | 42 | |
efb7e119 JMF |
43 | class VimeoBaseInfoExtractor(InfoExtractor): |
44 | _NETRC_MACHINE = 'vimeo' | |
45 | _LOGIN_REQUIRED = False | |
f6c3664d | 46 | _LOGIN_URL = 'https://vimeo.com/log_in' |
efb7e119 JMF |
47 | |
48 | def _login(self): | |
68217024 | 49 | username, password = self._get_login_info() |
efb7e119 JMF |
50 | if username is None: |
51 | if self._LOGIN_REQUIRED: | |
4f3e9430 | 52 | raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) |
efb7e119 | 53 | return |
26ad6bcd S |
54 | webpage = self._download_webpage( |
55 | self._LOGIN_URL, None, 'Downloading login page') | |
7c845629 | 56 | token, vuid = self._extract_xsrft_and_vuid(webpage) |
26ad6bcd | 57 | data = { |
f6c3664d | 58 | 'action': 'login', |
efb7e119 JMF |
59 | 'email': username, |
60 | 'password': password, | |
efb7e119 JMF |
61 | 'service': 'vimeo', |
62 | 'token': token, | |
26ad6bcd | 63 | } |
9eab37dc | 64 | self._set_vimeo_cookie('vuid', vuid) |
26ad6bcd S |
65 | try: |
66 | self._download_webpage( | |
67 | self._LOGIN_URL, None, 'Logging in', | |
68 | data=urlencode_postdata(data), headers={ | |
69 | 'Content-Type': 'application/x-www-form-urlencoded', | |
70 | 'Referer': self._LOGIN_URL, | |
71 | }) | |
72 | except ExtractorError as e: | |
73 | if isinstance(e.cause, compat_HTTPError) and e.cause.code == 418: | |
74 | raise ExtractorError( | |
75 | 'Unable to log in: bad username or password', | |
76 | expected=True) | |
77 | raise ExtractorError('Unable to log in') | |
efb7e119 | 78 | |
cce889b9 | 79 | def _get_video_password(self): |
a06916d9 | 80 | password = self.get_param('videopassword') |
c1ff6e1a | 81 | if password is None: |
cce889b9 | 82 | raise ExtractorError( |
83 | 'This video is protected by a password, use the --video-password option', | |
84 | expected=True) | |
85 | return password | |
86 | ||
87 | def _verify_video_password(self, url, video_id, password, token, vuid): | |
c1ff6e1a YCH |
88 | if url.startswith('http://'): |
89 | # vimeo only supports https now, but the user can give an http url | |
90 | url = url.replace('http://', 'https://') | |
c1ff6e1a YCH |
91 | self._set_vimeo_cookie('vuid', vuid) |
92 | return self._download_webpage( | |
cce889b9 | 93 | url + '/password', video_id, 'Verifying the password', |
94 | 'Wrong password', data=urlencode_postdata({ | |
95 | 'password': password, | |
96 | 'token': token, | |
97 | }), headers={ | |
98 | 'Content-Type': 'application/x-www-form-urlencoded', | |
99 | 'Referer': url, | |
100 | }) | |
c1ff6e1a | 101 | |
7c845629 S |
102 | def _extract_xsrft_and_vuid(self, webpage): |
103 | xsrft = self._search_regex( | |
b826035d | 104 | r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)', |
f6c3664d | 105 | webpage, 'login token', group='xsrft') |
7c845629 S |
106 | vuid = self._search_regex( |
107 | r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1', | |
108 | webpage, 'vuid', group='vuid') | |
109 | return xsrft, vuid | |
f6c3664d | 110 | |
eb9c9c74 RA |
111 | def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs): |
112 | vimeo_config = self._search_regex( | |
113 | r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', | |
114 | webpage, 'vimeo config', *args, **compat_kwargs(kwargs)) | |
115 | if vimeo_config: | |
116 | return self._parse_json(vimeo_config, video_id) | |
117 | ||
9eab37dc S |
118 | def _set_vimeo_cookie(self, name, value): |
119 | self._set_cookie('vimeo.com', name, value) | |
120 | ||
531a7496 YCH |
121 | def _vimeo_sort_formats(self, formats): |
122 | # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps | |
123 | # at the same time without actual units specified. This lead to wrong sorting. | |
54f37eea | 124 | # But since yt-dlp prefers 'res,fps' anyway, 'field_preference' is not needed |
125 | self._sort_formats(formats) | |
531a7496 YCH |
126 | |
127 | def _parse_config(self, config, video_id): | |
d8c507c9 | 128 | video_data = config['video'] |
d8c507c9 | 129 | video_title = video_data['title'] |
85b6335d RA |
130 | live_event = video_data.get('live_event') or {} |
131 | is_live = live_event.get('status') == 'started' | |
58ab5cbc | 132 | request = config.get('request') or {} |
531a7496 YCH |
133 | |
134 | formats = [] | |
58ab5cbc | 135 | config_files = video_data.get('files') or request.get('files') or {} |
136 | for f in (config_files.get('progressive') or []): | |
531a7496 YCH |
137 | video_url = f.get('url') |
138 | if not video_url: | |
139 | continue | |
140 | formats.append({ | |
141 | 'url': video_url, | |
142 | 'format_id': 'http-%s' % f.get('quality'), | |
143 | 'width': int_or_none(f.get('width')), | |
144 | 'height': int_or_none(f.get('height')), | |
145 | 'fps': int_or_none(f.get('fps')), | |
146 | 'tbr': int_or_none(f.get('bitrate')), | |
147 | }) | |
d8c507c9 | 148 | |
85b6335d | 149 | # TODO: fix handling of 308 status code returned for live archive manifest requests |
52c50a10 | 150 | sep_pattern = r'/sep/video/' |
d8c507c9 | 151 | for files_type in ('hls', 'dash'): |
58ab5cbc | 152 | for cdn_name, cdn_data in (try_get(config_files, lambda x: x[files_type]['cdns']) or {}).items(): |
d8c507c9 RA |
153 | manifest_url = cdn_data.get('url') |
154 | if not manifest_url: | |
155 | continue | |
156 | format_id = '%s-%s' % (files_type, cdn_name) | |
52c50a10 RA |
157 | sep_manifest_urls = [] |
158 | if re.search(sep_pattern, manifest_url): | |
159 | for suffix, repl in (('', 'video'), ('_sep', 'sep/video')): | |
160 | sep_manifest_urls.append((format_id + suffix, re.sub( | |
161 | sep_pattern, '/%s/' % repl, manifest_url))) | |
162 | else: | |
163 | sep_manifest_urls = [(format_id, manifest_url)] | |
164 | for f_id, m_url in sep_manifest_urls: | |
165 | if files_type == 'hls': | |
166 | formats.extend(self._extract_m3u8_formats( | |
167 | m_url, video_id, 'mp4', | |
168 | 'm3u8' if is_live else 'm3u8_native', m3u8_id=f_id, | |
169 | note='Downloading %s m3u8 information' % cdn_name, | |
170 | fatal=False)) | |
171 | elif files_type == 'dash': | |
c25720ef RA |
172 | if 'json=1' in m_url: |
173 | real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url') | |
174 | if real_m_url: | |
175 | m_url = real_m_url | |
e834f044 | 176 | mpd_formats = self._extract_mpd_formats( |
ae9a173b RA |
177 | m_url.replace('/master.json', '/master.mpd'), video_id, f_id, |
178 | 'Downloading %s MPD information' % cdn_name, | |
e834f044 | 179 | fatal=False) |
e834f044 | 180 | formats.extend(mpd_formats) |
531a7496 | 181 | |
85b6335d RA |
182 | live_archive = live_event.get('archive') or {} |
183 | live_archive_source_url = live_archive.get('source_url') | |
184 | if live_archive_source_url and live_archive.get('status') == 'done': | |
185 | formats.append({ | |
186 | 'format_id': 'live-archive-source', | |
187 | 'url': live_archive_source_url, | |
f983b875 | 188 | 'quality': 10, |
85b6335d RA |
189 | }) |
190 | ||
531a7496 | 191 | subtitles = {} |
58ab5cbc | 192 | for tt in (request.get('text_tracks') or []): |
193 | subtitles[tt['lang']] = [{ | |
