2 from __future__ import unicode_literals
8 from .common import InfoExtractor
32 class VimeoBaseInfoExtractor(InfoExtractor):
33 _NETRC_MACHINE = 'vimeo'
34 _LOGIN_REQUIRED = False
35 _LOGIN_URL = 'https://vimeo.com/log_in'
38 (username, password) = self._get_login_info()
40 if self._LOGIN_REQUIRED:
41 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
44 webpage = self._download_webpage(self._LOGIN_URL, None, False)
45 token, vuid = self._extract_xsrft_and_vuid(webpage)
46 data = urlencode_postdata({
53 login_request = sanitized_Request(self._LOGIN_URL, data)
54 login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
55 login_request.add_header('Referer', self._LOGIN_URL)
56 self._set_vimeo_cookie('vuid', vuid)
57 self._download_webpage(login_request, None, False, 'Wrong login info')
59 def _extract_xsrft_and_vuid(self, webpage):
60 xsrft = self._search_regex(
61 r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
62 webpage, 'login token', group='xsrft')
63 vuid = self._search_regex(
64 r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
65 webpage, 'vuid', group='vuid')
68 def _set_vimeo_cookie(self, name, value):
69 self._set_cookie('vimeo.com', name, value)
71 def _vimeo_sort_formats(self, formats):
72 # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
73 # at the same time without actual units specified. This lead to wrong sorting.
74 self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'format_id'))
76 def _parse_config(self, config, video_id):
78 video_title = config['video']['title']
80 # Extract uploader, uploader_url and uploader_id
81 video_uploader = config['video'].get('owner', {}).get('name')
82 video_uploader_url = config['video'].get('owner', {}).get('url')
83 video_uploader_id = video_uploader_url.split('/')[-1] if video_uploader_url else None
85 # Extract video thumbnail
86 video_thumbnail = config['video'].get('thumbnail')
87 if video_thumbnail is None:
88 video_thumbs = config['video'].get('thumbs')
89 if video_thumbs and isinstance(video_thumbs, dict):
90 _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
92 # Extract video duration
93 video_duration = int_or_none(config['video'].get('duration'))
96 config_files = config['video'].get('files') or config['request'].get('files', {})
97 for f in config_files.get('progressive', []):
98 video_url = f.get('url')
103 'format_id': 'http-%s' % f.get('quality'),
104 'width': int_or_none(f.get('width')),
105 'height': int_or_none(f.get('height')),
106 'fps': int_or_none(f.get('fps')),
107 'tbr': int_or_none(f.get('bitrate')),
109 m3u8_url = config_files.get('hls', {}).get('url')
111 formats.extend(self._extract_m3u8_formats(
112 m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
115 text_tracks = config['request'].get('text_tracks')
117 for tt in text_tracks:
118 subtitles[tt['lang']] = [{
120 'url': 'https://vimeo.com' + tt['url'],
124 'title': video_title,
125 'uploader': video_uploader,
126 'uploader_id': video_uploader_id,
127 'uploader_url': video_uploader_url,
128 'thumbnail': video_thumbnail,
129 'duration': video_duration,
131 'subtitles': subtitles,
135 class VimeoIE(VimeoBaseInfoExtractor):
136 """Information extractor for vimeo.com."""