194 | 'ext': 'vtt', | |
195 | 'url': urljoin('https://vimeo.com', tt['url']), | |
196 | }] | |
531a7496 | 197 | |
c25720ef RA |
198 | thumbnails = [] |
199 | if not is_live: | |
58ab5cbc | 200 | for key, thumb in (video_data.get('thumbs') or {}).items(): |
c25720ef RA |
201 | thumbnails.append({ |
202 | 'id': key, | |
203 | 'width': int_or_none(key), | |
204 | 'url': thumb, | |
205 | }) | |
206 | thumbnail = video_data.get('thumbnail') | |
207 | if thumbnail: | |
208 | thumbnails.append({ | |
209 | 'url': thumbnail, | |
210 | }) | |
211 | ||
212 | owner = video_data.get('owner') or {} | |
213 | video_uploader_url = owner.get('url') | |
214 | ||
531a7496 | 215 | return { |
681ac7c9 | 216 | 'id': str_or_none(video_data.get('id')) or video_id, |
c25720ef RA |
217 | 'title': self._live_title(video_title) if is_live else video_title, |
218 | 'uploader': owner.get('name'), | |
219 | 'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None, | |
531a7496 | 220 | 'uploader_url': video_uploader_url, |
c25720ef RA |
221 | 'thumbnails': thumbnails, |
222 | 'duration': int_or_none(video_data.get('duration')), | |
531a7496 YCH |
223 | 'formats': formats, |
224 | 'subtitles': subtitles, | |
c25720ef | 225 | 'is_live': is_live, |
531a7496 YCH |
226 | } |
227 | ||
bc2ca1bb | 228 | def _extract_original_format(self, url, video_id, unlisted_hash=None): |
229 | query = {'action': 'load_download_config'} | |
230 | if unlisted_hash: | |
231 | query['unlisted_hash'] = unlisted_hash | |
27655037 | 232 | download_data = self._download_json( |
bc2ca1bb | 233 | url, video_id, fatal=False, query=query, |
9cb070f9 | 234 | headers={'X-Requested-With': 'XMLHttpRequest'}, |
235 | expected_status=(403, 404)) or {} | |
236 | source_file = download_data.get('source_file') | |
237 | download_url = try_get(source_file, lambda x: x['download_url']) | |
238 | if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'): | |
239 | source_name = source_file.get('public_name', 'Original') | |
240 | if self._is_valid_url(download_url, video_id, '%s video' % source_name): | |
241 | ext = (try_get( | |
242 | source_file, lambda x: x['extension'], | |
243 | compat_str) or determine_ext( | |
244 | download_url, None) or 'mp4').lower() | |
245 | return { | |
246 | 'url': download_url, | |
247 | 'ext': ext, | |
248 | 'width': int_or_none(source_file.get('width')), | |
249 | 'height': int_or_none(source_file.get('height')), | |
250 | 'filesize': parse_filesize(source_file.get('size')), | |
251 | 'format_id': source_name, | |
252 | 'quality': 1, | |
253 | } | |
27655037 | 254 | |
605cad0b A |
255 | jwt_response = self._download_json( |
256 | 'https://vimeo.com/_rv/viewer', video_id, note='Downloading jwt token', fatal=False) or {} | |
257 | if not jwt_response.get('jwt'): | |
258 | return | |
259 | headers = {'Authorization': 'jwt %s' % jwt_response['jwt']} | |
260 | original_response = self._download_json( | |
261 | f'https://api.vimeo.com/videos/{video_id}', video_id, | |
9cb070f9 | 262 | headers=headers, fatal=False, expected_status=(403, 404)) or {} |
263 | for download_data in original_response.get('download') or []: | |
605cad0b A |
264 | download_url = download_data.get('link') |
265 | if not download_url or download_data.get('quality') != 'source': | |
266 | continue | |
9cb070f9 | 267 | ext = determine_ext(parse_qs(download_url).get('filename', [''])[0].lower(), default_ext=None) |
268 | if not ext: | |
269 | urlh = self._request_webpage( | |
270 | HEADRequest(download_url), video_id, fatal=False, note='Determining source extension') | |
271 | ext = urlh and urlhandle_detect_ext(urlh) | |
605cad0b A |
272 | return { |
273 | 'url': download_url, | |
9cb070f9 | 274 | 'ext': ext or 'unknown_video', |
605cad0b A |
275 | 'format_id': download_data.get('public_name', 'Original'), |
276 | 'width': int_or_none(download_data.get('width')), | |
277 | 'height': int_or_none(download_data.get('height')), | |
278 | 'fps': int_or_none(download_data.get('fps')), | |
279 | 'filesize': int_or_none(download_data.get('size')), | |
280 | 'quality': 1, | |
281 | } | |
282 | ||
efb7e119 | 283 | |
65469a7f | 284 | class VimeoIE(VimeoBaseInfoExtractor): |
b3d14cbf PH |
285 | """Information extractor for vimeo.com.""" |
286 | ||
287 | # _VALID_URL matches Vimeo URLs | |
bbafbe20 | 288 | _VALID_URL = r'''(?x) |
74278def S |
289 | https?:// |
290 | (?: | |
291 | (?: | |
292 | www| | |
681ac7c9 | 293 | player |
74278def S |
294 | ) |
295 | \. | |
296 | )? | |
681ac7c9 | 297 | vimeo(?:pro)?\.com/ |
eb9c9c74 | 298 | (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/) |
2a6f8475 | 299 | (?:[^/]+/)*? |
74278def S |
300 | (?: |
301 | (?: | |
302 | play_redirect_hls| | |
303 | moogaloop\.swf)\?clip_id= | |
304 | )? | |
305 | (?:videos?/)? | |
306 | (?P<id>[0-9]+) | |
cce889b9 | 307 | (?:/(?P<unlisted_hash>[\da-f]{10}))? |
74278def S |
308 | /?(?:[?&].*)?(?:[#].*)?$ |
309 | ''' | |
9148eb00 | 310 | IE_NAME = 'vimeo' |
a91b954b JMF |
311 | _TESTS = [ |
312 | { | |
9148eb00 | 313 | 'url': 'http://vimeo.com/56015672#at=0', |
9148eb00 PH |
314 | 'md5': '8879b6cc097e987f02484baf890129e5', |
315 | 'info_dict': { | |
ad5976b4 PH |
316 | 'id': '56015672', |
317 | 'ext': 'mp4', | |
3867038a | 318 | 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550", |
681ac7c9 | 319 | 'description': 'md5:2d3305bad981a06ff79f027f19865021', |
c15cd296 | 320 | 'timestamp': 1355990239, |
68f3b61f | 321 | 'upload_date': '20121220', |
ec85ded8 | 322 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434', |
68f3b61f S |
323 | 'uploader_id': 'user7108434', |
324 | 'uploader': 'Filippo Valsorda', | |
325 | 'duration': 10, | |
c38a67bc | 326 | 'license': 'by-sa', |
a91b954b | 327 | }, |
681ac7c9 RA |
328 | 'params': { |
329 | 'format': 'best[protocol=https]', | |
330 | }, | |
a91b954b JMF |
331 | }, |
332 | { | |
9148eb00 | 333 | 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876', |
9148eb00 PH |
334 | 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82', |
335 | 'note': 'Vimeo Pro video (#1197)', | |
336 | 'info_dict': { | |
4f3e9430 JMF |
337 | 'id': '68093876', |
338 | 'ext': 'mp4', | |
ec85ded8 | 339 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus', |
9148eb00 PH |
340 | 'uploader_id': 'openstreetmapus', |
341 | 'uploader': 'OpenStreetMap US', | |
342 | 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography', | |
681ac7c9 | 343 | 'description': 'md5:2c362968038d4499f4d79f88458590c1', |
69c8fb9e | 344 | 'duration': 1595, |
681ac7c9 RA |
345 | 'upload_date': '20130610', |
346 | 'timestamp': 1370893156, | |
58ab5cbc | 347 | 'license': 'by', |
681ac7c9 RA |
348 | }, |
349 | 'params': { | |
350 | 'format': 'best[protocol=https]', | |
a91b954b JMF |
351 | }, |
352 | }, | |
aa32314d | 353 | { |
9148eb00 | 354 | 'url': 'http://player.vimeo.com/video/54469442', |
9148eb00 PH |
355 | 'md5': '619b811a4417aa4abe78dc653becf511', |
356 | 'note': 'Videos that embed the url in the player page', | |
357 | 'info_dict': { | |
4f3e9430 JMF |
358 | 'id': '54469442', |
359 | 'ext': 'mp4', | |
0e6ebc13 | 360 | 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012', |
cce889b9 | 361 | 'uploader': 'Business of Software', |
362 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/businessofsoftware', | |
363 | 'uploader_id': 'businessofsoftware', | |
69c8fb9e | 364 | 'duration': 3610, |
58ea7ec8 | 365 | 'description': None, |
aa32314d | 366 | }, |
681ac7c9 RA |
367 | 'params': { |
368 | 'format': 'best[protocol=https]', | |
369 | }, | |
93b22c78 JMF |
370 | }, |
371 | { | |
9148eb00 | 372 | 'url': 'http://vimeo.com/68375962', |
9148eb00 PH |
373 | 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7', |
374 | 'note': 'Video protected with password', | |
375 | 'info_dict': { | |
4f3e9430 JMF |
376 | 'id': '68375962', |
377 | 'ext': 'mp4', | |
3867038a | 378 | 'title': 'youtube-dl password protected test video', |
c15cd296 | 379 | 'timestamp': 1371200155, |
9148eb00 | 380 | 'upload_date': '20130614', |
ec85ded8 | 381 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128', |
9148eb00 PH |
382 | 'uploader_id': 'user18948128', |
383 | 'uploader': 'Jaime Marquínez Ferrándiz', | |
69c8fb9e | 384 | 'duration': 10, |
365d136b | 385 | 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f', |
93b22c78 | 386 | }, |
9148eb00 | 387 | 'params': { |
681ac7c9 | 388 | 'format': 'best[protocol=https]', |
3867038a | 389 | 'videopassword': 'youtube-dl', |
93b22c78 JMF |
390 | }, |
391 | }, | |
548f31d9 S |
392 | { |
393 | 'url': 'http://vimeo.com/channels/keypeele/75629013', | |
394 | 'md5': '2f86a05afe9d7abc0b9126d229bbe15d', | |
548f31d9 S |
395 | 'info_dict': { |
396 | 'id': '75629013', | |
397 | 'ext': 'mp4', | |
398 | 'title': 'Key & Peele: Terrorist Interrogation', | |
399 | 'description': 'md5:8678b246399b070816b12313e8b4eb5c', | |
ec85ded8 | 400 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio', |
548f31d9 S |
401 | 'uploader_id': 'atencio', |
402 | 'uploader': 'Peter Atencio', | |
d03beddf S |
403 | 'channel_id': 'keypeele', |
404 | 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele', | |
c15cd296 S |
405 | 'timestamp': 1380339469, |
406 | 'upload_date': '20130928', | |
548f31d9 S |
407 | 'duration': 187, |
408 | }, | |
9cb070f9 | 409 | 'params': {'format': 'http-1080p'}, |
548f31d9 | 410 | }, |
1eac553e S |
411 | { |
412 | 'url': 'http://vimeo.com/76979871', | |
1eac553e S |
413 | 'note': 'Video with subtitles', |
414 | 'info_dict': { | |
415 | 'id': '76979871', | |
416 | 'ext': 'mp4', | |
417 | 'title': 'The New Vimeo Player (You Know, For Videos)', | |
418 | 'description': 'md5:2ec900bf97c3f389378a96aee11260ea', | |
c15cd296 | 419 | 'timestamp': 1381846109, |
1eac553e | 420 | 'upload_date': '20131015', |
ec85ded8 | 421 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff', |
1eac553e S |
422 | 'uploader_id': 'staff', |
423 | 'uploader': 'Vimeo Staff', | |
69c8fb9e | 424 | 'duration': 62, |
58ab5cbc | 425 | 'subtitles': { |
426 | 'de': [{'ext': 'vtt'}], | |
427 | 'en': [{'ext': 'vtt'}], | |
428 | 'es': [{'ext': 'vtt'}], | |
429 | 'fr': [{'ext': 'vtt'}], | |
430 | }, | |
9cb070f9 | 431 | }, |
432 | 'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'], | |
1eac553e | 433 | }, |
4698f0d8 JMF |
434 | { |
435 | # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/ | |
436 | 'url': 'https://player.vimeo.com/video/98044508', | |
437 | 'note': 'The js code contains assignments to the same variable as the config', | |
438 | 'info_dict': { | |
439 | 'id': '98044508', | |
440 | 'ext': 'mp4', | |
441 | 'title': 'Pier Solar OUYA Official Trailer', | |
442 | 'uploader': 'Tulio Gonçalves', | |
ec85ded8 | 443 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593', |
4698f0d8 JMF |
444 | 'uploader_id': 'user28849593', |
445 | }, | |
446 | }, | |
323f82a7 | 447 | { |
448 | # contains original format | |
449 | 'url': 'https://vimeo.com/33951933', | |
365d136b | 450 | 'md5': '53c688fa95a55bf4b7293d37a89c5c53', |
323f82a7 | 451 | 'info_dict': { |
452 | 'id': '33951933', | |
453 | 'ext': 'mp4', | |
454 | 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute', | |
455 | 'uploader': 'The DMCI', | |
ec85ded8 | 456 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci', |
323f82a7 | 457 | 'uploader_id': 'dmci', |
c15cd296 | 458 | 'timestamp': 1324343742, |
323f82a7 | 459 | 'upload_date': '20111220', |
460 | 'description': 'md5:ae23671e82d05415868f7ad1aec21147', | |
461 | }, | |
462 | }, | |
605cad0b A |
463 | { |
464 | 'note': 'Contains original format not accessible in webpage', | |
465 | 'url': 'https://vimeo.com/393756517', | |
466 | 'md5': 'c464af248b592190a5ffbb5d33f382b0', | |
467 | 'info_dict': { | |
468 | 'id': '393756517', | |
469 | 'ext': 'mov', | |
470 | 'timestamp': 1582642091, | |
471 | 'uploader_id': 'frameworkla', | |
472 | 'title': 'Straight To Hell - Sabrina: Netflix', | |
473 | 'uploader': 'Framework Studio', | |
474 | 'description': 'md5:f2edc61af3ea7a5592681ddbb683db73', | |
475 | 'upload_date': '20200225', | |
476 | }, | |
605cad0b | 477 | }, |
c143ddce S |
478 | { |
479 | # only available via https://vimeo.com/channels/tributes/6213729 and | |
480 | # not via https://vimeo.com/6213729 | |
481 | 'url': 'https://vimeo.com/channels/tributes/6213729', | |
482 | 'info_dict': { | |
483 | 'id': '6213729', | |
d03beddf | 484 | 'ext': 'mp4', |
c143ddce S |
485 | 'title': 'Vimeo Tribute: The Shining', |
486 | 'uploader': 'Casey Donahue', | |
ec85ded8 | 487 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue', |
c143ddce | 488 | 'uploader_id': 'caseydonahue', |
d03beddf S |
489 | 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes', |
490 | 'channel_id': 'tributes', | |
c15cd296 | 491 | 'timestamp': 1250886430, |
c143ddce S |
492 | 'upload_date': '20090821', |
493 | 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6', | |
494 | }, | |
495 | 'params': { | |
496 | 'skip_download': True, | |
497 | }, | |
c143ddce | 498 | }, |
f16f8505 | 499 | { |
cccd70a2 | 500 | # redirects to ondemand extractor and should be passed through it |
f16f8505 S |
501 | # for successful extraction |
502 | 'url': 'https://vimeo.com/73445910', | |
503 | 'info_dict': { | |
504 | 'id': '73445910', | |
505 | 'ext': 'mp4', | |
506 | 'title': 'The Reluctant Revolutionary', | |
507 | 'uploader': '10Ft Films', | |
ec85ded8 | 508 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms', |
f16f8505 | 509 | 'uploader_id': 'tenfootfilms', |
681ac7c9 RA |
510 | 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384', |
511 | 'upload_date': '20130830', | |
512 | 'timestamp': 1377853339, | |
f16f8505 S |
513 | }, |
514 | 'params': { | |
515 | 'skip_download': True, | |
516 | }, | |
cce889b9 | 517 | 'skip': 'this page is no longer available.', |
f16f8505 | 518 | }, |
79fec976 RA |
519 | { |
520 | 'url': 'http://player.vimeo.com/video/68375962', | |
521 | 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7', | |
522 | 'info_dict': { | |
523 | 'id': '68375962', | |