138 # _VALID_URL matches Vimeo URLs
139 _VALID_URL = r'''(?x)
148 vimeo(?P<pro>pro)?\.com/
149 (?!(?:channels|album)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
154 moogaloop\.swf)\?clip_id=
159 /?(?:[?&].*)?(?:[#].*)?$
164 'url': 'http://vimeo.com/56015672#at=0',
165 'md5': '8879b6cc097e987f02484baf890129e5',
169 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
170 'description': 'md5:2d3305bad981a06ff79f027f19865021',
171 'upload_date': '20121220',
172 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user7108434',
173 'uploader_id': 'user7108434',
174 'uploader': 'Filippo Valsorda',
179 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
180 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
181 'note': 'Vimeo Pro video (#1197)',
185 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
186 'uploader_id': 'openstreetmapus',
187 'uploader': 'OpenStreetMap US',
188 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
189 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30',
194 'url': 'http://player.vimeo.com/video/54469442',
195 'md5': '619b811a4417aa4abe78dc653becf511',
196 'note': 'Videos that embed the url in the player page',
200 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
201 'uploader': 'The BLN & Business of Software',
202 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware',
203 'uploader_id': 'theblnbusinessofsoftware',
209 'url': 'http://vimeo.com/68375962',
210 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
211 'note': 'Video protected with password',
215 'title': 'youtube-dl password protected test video',
216 'upload_date': '20130614',
217 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user18948128',
218 'uploader_id': 'user18948128',
219 'uploader': 'Jaime Marquínez Ferrándiz',
221 'description': 'This is "youtube-dl password protected test video" by on Vimeo, the home for high quality videos and the people who love them.',
224 'videopassword': 'youtube-dl',
228 'url': 'http://vimeo.com/channels/keypeele/75629013',
229 'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
233 'title': 'Key & Peele: Terrorist Interrogation',
234 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
235 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/atencio',
236 'uploader_id': 'atencio',
237 'uploader': 'Peter Atencio',
238 'upload_date': '20130927',
243 'url': 'http://vimeo.com/76979871',
244 'note': 'Video with subtitles',
248 'title': 'The New Vimeo Player (You Know, For Videos)',
249 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
250 'upload_date': '20131015',
251 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/staff',
252 'uploader_id': 'staff',
253 'uploader': 'Vimeo Staff',
258 # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
259 'url': 'https://player.vimeo.com/video/98044508',
260 'note': 'The js code contains assignments to the same variable as the config',
264 'title': 'Pier Solar OUYA Official Trailer',
265 'uploader': 'Tulio Gonçalves',
266 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user28849593',
267 'uploader_id': 'user28849593',
271 # contains original format
272 'url': 'https://vimeo.com/33951933',
273 'md5': '2d9f5475e0537f013d0073e812ab89e6',
277 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
278 'uploader': 'The DMCI',
279 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/dmci',
280 'uploader_id': 'dmci',
281 'upload_date': '20111220',
282 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
286 # only available via https://vimeo.com/channels/tributes/6213729 and
287 # not via https://vimeo.com/6213729
288 'url': 'https://vimeo.com/channels/tributes/6213729',
292 'title': 'Vimeo Tribute: The Shining',
293 'uploader': 'Casey Donahue',
294 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/caseydonahue',
295 'uploader_id': 'caseydonahue',
296 'upload_date': '20090821',
297 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
300 'skip_download': True,
302 'expected_warnings': ['Unable to download JSON metadata'],
305 'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
306 'only_matching': True,
309 'url': 'https://vimeo.com/109815029',
310 'note': 'Video not completely processed, "failed" seed status',
311 'only_matching': True,
314 'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
315 'only_matching': True,
318 'url': 'https://vimeo.com/album/2632481/video/79010983',
319 'only_matching': True,
322 # source file returns 403: Forbidden
323 'url': 'https://vimeo.com/7809605',
324 'only_matching': True,
327 'url': 'https://vimeo.com/160743502/abd0e13fb4',
328 'only_matching': True,
333 def _extract_vimeo_url(url, webpage):
334 # Look for embedded (iframe) Vimeo player
336 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
338 player_url = unescapeHTML(mobj.group('url'))
339 surl = smuggle_url(player_url, {'http_headers': {'Referer': url}})
341 # Look for embedded (swf embed) Vimeo player
343 r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
347 def _verify_video_password(self, url, video_id, webpage):
348 password = self._downloader.params.get('videopassword')
350 raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
351 token, vuid = self._extract_xsrft_and_vuid(webpage)
352 data = urlencode_postdata({
353 'password': password,
356 if url.startswith('http://'):
357 # vimeo only supports https now, but the user can give an http url
358 url = url.replace('http://', 'https://')
359 password_request = sanitized_Request(url + '/password', data)
360 password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
361 password_request.add_header('Referer', url)
362 self._set_vimeo_cookie('vuid', vuid)
363 return self._download_webpage(
364 password_request, video_id,
365 'Verifying the password', 'Wrong password')
367 def _verify_player_video_password(self, url, video_id):
368 password = self._downloader.params.get('videopassword')
370 raise ExtractorError('This video is protected by a password, use the --video-password option')
371 data = urlencode_postdata({'password': password})
372 pass_url = url + '/check-password'
373 password_request = sanitized_Request(pass_url, data)
374 password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
375 password_request.add_header('Referer', url)
376 return self._download_json(
377 password_request, video_id,
378 'Verifying the password', 'Wrong password')
380 def _real_initialize(self):
383 def _real_extract(self, url):
384 url, data = unsmuggle_url(url, {})
385 headers = std_headers.copy()
386 if 'http_headers' in data:
387 headers.update(data['http_headers'])
388 if 'Referer' not in headers:
389 headers['Referer'] = url
391 # Extract ID from URL
392 mobj = re.match(self._VALID_URL, url)
393 video_id = mobj.group('id')
395 if mobj.group('pro') or mobj.group('player'):
396 url = 'https://player.vimeo.com/video/' + video_id
397 elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
398 url = 'https://vimeo.com/' + video_id
400 # Retrieve video webpage to extract further information
401 request = sanitized_Request(url, headers=headers)
403 webpage = self._download_webpage(request, video_id)
404 except ExtractorError as ee:
405 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
406 errmsg = ee.cause.read()
407 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
408 raise ExtractorError(
409 'Cannot download embed-only video without embedding '
410 'URL. Please call youtube-dl with the URL of the page '
411 'that embeds this video.',
415 # Now we begin extracting as much information as we can from what we
416 # retrieved. First we extract the information common to all extractors,
417 # and latter we extract those that are Vimeo specific.