524 | 'ext': 'mp4', | |
3867038a | 525 | 'title': 'youtube-dl password protected test video', |
79fec976 RA |
526 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128', |
527 | 'uploader_id': 'user18948128', | |
528 | 'uploader': 'Jaime Marquínez Ferrándiz', | |
529 | 'duration': 10, | |
530 | }, | |
531 | 'params': { | |
681ac7c9 | 532 | 'format': 'best[protocol=https]', |
3867038a | 533 | 'videopassword': 'youtube-dl', |
79fec976 RA |
534 | }, |
535 | }, | |
c143ddce S |
536 | { |
537 | 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741', | |
538 | 'only_matching': True, | |
539 | }, | |
8bea039b LL |
540 | { |
541 | 'url': 'https://vimeo.com/109815029', | |
542 | 'note': 'Video not completely processed, "failed" seed status', | |
543 | 'only_matching': True, | |
544 | }, | |
6b7ceee1 S |
545 | { |
546 | 'url': 'https://vimeo.com/groups/travelhd/videos/22439234', | |
547 | 'only_matching': True, | |
548 | }, | |
c8e3e097 S |
549 | { |
550 | 'url': 'https://vimeo.com/album/2632481/video/79010983', | |
551 | 'only_matching': True, | |
552 | }, | |
1f52a09e | 553 | { |
554 | 'url': 'https://vimeo.com/showcase/3253534/video/119195465', | |
555 | 'note': 'A video in a password protected album (showcase)', | |
556 | 'info_dict': { | |
557 | 'id': '119195465', | |
558 | 'ext': 'mp4', | |
559 | 'title': 'youtube-dl test video \'ä"BaW_jenozKc', | |
560 | 'uploader': 'Philipp Hagemeister', | |
561 | 'uploader_id': 'user20132939', | |
562 | 'description': 'md5:fa7b6c6d8db0bdc353893df2f111855b', | |
563 | 'upload_date': '20150209', | |
564 | 'timestamp': 1423518307, | |
565 | }, | |
566 | 'params': { | |
567 | 'format': 'best[protocol=https]', | |
568 | 'videopassword': 'youtube-dl', | |
569 | }, | |
570 | }, | |
16f1131a S |
571 | { |
572 | # source file returns 403: Forbidden | |
573 | 'url': 'https://vimeo.com/7809605', | |
574 | 'only_matching': True, | |
575 | }, | |
241a318f | 576 | { |
2a6f8475 | 577 | 'note': 'Direct URL with hash', |
241a318f | 578 | 'url': 'https://vimeo.com/160743502/abd0e13fb4', |
2a6f8475 | 579 | 'info_dict': { |
580 | 'id': '160743502', | |
581 | 'ext': 'mp4', | |
582 | 'uploader': 'Julian Tryba', | |
583 | 'uploader_id': 'aliniamedia', | |
584 | 'title': 'Harrisville New Hampshire', | |
585 | 'timestamp': 1459259666, | |
586 | 'upload_date': '20160329', | |
587 | }, | |
9cb070f9 | 588 | 'params': {'skip_download': True}, |
589 | }, | |
590 | { | |
591 | 'url': 'https://vimeo.com/138909882', | |
592 | 'info_dict': { | |
593 | 'id': '138909882', | |
594 | 'ext': 'mp4', | |
595 | 'title': 'Eastnor Castle 2015 Firework Champions - The Promo!', | |
596 | 'description': 'md5:5967e090768a831488f6e74b7821b3c1', | |
597 | 'uploader_id': 'fireworkchampions', | |
598 | 'uploader': 'Firework Champions', | |
599 | 'upload_date': '20150910', | |
600 | 'timestamp': 1441901895, | |
601 | }, | |
602 | 'params': { | |
603 | 'skip_download': True, | |
604 | 'format': 'Original', | |
605 | }, | |
bc2ca1bb | 606 | }, |
1ee34c76 | 607 | { |
608 | 'url': 'https://vimeo.com/channels/staffpicks/143603739', | |
609 | 'info_dict': { | |
610 | 'id': '143603739', | |
611 | 'ext': 'mp4', | |
612 | 'uploader': 'Karim Huu Do', | |
613 | 'timestamp': 1445846953, | |
614 | 'upload_date': '20151026', | |
615 | 'title': 'The Shoes - Submarine Feat. Blaine Harrison', | |
616 | 'uploader_id': 'karimhd', | |
617 | 'description': 'md5:8e2eea76de4504c2e8020a9bcfa1e843', | |
618 | }, | |
619 | 'params': {'skip_download': 'm3u8'}, | |
620 | }, | |
bc2ca1bb | 621 | { |
622 | # requires passing unlisted_hash(a52724358e) to load_download_config request | |
623 | 'url': 'https://vimeo.com/392479337/a52724358e', | |
624 | 'only_matching': True, | |
9cb070f9 | 625 | }, |
a1a46075 S |
626 | # https://gettingthingsdone.com/workflowmap/ |
627 | # vimeo embed with check-password page protected by Referer header | |
a91b954b | 628 | ] |
b3d14cbf | 629 | |
d002e919 S |
630 | @staticmethod |
631 | def _smuggle_referrer(url, referrer_url): | |
632 | return smuggle_url(url, {'http_headers': {'Referer': referrer_url}}) | |
633 | ||
b407e173 | 634 | @staticmethod |
09b9c45e S |
635 | def _extract_urls(url, webpage): |
636 | urls = [] | |
b407e173 | 637 | # Look for embedded (iframe) Vimeo player |
09b9c45e | 638 | for mobj in re.finditer( |
7c1f4193 | 639 | r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1', |
f475e881 | 640 | webpage): |
09b9c45e S |
641 | urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url')), url)) |
642 | PLAIN_EMBED_RE = ( | |
643 | # Look for embedded (swf embed) Vimeo player | |
644 | r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1', | |
645 | # Look more for non-standard embedded Vimeo player | |
646 | r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1', | |
647 | ) | |
648 | for embed_re in PLAIN_EMBED_RE: | |
649 | for mobj in re.finditer(embed_re, webpage): | |
650 | urls.append(mobj.group('url')) | |
651 | return urls | |
652 | ||
653 | @staticmethod | |
654 | def _extract_url(url, webpage): | |
655 | urls = VimeoIE._extract_urls(url, webpage) | |
656 | return urls[0] if urls else None | |
b407e173 | 657 | |
a1a46075 | 658 | def _verify_player_video_password(self, url, video_id, headers): |
cce889b9 | 659 | password = self._get_video_password() |
79fec976 RA |
660 | data = urlencode_postdata({ |
661 | 'password': base64.b64encode(password.encode()), | |
662 | }) | |
a1a46075 S |
663 | headers = merge_dicts(headers, { |
664 | 'Content-Type': 'application/x-www-form-urlencoded', | |
665 | }) | |
666 | checked = self._download_json( | |
667 | url + '/check-password', video_id, | |
668 | 'Verifying the password', data=data, headers=headers) | |
669 | if checked is False: | |
670 | raise ExtractorError('Wrong video password', expected=True) | |
671 | return checked | |
0eecc6a4 | 672 | |
fc79158d JMF |
673 | def _real_initialize(self): |
674 | self._login() | |
675 | ||
58ab5cbc | 676 | def _extract_from_api(self, video_id, unlisted_hash=None): |
677 | token = self._download_json( | |
678 | 'https://vimeo.com/_rv/jwt', video_id, headers={ | |
679 | 'X-Requested-With': 'XMLHttpRequest' | |
680 | })['token'] | |
681 | api_url = 'https://api.vimeo.com/videos/' + video_id | |
682 | if unlisted_hash: | |
683 | api_url += ':' + unlisted_hash | |
684 | video = self._download_json( | |
685 | api_url, video_id, headers={ | |
686 | 'Authorization': 'jwt ' + token, | |
687 | }, query={ | |
688 | 'fields': 'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays', | |
689 | }) | |
690 | info = self._parse_config(self._download_json( | |
691 | video['config_url'], video_id), video_id) | |
692 | self._vimeo_sort_formats(info['formats']) | |
693 | get_timestamp = lambda x: parse_iso8601(video.get(x + '_time')) | |
694 | info.update({ | |
695 | 'description': video.get('description'), | |
696 | 'license': video.get('license'), | |
697 | 'release_timestamp': get_timestamp('release'), | |
698 | 'timestamp': get_timestamp('created'), | |
699 | 'view_count': int_or_none(try_get(video, lambda x: x['stats']['plays'])), | |
700 | }) | |
701 | connections = try_get( | |
702 | video, lambda x: x['metadata']['connections'], dict) or {} | |
703 | for k in ('comment', 'like'): | |
704 | info[k + '_count'] = int_or_none(try_get(connections, lambda x: x[k + 's']['total'])) | |
705 | return info | |
706 | ||
1f52a09e | 707 | def _try_album_password(self, url): |
708 | album_id = self._search_regex( | |
709 | r'vimeo\.com/(?:album|showcase)/([^/]+)', url, 'album id', default=None) | |
710 | if not album_id: | |
711 | return | |
712 | viewer = self._download_json( | |
713 | 'https://vimeo.com/_rv/viewer', album_id, fatal=False) | |
714 | if not viewer: | |
715 | webpage = self._download_webpage(url, album_id) | |
716 | viewer = self._parse_json(self._search_regex( | |
717 | r'bootstrap_data\s*=\s*({.+?})</script>', | |
718 | webpage, 'bootstrap data'), album_id)['viewer'] | |
719 | jwt = viewer['jwt'] | |
720 | album = self._download_json( | |
721 | 'https://api.vimeo.com/albums/' + album_id, | |
722 | album_id, headers={'Authorization': 'jwt ' + jwt}, | |
723 | query={'fields': 'description,name,privacy'}) | |
724 | if try_get(album, lambda x: x['privacy']['view']) == 'password': | |
a06916d9 | 725 | password = self.get_param('videopassword') |
1f52a09e | 726 | if not password: |
727 | raise ExtractorError( | |
728 | 'This album is protected by a password, use the --video-password option', | |
729 | expected=True) | |
730 | self._set_vimeo_cookie('vuid', viewer['vuid']) | |
731 | try: | |
732 | self._download_json( | |
733 | 'https://vimeo.com/showcase/%s/auth' % album_id, | |
734 | album_id, 'Verifying the password', data=urlencode_postdata({ | |
735 | 'password': password, | |
736 | 'token': viewer['xsrft'], | |
737 | }), headers={ | |
738 | 'X-Requested-With': 'XMLHttpRequest', | |
739 | }) | |
740 | except ExtractorError as e: | |
741 | if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: | |
742 | raise ExtractorError('Wrong password', expected=True) | |
743 | raise | |
744 | ||
a0088bdf | 745 | def _real_extract(self, url): |
5dbe81a1 | 746 | url, data = unsmuggle_url(url, {}) |
0f56a4b4 | 747 | headers = std_headers.copy() |
5dbe81a1 | 748 | if 'http_headers' in data: |
5dbe81a1 | 749 | headers.update(data['http_headers']) |
ba5d51b3 PH |
750 | if 'Referer' not in headers: |
751 | headers['Referer'] = url | |
9d4660ca | 752 | |
b3d14cbf | 753 | # Extract ID from URL |
2a6f8475 | 754 | mobj = self._match_valid_url(url).groupdict() |
755 | video_id, unlisted_hash = mobj['id'], mobj.get('unlisted_hash') | |
cce889b9 | 756 | if unlisted_hash: |
58ab5cbc | 757 | return self._extract_from_api(video_id, unlisted_hash) |
cce889b9 | 758 | |
58ea7ec8 | 759 | orig_url = url |
681ac7c9 | 760 | is_pro = 'vimeopro.com/' in url |
681ac7c9 | 761 | if is_pro: |
06242d44 | 762 | # some videos require portfolio_id to be present in player url |
067aa17e | 763 | # https://github.com/ytdl-org/youtube-dl/issues/20070 |
06242d44 | 764 | url = self._extract_url(url, self._download_webpage(url, video_id)) |
681ac7c9 RA |
765 | if not url: |
766 | url = 'https://vimeo.com/' + video_id | |
40b6495d | 767 | elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')): |
10831b5e | 768 | url = 'https://vimeo.com/' + video_id |
b3d14cbf | 769 | |
1f52a09e | 770 | self._try_album_password(url) |
1060425c | 771 | try: |
681ac7c9 RA |
772 | # Retrieve video webpage to extract further information |
773 | webpage, urlh = self._download_webpage_handle( | |
774 | url, video_id, headers=headers) | |
7947a1f7 | 775 | redirect_url = urlh.geturl() |
1060425c PH |
776 | except ExtractorError as ee: |
777 | if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403: | |
778 | errmsg = ee.cause.read() | |
779 | if b'Because of its privacy settings, this video cannot be played here' in errmsg: | |
780 | raise ExtractorError( | |
781 | 'Cannot download embed-only video without embedding ' | |
7a5c1cfe | 782 | 'URL. Please call yt-dlp with the URL of the page ' |
1060425c PH |
783 | 'that embeds this video.', |
784 | expected=True) | |
785 | raise | |
b3d14cbf | 786 | |
58ab5cbc | 787 | if '://player.vimeo.com/video/' in url: |
788 | config = self._parse_json(self._search_regex( | |
789 | r'\bconfig\s*=\s*({.+?})\s*;', webpage, 'info section'), video_id) | |
790 | if config.get('view') == 4: | |
791 | config = self._verify_player_video_password( | |
792 | redirect_url, video_id, headers) | |
793 | info = self._parse_config(config, video_id) | |
794 | self._vimeo_sort_formats(info['formats']) | |
795 | return info | |
796 | ||
797 | if re.search(r'<form[^>]+?id="pw_form"', webpage): | |
798 | video_password = self._get_video_password() | |
799 | token, vuid = self._extract_xsrft_and_vuid(webpage) | |
800 | webpage = self._verify_video_password( | |
801 | redirect_url, video_id, video_password, token, vuid) | |
b3d14cbf | 802 | |
eb9c9c74 | 803 | vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None) |
998e6cdb | 804 | if vimeo_config: |
58ab5cbc | 805 | seed_status = vimeo_config.get('seed_status') or {} |
998e6cdb S |
806 | if seed_status.get('state') == 'failed': |
807 | raise ExtractorError( | |
b6aa99af | 808 | '%s said: %s' % (self.IE_NAME, seed_status['title']), |
998e6cdb S |
809 | expected=True) |
810 | ||
c38a67bc | 811 | cc_license = None |
c15cd296 | 812 | timestamp = None |
681ac7c9 | 813 | video_description = None |
58ab5cbc | 814 | info_dict = {} |
1ee34c76 | 815 | config_url = None |
c38a67bc | 816 | |
58ab5cbc | 817 | channel_id = self._search_regex( |
818 | r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None) | |
819 | if channel_id: | |
820 | config_url = self._html_search_regex( | |
1ee34c76 | 821 | r'\bdata-config-url="([^"]+)"', webpage, 'config URL', default=None) |
58ab5cbc | 822 | video_description = clean_html(get_element_by_class('description', webpage)) |
823 | info_dict.update({ | |
824 | 'channel_id': channel_id, | |
825 | 'channel_url': 'https://vimeo.com/channels/' + channel_id, | |
826 | }) | |
1ee34c76 | 827 | if not config_url: |
58ab5cbc | 828 | page_config = self._parse_json(self._search_regex( |
829 | r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});', | |
830 | webpage, 'page config', default='{}'), video_id, fatal=False) | |
831 | if not page_config: | |
832 | return self._extract_from_api(video_id) | |
833 | config_url = page_config['player']['config_url'] | |
834 | cc_license = page_config.get('cc_license') | |
835 | clip = page_config.get('clip') or {} | |
836 | timestamp = clip.get('uploaded_on') | |
837 | video_description = clean_html( | |
838 | clip.get('description') or page_config.get('description_html_escaped')) | |
839 | config = self._download_json(config_url, video_id) | |
bc2ca1bb | 840 | video = config.get('video') or {} |
841 | vod = video.get('vod') or {} | |
8b40c927 | 842 | |
6a55bb66 S |
843 | def is_rented(): |