418 self.report_extraction(video_id)
420 vimeo_config = self._search_regex(
421 r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage,
422 'vimeo config', default=None)
424 seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
425 if seed_status.get('state') == 'failed':
426 raise ExtractorError(
427 '%s said: %s' % (self.IE_NAME, seed_status['title']),
430 # Extract the config JSON
433 config_url = self._html_search_regex(
434 r' data-config-url="(.+?)"', webpage,
435 'config URL', default=None)
437 # Sometimes new react-based page is served instead of old one that require
438 # different config URL extraction approach (see
439 # https://github.com/rg3/youtube-dl/pull/7209)
440 vimeo_clip_page_config = self._search_regex(
441 r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
442 'vimeo clip page config')
443 config_url = self._parse_json(
444 vimeo_clip_page_config, video_id)['player']['config_url']
445 config_json = self._download_webpage(config_url, video_id)
446 config = json.loads(config_json)
447 except RegexNotFoundError:
448 # For pro videos or player.vimeo.com urls
449 # We try to find out to which variable is assigned the config dic
450 m_variable_name = re.search('(\w)\.video\.id', webpage)
451 if m_variable_name is not None:
452 config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))
454 config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
455 config = self._search_regex(config_re, webpage, 'info section',
457 config = json.loads(config)
458 except Exception as e:
459 if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
460 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
462 if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
463 if '_video_password_verified' in data:
464 raise ExtractorError('video password verification failed!')
465 self._verify_video_password(url, video_id, webpage)
466 return self._real_extract(
467 smuggle_url(url, {'_video_password_verified': 'verified'}))
469 raise ExtractorError('Unable to extract info section',
472 if config.get('view') == 4:
473 config = self._verify_player_video_password(url, video_id)
476 if '>You rented this title.<' in webpage:
478 if config.get('user', {}).get('purchased'):
481 config, lambda x: x['video']['vod']['purchase_options'][0]['label_string'], compat_str)
482 if label and label.startswith('You rented this'):
487 feature_id = config.get('video', {}).get('vod', {}).get('feature_id')
488 if feature_id and not data.get('force_feature_id', False):
489 return self.url_result(smuggle_url(
490 'https://player.vimeo.com/player/%s' % feature_id,
491 {'force_feature_id': True}), 'Vimeo')
493 # Extract video description
495 video_description = self._html_search_regex(
496 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
497 webpage, 'description', default=None)
498 if not video_description:
499 video_description = self._html_search_meta(
500 'description', webpage, default=None)
501 if not video_description and mobj.group('pro'):
502 orig_webpage = self._download_webpage(
504 note='Downloading webpage for description',
507 video_description = self._html_search_meta(
508 'description', orig_webpage, default=None)
509 if not video_description and not mobj.group('player'):
510 self._downloader.report_warning('Cannot find video description')
512 # Extract upload date
513 video_upload_date = None
514 mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage)
516 video_upload_date = unified_strdate(mobj.group(1))
519 view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
520 like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
521 comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
522 except RegexNotFoundError:
523 # This info is only available in vimeo.com/{id} urls
529 download_request = sanitized_Request('https://vimeo.com/%s?action=load_download_config' % video_id, headers={
530 'X-Requested-With': 'XMLHttpRequest'})
531 download_data = self._download_json(download_request, video_id, fatal=False)
533 source_file = download_data.get('source_file')
534 if isinstance(source_file, dict):
535 download_url = source_file.get('download_url')
536 if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
537 source_name = source_file.get('public_name', 'Original')
538 if self._is_valid_url(download_url, video_id, '%s video' % source_name):
539 ext = source_file.get('extension', determine_ext(download_url)).lower()
543 'width': int_or_none(source_file.get('width')),
544 'height': int_or_none(source_file.get('height')),
545 'filesize': parse_filesize(source_file.get('size')),
546 'format_id': source_name,
550 info_dict = self._parse_config(config, video_id)
551 formats.extend(info_dict['formats'])
552 self._vimeo_sort_formats(formats)
556 'upload_date': video_upload_date,
557 'description': video_description,
559 'view_count': view_count,
560 'like_count': like_count,
561 'comment_count': comment_count,
567 class VimeoOndemandIE(VimeoBaseInfoExtractor):
568 IE_NAME = 'vimeo:ondemand'
569 _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?P<id>[^/?#&]+)'
571 # ondemand video not available via https://vimeo.com/id
572 'url': 'https://vimeo.com/ondemand/20704',
573 'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
577 'title': 'המעבדה - במאי יותם פלדמן',
578 'uploader': 'גם סרטים',
579 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/gumfilms',
580 'uploader_id': 'gumfilms',
583 'url': 'https://vimeo.com/ondemand/nazmaalik',
584 'only_matching': True,
586 'url': 'https://vimeo.com/ondemand/141692381',
587 'only_matching': True,
589 'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
590 'only_matching': True,
593 def _real_extract(self, url):
594 video_id = self._match_id(url)
595 webpage = self._download_webpage(url, video_id)
596 return self.url_result(self._og_search_video_url(webpage), VimeoIE.ie_key())
599 class VimeoChannelIE(VimeoBaseInfoExtractor):
600 IE_NAME = 'vimeo:channel'
601 _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
602 _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
604 _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
606 'url': 'https://vimeo.com/channels/tributes',
609 'title': 'Vimeo Tributes',
611 'playlist_mincount': 25,
614 def _page_url(self, base_url, pagenum):
615 return '%s/videos/page:%d/' % (base_url, pagenum)
617 def _extract_list_title(self, webpage):
618 return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title')
620 def _login_list_password(self, page_url, list_id, webpage):
621 login_form = self._search_regex(
622 r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
623 webpage, 'login form', default=None)
627 password = self._downloader.params.get('videopassword')
629 raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
630 fields = self._hidden_inputs(login_form)
631 token, vuid = self._extract_xsrft_and_vuid(webpage)
632 fields['token'] = token
633 fields['password'] = password
634 post = urlencode_postdata(fields)
635 password_path = self._search_regex(
636 r'action="([^"]+)"', login_form, 'password URL')
637 password_url = compat_urlparse.urljoin(page_url, password_path)
638 password_request = sanitized_Request(password_url, post)
639 password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
640 self._set_vimeo_cookie('vuid', vuid)
641 self._set_vimeo_cookie('xsrft', token)
643 return self._download_webpage(
644 password_request, list_id,
645 'Verifying the password', 'Wrong password')
647 def _title_and_entries(self, list_id, base_url):
648 for pagenum in itertools.count(1):
649 page_url = self._page_url(base_url, pagenum)
650 webpage = self._download_webpage(
652 'Downloading page %s' % pagenum)
655 webpage = self._login_list_password(page_url, list_id, webpage)
656 yield self._extract_list_title(webpage)
658 # Try extracting href first since not all videos are available via
659 # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
661 r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)', webpage)
663 for video_id, video_url in clips:
664 yield self.url_result(
665 compat_urlparse.urljoin(base_url, video_url),
666 VimeoIE.ie_key(), video_id=video_id)
667 # More relaxed fallback
669 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
670 yield self.url_result(
671 'https://vimeo.com/%s' % video_id,
672 VimeoIE.ie_key(), video_id=video_id)
674 if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
677 def _extract_videos(self, list_id, base_url):
678 title_and_entries = self._title_and_entries(list_id, base_url)
679 list_title = next(title_and_entries)
680 return self.playlist_result(title_and_entries, list_id, list_title)
682 def _real_extract(self, url):
683 mobj = re.match(self._VALID_URL, url)
684 channel_id = mobj.group('id')
685 return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
688 class VimeoUserIE(VimeoChannelIE):
689 IE_NAME = 'vimeo:user'
690 _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
691 _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
693 'url': 'https://vimeo.com/nkistudio/videos',
698 'playlist_mincount': 66,
701 def _real_extract(self, url):
702 mobj = re.match(self._VALID_URL, url)
703 name = mobj.group('name')