844 | if '>You rented this title.<' in webpage: | |
845 | return True | |
58ab5cbc | 846 | if try_get(config, lambda x: x['user']['purchased']): |
6a55bb66 | 847 | return True |
58ab5cbc | 848 | for purchase_option in (vod.get('purchase_options') or []): |
8b40c927 RA |
849 | if purchase_option.get('purchased'): |
850 | return True | |
851 | label = purchase_option.get('label_string') | |
852 | if label and (label.startswith('You rented this') or label.endswith(' remaining')): | |
853 | return True | |
6a55bb66 S |
854 | return False |
855 | ||
8b40c927 RA |
856 | if is_rented() and vod.get('is_trailer'): |
857 | feature_id = vod.get('feature_id') | |
5dbe81a1 S |
858 | if feature_id and not data.get('force_feature_id', False): |
859 | return self.url_result(smuggle_url( | |
860 | 'https://player.vimeo.com/player/%s' % feature_id, | |
861 | {'force_feature_id': True}), 'Vimeo') | |
862 | ||
681ac7c9 RA |
863 | if not video_description: |
864 | video_description = self._html_search_regex( | |
865 | r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>', | |
866 | webpage, 'description', default=None) | |
58ea7ec8 PH |
867 | if not video_description: |
868 | video_description = self._html_search_meta( | |
58ab5cbc | 869 | ['description', 'og:description', 'twitter:description'], |
870 | webpage, default=None) | |
681ac7c9 | 871 | if not video_description and is_pro: |
58ea7ec8 PH |
872 | orig_webpage = self._download_webpage( |
873 | orig_url, video_id, | |
874 | note='Downloading webpage for description', | |
875 | fatal=False) | |
876 | if orig_webpage: | |
877 | video_description = self._html_search_meta( | |
878 | 'description', orig_webpage, default=None) | |
58ab5cbc | 879 | if not video_description: |
6a39ee13 | 880 | self.report_warning('Cannot find video description') |
b3d14cbf | 881 | |
c15cd296 S |
882 | if not timestamp: |
883 | timestamp = self._search_regex( | |
884 | r'<time[^>]+datetime="([^"]+)"', webpage, | |
885 | 'timestamp', default=None) | |
b3d14cbf | 886 | |
58ab5cbc | 887 | view_count = int_or_none(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count', default=None)) |
888 | like_count = int_or_none(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count', default=None)) | |
889 | comment_count = int_or_none(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count', default=None)) | |
4e761794 | 890 | |
a6387bfd | 891 | formats = [] |
27655037 RA |
892 | |
893 | source_format = self._extract_original_format( | |
bc2ca1bb | 894 | 'https://vimeo.com/' + video_id, video_id, video.get('unlisted_hash')) |
27655037 RA |
895 | if source_format: |
896 | formats.append(source_format) | |
1eac553e | 897 | |
ae1c585c S |
898 | info_dict_config = self._parse_config(config, video_id) |
899 | formats.extend(info_dict_config['formats']) | |
531a7496 | 900 | self._vimeo_sort_formats(formats) |
c38a67bc | 901 | |
ae1c585c S |
902 | json_ld = self._search_json_ld(webpage, video_id, default={}) |
903 | ||
c38a67bc S |
904 | if not cc_license: |
905 | cc_license = self._search_regex( | |
906 | r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1', | |
907 | webpage, 'license', default=None, group='license') | |
908 | ||
58ab5cbc | 909 | info_dict.update({ |
531a7496 | 910 | 'formats': formats, |
c15cd296 | 911 | 'timestamp': unified_timestamp(timestamp), |
b0268cb6 | 912 | 'description': video_description, |
9103bbc5 | 913 | 'webpage_url': url, |
4e761794 JMF |
914 | 'view_count': view_count, |
915 | 'like_count': like_count, | |
916 | 'comment_count': comment_count, | |
c38a67bc | 917 | 'license': cc_license, |
58ab5cbc | 918 | }) |
531a7496 | 919 | |
58ab5cbc | 920 | return merge_dicts(info_dict, info_dict_config, json_ld) |
caeefc29 JMF |
921 | |
922 | ||
681ac7c9 | 923 | class VimeoOndemandIE(VimeoIE): |
1e501364 | 924 | IE_NAME = 'vimeo:ondemand' |
58ab5cbc | 925 | _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?:[^/]+/)?(?P<id>[^/?#&]+)' |
74278def S |
926 | _TESTS = [{ |
927 | # ondemand video not available via https://vimeo.com/id | |
928 | 'url': 'https://vimeo.com/ondemand/20704', | |
929 | 'md5': 'c424deda8c7f73c1dfb3edd7630e2f35', | |
930 | 'info_dict': { | |
931 | 'id': '105442900', | |
932 | 'ext': 'mp4', | |
933 | 'title': 'המעבדה - במאי יותם פלדמן', | |
934 | 'uploader': 'גם סרטים', | |
ec85ded8 | 935 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms', |
74278def | 936 | 'uploader_id': 'gumfilms', |
681ac7c9 RA |
937 | 'description': 'md5:4c027c965e439de4baab621e48b60791', |
938 | 'upload_date': '20140906', | |
939 | 'timestamp': 1410032453, | |
74278def | 940 | }, |
1fd0fc42 S |
941 | 'params': { |
942 | 'format': 'best[protocol=https]', | |
943 | }, | |
681ac7c9 | 944 | 'expected_warnings': ['Unable to download JSON metadata'], |
d002e919 S |
945 | }, { |
946 | # requires Referer to be passed along with og:video:url | |
947 | 'url': 'https://vimeo.com/ondemand/36938/126682985', | |
948 | 'info_dict': { | |
681ac7c9 | 949 | 'id': '126584684', |
d002e919 S |
950 | 'ext': 'mp4', |
951 | 'title': 'Rävlock, rätt läte på rätt plats', | |
952 | 'uploader': 'Lindroth & Norin', | |
681ac7c9 RA |
953 | 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin', |
954 | 'uploader_id': 'lindrothnorin', | |
955 | 'description': 'md5:c3c46a90529612c8279fb6af803fc0df', | |
956 | 'upload_date': '20150502', | |
957 | 'timestamp': 1430586422, | |
d002e919 S |
958 | }, |
959 | 'params': { | |
960 | 'skip_download': True, | |
961 | }, | |
681ac7c9 | 962 | 'expected_warnings': ['Unable to download JSON metadata'], |
74278def S |
963 | }, { |
964 | 'url': 'https://vimeo.com/ondemand/nazmaalik', | |
965 | 'only_matching': True, | |
966 | }, { | |
967 | 'url': 'https://vimeo.com/ondemand/141692381', | |
968 | 'only_matching': True, | |
969 | }, { | |
970 | 'url': 'https://vimeo.com/ondemand/thelastcolony/150274832', | |
971 | 'only_matching': True, | |
972 | }] | |
973 | ||
74278def | 974 | |
f6c3664d | 975 | class VimeoChannelIE(VimeoBaseInfoExtractor): |
9148eb00 | 976 | IE_NAME = 'vimeo:channel' |
3946864c | 977 | _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])' |
caeefc29 | 978 | _MORE_PAGES_INDICATOR = r'<a.+?rel="next"' |
84458766 | 979 | _TITLE = None |
55a10eab | 980 | _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"' |
2929b3e7 | 981 | _TESTS = [{ |
3946864c | 982 | 'url': 'https://vimeo.com/channels/tributes', |
2929b3e7 | 983 | 'info_dict': { |
a3fa5da4 | 984 | 'id': 'tributes', |
2929b3e7 PH |
985 | 'title': 'Vimeo Tributes', |
986 | }, | |
987 | 'playlist_mincount': 25, | |
988 | }] | |
681ac7c9 | 989 | _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s' |
caeefc29 | 990 | |
5cc14c2f JMF |
991 | def _page_url(self, base_url, pagenum): |
992 | return '%s/videos/page:%d/' % (base_url, pagenum) | |
993 | ||
fb30ec22 | 994 | def _extract_list_title(self, webpage): |
2605043d S |
995 | return self._TITLE or self._html_search_regex( |
996 | self._TITLE_RE, webpage, 'list title', fatal=False) | |
fb30ec22 | 997 | |
2c94198e | 998 | def _title_and_entries(self, list_id, base_url): |
caeefc29 | 999 | for pagenum in itertools.count(1): |
bf8f082a | 1000 | page_url = self._page_url(base_url, pagenum) |
55a10eab | 1001 | webpage = self._download_webpage( |
bf8f082a | 1002 | page_url, list_id, |
9148eb00 | 1003 | 'Downloading page %s' % pagenum) |
bf8f082a PH |
1004 | |
1005 | if pagenum == 1: | |
2c94198e S |
1006 | yield self._extract_list_title(webpage) |
1007 | ||
c8e3e097 S |
1008 | # Try extracting href first since not all videos are available via |
1009 | # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729) | |
1010 | clips = re.findall( | |
04a3d4d2 | 1011 | r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage) |
c8e3e097 | 1012 | if clips: |
04a3d4d2 | 1013 | for video_id, video_url, video_title in clips: |
c8e3e097 S |
1014 | yield self.url_result( |
1015 | compat_urlparse.urljoin(base_url, video_url), | |
04a3d4d2 | 1016 | VimeoIE.ie_key(), video_id=video_id, video_title=video_title) |
c8e3e097 S |
1017 | # More relaxed fallback |
1018 | else: | |
1019 | for video_id in re.findall(r'id=["\']clip_(\d+)', webpage): | |
1020 | yield self.url_result( | |
1021 | 'https://vimeo.com/%s' % video_id, | |
1022 | VimeoIE.ie_key(), video_id=video_id) | |
bf8f082a | 1023 | |
caeefc29 JMF |
1024 | if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None: |
1025 | break | |
1026 | ||
2c94198e S |
1027 | def _extract_videos(self, list_id, base_url): |
1028 | title_and_entries = self._title_and_entries(list_id, base_url) | |
1029 | list_title = next(title_and_entries) | |
1030 | return self.playlist_result(title_and_entries, list_id, list_title) | |
55a10eab JMF |
1031 | |
1032 | def _real_extract(self, url): | |
681ac7c9 RA |
1033 | channel_id = self._match_id(url) |
1034 | return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id) | |
55a10eab JMF |
1035 | |
1036 | ||
1037 | class VimeoUserIE(VimeoChannelIE): | |
9148eb00 | 1038 | IE_NAME = 'vimeo:user' |
681ac7c9 | 1039 | _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos|[#?]|$)' |
55a10eab | 1040 | _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>' |
2929b3e7 | 1041 | _TESTS = [{ |
3946864c | 1042 | 'url': 'https://vimeo.com/nkistudio/videos', |
2929b3e7 PH |
1043 | 'info_dict': { |
1044 | 'title': 'Nki', | |
a3fa5da4 | 1045 | 'id': 'nkistudio', |
2929b3e7 PH |
1046 | }, |
1047 | 'playlist_mincount': 66, | |
1048 | }] | |
681ac7c9 | 1049 | _BASE_URL_TEMPL = 'https://vimeo.com/%s' |
5cc14c2f JMF |
1050 | |
1051 | ||
51c7f40c | 1052 | class VimeoAlbumIE(VimeoBaseInfoExtractor): |
9148eb00 | 1053 | IE_NAME = 'vimeo:album' |
eb9c9c74 | 1054 | _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))' |
5cc14c2f | 1055 | _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>' |
2929b3e7 | 1056 | _TESTS = [{ |
d1508cd6 | 1057 | 'url': 'https://vimeo.com/album/2632481', |
2929b3e7 | 1058 | 'info_dict': { |
a3fa5da4 | 1059 | 'id': '2632481', |
2929b3e7 PH |
1060 | 'title': 'Staff Favorites: November 2013', |
1061 | }, | |
1062 | 'playlist_mincount': 13, | |
bf8f082a PH |
1063 | }, { |
1064 | 'note': 'Password-protected album', | |
1065 | 'url': 'https://vimeo.com/album/3253534', | |
1066 | 'info_dict': { | |
1067 | 'title': 'test', | |
1068 | 'id': '3253534', | |
1069 | }, | |
1070 | 'playlist_count': 1, | |
1071 | 'params': { | |
3867038a | 1072 | 'videopassword': 'youtube-dl', |
bf8f082a | 1073 | } |
2929b3e7 | 1074 | }] |
eb9c9c74 RA |
1075 | _PAGE_SIZE = 100 |
1076 | ||
a0566bbf | 1077 | def _fetch_page(self, album_id, authorization, hashed_pass, page): |
eb9c9c74 RA |
1078 | api_page = page + 1 |
1079 | query = { | |
974311b5 | 1080 | 'fields': 'link,uri', |
eb9c9c74 RA |
1081 | 'page': api_page, |
1082 | 'per_page': self._PAGE_SIZE, | |
1083 | } | |
1084 | if hashed_pass: | |
1085 | query['_hashed_pass'] = hashed_pass | |
421a4595 | 1086 | try: |
1087 | videos = self._download_json( | |
1088 | 'https://api.vimeo.com/albums/%s/videos' % album_id, | |
1089 | album_id, 'Downloading page %d' % api_page, query=query, headers={ | |
1090 | 'Authorization': 'jwt ' + authorization, | |
1091 | })['data'] | |
1092 | except ExtractorError as e: | |
1093 | if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400: | |
1094 | return | |
eb9c9c74 RA |
1095 | for video in videos: |
1096 | link = video.get('link') | |
1097 | if not link: | |
1098 | continue | |
974311b5 RA |
1099 | uri = video.get('uri') |
1100 | video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None | |
1101 | yield self.url_result(link, VimeoIE.ie_key(), video_id) | |
5cc14c2f JMF |
1102 | |
1103 | def _real_extract(self, url): | |
bf8f082a | 1104 | album_id = self._match_id(url) |
8bdd16b4 | 1105 | viewer = self._download_json( |
1106 | 'https://vimeo.com/_rv/viewer', album_id, fatal=False) | |
1107 | if not viewer: | |
1108 | webpage = self._download_webpage(url, album_id) | |
1109 | viewer = self._parse_json(self._search_regex( | |
1110 | r'bootstrap_data\s*=\s*({.+?})</script>', | |
1111 | webpage, 'bootstrap data'), album_id)['viewer'] | |
51c7f40c RA |
1112 | jwt = viewer['jwt'] |
1113 | album = self._download_json( | |
1114 | 'https://api.vimeo.com/albums/' + album_id, | |
1115 | album_id, headers={'Authorization': 'jwt ' + jwt}, | |
1116 | query={'fields': 'description,name,privacy'}) | |
1117 | hashed_pass = None | |
1118 | if try_get(album, lambda x: x['privacy']['view']) == 'password': | |
a06916d9 | 1119 | password = self.get_param('videopassword') |
51c7f40c RA |
1120 | if not password: |
1121 | raise ExtractorError( | |
1122 | 'This album is protected by a password, use the --video-password option', | |
1123 | expected=True) | |
1124 | self._set_vimeo_cookie('vuid', viewer['vuid']) | |
1125 | try: | |
1126 | hashed_pass = self._download_json( | |
1127 | 'https://vimeo.com/showcase/%s/auth' % album_id, | |
1128 | album_id, 'Verifying the password', data=urlencode_postdata({ | |
1129 | 'password': password, | |
1130 | 'token': viewer['xsrft'], | |
1131 | }), headers={ | |
1132 | 'X-Requested-With': 'XMLHttpRequest', | |
1133 | })['hashed_pass'] | |
1134 | except ExtractorError as e: | |
1135 | if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: | |
1136 | raise ExtractorError('Wrong password', expected=True) | |
1137 | raise | |
eb9c9c74 | 1138 | entries = OnDemandPagedList(functools.partial( |
51c7f40c RA |
1139 | self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE) |
1140 | return self.playlist_result( | |
1141 | entries, album_id, album.get('name'), album.get('description')) | |
fb30ec22 JMF |
1142 | |
1143 | ||
681ac7c9 | 1144 | class VimeoGroupsIE(VimeoChannelIE): |
9148eb00 | 1145 | IE_NAME = 'vimeo:group' |
681ac7c9 | 1146 | _VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)' |
2929b3e7 | 1147 | _TESTS = [{ |
9cb070f9 | 1148 | 'url': 'https://vimeo.com/groups/meetup', |
2929b3e7 | 1149 | 'info_dict': { |
9cb070f9 | 1150 | 'id': 'meetup', |
1151 | 'title': 'Vimeo Meetup!', | |