704 return self._extract_videos(name, 'https://vimeo.com/%s' % name)
707 class VimeoAlbumIE(VimeoChannelIE):
708 IE_NAME = 'vimeo:album'
709 _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)(?:$|[?#]|/(?!video))'
710 _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
712 'url': 'https://vimeo.com/album/2632481',
715 'title': 'Staff Favorites: November 2013',
717 'playlist_mincount': 13,
719 'note': 'Password-protected album',
720 'url': 'https://vimeo.com/album/3253534',
727 'videopassword': 'youtube-dl',
730 'url': 'https://vimeo.com/album/2632481/sort:plays/format:thumbnail',
731 'only_matching': True,
733 # TODO: respect page number
734 'url': 'https://vimeo.com/album/2632481/page:2/sort:plays/format:thumbnail',
735 'only_matching': True,
738 def _page_url(self, base_url, pagenum):
739 return '%s/page:%d/' % (base_url, pagenum)
741 def _real_extract(self, url):
742 album_id = self._match_id(url)
743 return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id)
746 class VimeoGroupsIE(VimeoAlbumIE):
747 IE_NAME = 'vimeo:group'
748 _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)'
750 'url': 'https://vimeo.com/groups/rolexawards',
753 'title': 'Rolex Awards for Enterprise',
755 'playlist_mincount': 73,
758 def _extract_list_title(self, webpage):
759 return self._og_search_title(webpage)
761 def _real_extract(self, url):
762 mobj = re.match(self._VALID_URL, url)
763 name = mobj.group('name')
764 return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
767 class VimeoReviewIE(VimeoBaseInfoExtractor):
768 IE_NAME = 'vimeo:review'
769 IE_DESC = 'Review pages on vimeo'
770 _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
772 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
773 'md5': 'c507a72f780cacc12b2248bb4006d253',
777 'title': "DICK HARDWICK 'Comedian'",
778 'uploader': 'Richard Hardwick',
779 'uploader_id': 'user21297594',
782 'note': 'video player needs Referer',
783 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
784 'md5': '6295fdab8f4bf6a002d058b2c6dce276',
788 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
789 'uploader': 'DevWeek Events',
791 'thumbnail': 're:^https?://.*\.jpg$',
792 'uploader_id': 'user22258446',
796 def _real_extract(self, url):
797 video_id = self._match_id(url)
798 config = self._download_json(
799 'https://player.vimeo.com/video/%s/config' % video_id, video_id)
800 info_dict = self._parse_config(config, video_id)
801 self._vimeo_sort_formats(info_dict['formats'])
802 info_dict['id'] = video_id
806 class VimeoWatchLaterIE(VimeoChannelIE):
807 IE_NAME = 'vimeo:watchlater'
808 IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
809 _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
810 _TITLE = 'Watch Later'
811 _LOGIN_REQUIRED = True
813 'url': 'https://vimeo.com/watchlater',
814 'only_matching': True,
817 def _real_initialize(self):
820 def _page_url(self, base_url, pagenum):
821 url = '%s/page:%d/' % (base_url, pagenum)
822 request = sanitized_Request(url)
823 # Set the header to get a partial html page with the ids,
824 # the normal page doesn't contain them.
825 request.add_header('X-Requested-With', 'XMLHttpRequest')
828 def _real_extract(self, url):
829 return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
832 class VimeoLikesIE(InfoExtractor):
833 _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
834 IE_NAME = 'vimeo:likes'
835 IE_DESC = 'Vimeo user likes'
837 'url': 'https://vimeo.com/user755559/likes/',
838 'playlist_mincount': 293,
840 'id': 'user755559_likes',
841 'description': 'See all the videos urza likes',
842 'title': 'Videos urza likes',
846 def _real_extract(self, url):
847 user_id = self._match_id(url)
848 webpage = self._download_webpage(url, user_id)
849 page_count = self._int(
851 r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
852 .*?</a></li>\s*<li\s+class="pagination_next">
853 ''', webpage, 'page count'),
854 'page count', fatal=True)
856 title = self._html_search_regex(
857 r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
858 description = self._html_search_meta('description', webpage)
861 page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
863 webpage = self._download_webpage(
865 note='Downloading page %d/%d' % (idx + 1, page_count))
866 video_list = self._search_regex(
867 r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
868 webpage, 'video content')
870 r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
874 'url': compat_urlparse.urljoin(page_url, path),
877 pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
881 'id': 'user%s_likes' % user_id,
883 'description': description,