2929b3e7 | 1152 | }, |
681ac7c9 | 1153 | 'playlist_mincount': 27, |
2929b3e7 | 1154 | }] |
681ac7c9 | 1155 | _BASE_URL_TEMPL = 'https://vimeo.com/groups/%s' |
fcea44c6 PH |
1156 | |
1157 | ||
531a7496 | 1158 | class VimeoReviewIE(VimeoBaseInfoExtractor): |
9148eb00 PH |
1159 | IE_NAME = 'vimeo:review' |
1160 | IE_DESC = 'Review pages on vimeo' | |
27655037 | 1161 | _VALID_URL = r'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})' |
d36d3f42 | 1162 | _TESTS = [{ |
fcea44c6 | 1163 | 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d', |
fcea44c6 PH |
1164 | 'md5': 'c507a72f780cacc12b2248bb4006d253', |
1165 | 'info_dict': { | |
fc09240e PH |
1166 | 'id': '75524534', |
1167 | 'ext': 'mp4', | |
fcea44c6 PH |
1168 | 'title': "DICK HARDWICK 'Comedian'", |
1169 | 'uploader': 'Richard Hardwick', | |
531a7496 | 1170 | 'uploader_id': 'user21297594', |
681ac7c9 RA |
1171 | 'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks", |
1172 | }, | |
d36d3f42 PH |
1173 | }, { |
1174 | 'note': 'video player needs Referer', | |
3946864c | 1175 | 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053', |
d36d3f42 PH |
1176 | 'md5': '6295fdab8f4bf6a002d058b2c6dce276', |
1177 | 'info_dict': { | |
1178 | 'id': '91613211', | |
1179 | 'ext': 'mp4', | |
9dec9930 | 1180 | 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn', |
d36d3f42 PH |
1181 | 'uploader': 'DevWeek Events', |
1182 | 'duration': 2773, | |
ec85ded8 | 1183 | 'thumbnail': r're:^https?://.*\.jpg$', |
531a7496 | 1184 | 'uploader_id': 'user22258446', |
681ac7c9 RA |
1185 | }, |
1186 | 'skip': 'video gone', | |
c1ff6e1a YCH |
1187 | }, { |
1188 | 'note': 'Password protected', | |
1189 | 'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde', | |
1190 | 'info_dict': { | |
1191 | 'id': '138823582', | |
1192 | 'ext': 'mp4', | |
1193 | 'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1', | |
1194 | 'uploader': 'TMB', | |
1195 | 'uploader_id': 'user37284429', | |
1196 | }, | |
1197 | 'params': { | |
1198 | 'videopassword': 'holygrail', | |
1199 | }, | |
a093cfc7 | 1200 | 'skip': 'video gone', |
d36d3f42 | 1201 | }] |
fcea44c6 | 1202 | |
c1ff6e1a YCH |
1203 | def _real_initialize(self): |
1204 | self._login() | |
1205 | ||
fcea44c6 | 1206 | def _real_extract(self, url): |
5ad28e7f | 1207 | page_url, video_id = self._match_valid_url(url).groups() |
cce889b9 | 1208 | data = self._download_json( |
1209 | page_url.replace('/review/', '/review/data/'), video_id) | |
1210 | if data.get('isLocked') is True: | |
1211 | video_password = self._get_video_password() | |
1212 | viewer = self._download_json( | |
1213 | 'https://vimeo.com/_rv/viewer', video_id) | |
1214 | webpage = self._verify_video_password( | |
1215 | 'https://vimeo.com/' + video_id, video_id, | |
1216 | video_password, viewer['xsrft'], viewer['vuid']) | |
1217 | clip_page_config = self._parse_json(self._search_regex( | |
1218 | r'window\.vimeo\.clip_page_config\s*=\s*({.+?});', | |
1219 | webpage, 'clip page config'), video_id) | |
1220 | config_url = clip_page_config['player']['config_url'] | |
1221 | clip_data = clip_page_config.get('clip') or {} | |
1222 | else: | |
1223 | clip_data = data['clipData'] | |
1224 | config_url = clip_data['configUrl'] | |
c1ff6e1a | 1225 | config = self._download_json(config_url, video_id) |
531a7496 | 1226 | info_dict = self._parse_config(config, video_id) |
681ac7c9 RA |
1227 | source_format = self._extract_original_format( |
1228 | page_url + '/action', video_id) | |
27655037 RA |
1229 | if source_format: |
1230 | info_dict['formats'].append(source_format) | |
531a7496 | 1231 | self._vimeo_sort_formats(info_dict['formats']) |
681ac7c9 | 1232 | info_dict['description'] = clean_html(clip_data.get('description')) |
531a7496 | 1233 | return info_dict |
efb7e119 JMF |
1234 | |
1235 | ||
f6c3664d | 1236 | class VimeoWatchLaterIE(VimeoChannelIE): |
efb7e119 JMF |
1237 | IE_NAME = 'vimeo:watchlater' |
1238 | IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)' | |
84458766 S |
1239 | _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater' |
1240 | _TITLE = 'Watch Later' | |
efb7e119 | 1241 | _LOGIN_REQUIRED = True |
2929b3e7 | 1242 | _TESTS = [{ |
84458766 | 1243 | 'url': 'https://vimeo.com/watchlater', |
2929b3e7 PH |
1244 | 'only_matching': True, |
1245 | }] | |
efb7e119 JMF |
1246 | |
1247 | def _real_initialize(self): | |
1248 | self._login() | |
1249 | ||
1250 | def _page_url(self, base_url, pagenum): | |
1251 | url = '%s/page:%d/' % (base_url, pagenum) | |
67dda517 | 1252 | request = sanitized_Request(url) |
efb7e119 JMF |
1253 | # Set the header to get a partial html page with the ids, |
1254 | # the normal page doesn't contain them. | |
1255 | request.add_header('X-Requested-With', 'XMLHttpRequest') | |
1256 | return request | |
1257 | ||
1258 | def _real_extract(self, url): | |
84458766 | 1259 | return self._extract_videos('watchlater', 'https://vimeo.com/watchlater') |
d6e6a422 PH |
1260 | |
1261 | ||
091c9b43 | 1262 | class VimeoLikesIE(VimeoChannelIE): |
361a965b | 1263 | _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)' |
d6e6a422 PH |
1264 | IE_NAME = 'vimeo:likes' |
1265 | IE_DESC = 'Vimeo user likes' | |
361a965b | 1266 | _TESTS = [{ |
9c44d242 PH |
1267 | 'url': 'https://vimeo.com/user755559/likes/', |
1268 | 'playlist_mincount': 293, | |
611c1dd9 | 1269 | 'info_dict': { |
091c9b43 S |
1270 | 'id': 'user755559', |
1271 | 'title': 'urza’s Likes', | |
d6e6a422 | 1272 | }, |
361a965b S |
1273 | }, { |
1274 | 'url': 'https://vimeo.com/stormlapse/likes', | |
1275 | 'only_matching': True, | |
1276 | }] | |
d6e6a422 | 1277 | |
091c9b43 S |
1278 | def _page_url(self, base_url, pagenum): |
1279 | return '%s/page:%d/' % (base_url, pagenum) | |
1280 | ||
d6e6a422 PH |
1281 | def _real_extract(self, url): |
1282 | user_id = self._match_id(url) | |
091c9b43 | 1283 | return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id) |
ca01d178 RA |
1284 | |
1285 | ||
a1ee23e9 | 1286 | class VHXEmbedIE(VimeoBaseInfoExtractor): |
ca01d178 RA |
1287 | IE_NAME = 'vhx:embed' |
1288 | _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)' | |
1289 | ||
29f7c58a | 1290 | @staticmethod |
1291 | def _extract_url(webpage): | |
1292 | mobj = re.search( | |
1293 | r'<iframe[^>]+src="(https?://embed\.vhx\.tv/videos/\d+[^"]*)"', webpage) | |
1294 | return unescapeHTML(mobj.group(1)) if mobj else None | |
1295 | ||
ca01d178 RA |
1296 | def _real_extract(self, url): |
1297 | video_id = self._match_id(url) | |
1298 | webpage = self._download_webpage(url, video_id) | |
a1ee23e9 RA |
1299 | config_url = self._parse_json(self._search_regex( |
1300 | r'window\.OTTData\s*=\s*({.+})', webpage, | |
1301 | 'ott data'), video_id, js_to_json)['config_url'] | |
1302 | config = self._download_json(config_url, video_id) | |
1303 | info = self._parse_config(config, video_id) | |
29f7c58a | 1304 | info['id'] = video_id |
a1ee23e9 RA |
1305 | self._vimeo_sort_formats(info['formats']) |
1306 | return info |