2 from __future__ import unicode_literals
8 from .common import InfoExtractor
31 class VimeoBaseInfoExtractor(InfoExtractor):
32 _NETRC_MACHINE = 'vimeo'
33 _LOGIN_REQUIRED = False
34 _LOGIN_URL = 'https://vimeo.com/log_in'
37 (username, password) = self._get_login_info()
39 if self._LOGIN_REQUIRED:
40 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
43 webpage = self._download_webpage(self._LOGIN_URL, None, False)
44 token, vuid = self._extract_xsrft_and_vuid(webpage)
45 data = urlencode_postdata(encode_dict({
52 login_request = sanitized_Request(self._LOGIN_URL, data)
53 login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
54 login_request.add_header('Referer', self._LOGIN_URL)
55 self._set_vimeo_cookie('vuid', vuid)
56 self._download_webpage(login_request, None, False, 'Wrong login info')
58 def _extract_xsrft_and_vuid(self, webpage):
59 xsrft = self._search_regex(
60 r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
61 webpage, 'login token', group='xsrft')
62 vuid = self._search_regex(
63 r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
64 webpage, 'vuid', group='vuid')
67 def _set_vimeo_cookie(self, name, value):
68 self._set_cookie('vimeo.com', name, value)
71 class VimeoIE(VimeoBaseInfoExtractor):
72 """Information extractor for vimeo.com."""
74 # _VALID_URL matches Vimeo URLs
84 vimeo(?P<pro>pro)?\.com/
85 (?!channels/[^/?#]+/?(?:$|[?#])|(?:album|ondemand)/)
90 moogaloop\.swf)\?clip_id=
94 /?(?:[?&].*)?(?:[#].*)?$
99 'url': 'http://vimeo.com/56015672#at=0',
100 'md5': '8879b6cc097e987f02484baf890129e5',
104 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
105 'description': 'md5:2d3305bad981a06ff79f027f19865021',
106 'upload_date': '20121220',
107 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user7108434',
108 'uploader_id': 'user7108434',
109 'uploader': 'Filippo Valsorda',
114 'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
115 'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
116 'note': 'Vimeo Pro video (#1197)',
120 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
121 'uploader_id': 'openstreetmapus',
122 'uploader': 'OpenStreetMap US',
123 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
124 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30',
129 'url': 'http://player.vimeo.com/video/54469442',
130 'md5': '619b811a4417aa4abe78dc653becf511',
131 'note': 'Videos that embed the url in the player page',
135 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
136 'uploader': 'The BLN & Business of Software',
137 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware',
138 'uploader_id': 'theblnbusinessofsoftware',
144 'url': 'http://vimeo.com/68375962',
145 'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
146 'note': 'Video protected with password',
150 'title': 'youtube-dl password protected test video',
151 'upload_date': '20130614',
152 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user18948128',
153 'uploader_id': 'user18948128',
154 'uploader': 'Jaime Marquínez Ferrándiz',
156 'description': 'This is "youtube-dl password protected test video" by Jaime Marquínez Ferrándiz on Vimeo, the home for high quality videos and the people\u2026',
159 'videopassword': 'youtube-dl',
163 'url': 'http://vimeo.com/channels/keypeele/75629013',
164 'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
165 'note': 'Video is freely available via original URL '
166 'and protected with password when accessed via http://vimeo.com/75629013',
170 'title': 'Key & Peele: Terrorist Interrogation',
171 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
172 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/atencio',
173 'uploader_id': 'atencio',
174 'uploader': 'Peter Atencio',
175 'upload_date': '20130927',
180 'url': 'http://vimeo.com/76979871',
181 'note': 'Video with subtitles',
185 'title': 'The New Vimeo Player (You Know, For Videos)',
186 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
187 'upload_date': '20131015',
188 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/staff',
189 'uploader_id': 'staff',
190 'uploader': 'Vimeo Staff',
195 # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
196 'url': 'https://player.vimeo.com/video/98044508',
197 'note': 'The js code contains assignments to the same variable as the config',
201 'title': 'Pier Solar OUYA Official Trailer',
202 'uploader': 'Tulio Gonçalves',
203 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user28849593',
204 'uploader_id': 'user28849593',
208 # contains original format
209 'url': 'https://vimeo.com/33951933',
210 'md5': '53c688fa95a55bf4b7293d37a89c5c53',
214 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
215 'uploader': 'The DMCI',
216 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/dmci',
217 'uploader_id': 'dmci',
218 'upload_date': '20111220',
219 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
223 'url': 'https://vimeo.com/109815029',
224 'note': 'Video not completely processed, "failed" seed status',
225 'only_matching': True,
228 'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
229 'only_matching': True,
232 # source file returns 403: Forbidden
233 'url': 'https://vimeo.com/7809605',
234 'only_matching': True,
239 def _extract_vimeo_url(url, webpage):
240 # Look for embedded (iframe) Vimeo player
242 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
244 player_url = unescapeHTML(mobj.group('url'))
245 surl = smuggle_url(player_url, {'http_headers': {'Referer': url}})
247 # Look for embedded (swf embed) Vimeo player
249 r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
253 def _verify_video_password(self, url, video_id, webpage):
254 password = self._downloader.params.get('videopassword')
256 raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
257 token, vuid = self._extract_xsrft_and_vuid(webpage)
258 data = urlencode_postdata(encode_dict({
259 'password': password,
262 if url.startswith('http://'):
263 # vimeo only supports https now, but the user can give an http url
264 url = url.replace('http://', 'https://')
265 password_request = sanitized_Request(url + '/password', data)
266 password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
267 password_request.add_header('Referer', url)
268 self._set_vimeo_cookie('vuid', vuid)
269 return self._download_webpage(
270 password_request, video_id,
271 'Verifying the password', 'Wrong password')
273 def _verify_player_video_password(self, url, video_id):
274 password = self._downloader.params.get('videopassword')
276 raise ExtractorError('This video is protected by a password, use the --video-password option')
277 data = urlencode_postdata(encode_dict({'password': password}))
278 pass_url = url + '/check-password'
279 password_request = sanitized_Request(pass_url, data)
280 password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
281 return self._download_json(
282 password_request, video_id,
283 'Verifying the password',
286 def _real_initialize(self):
289 def _real_extract(self, url):
290 url, data = unsmuggle_url(url, {})
291 headers = std_headers.copy()
292 if 'http_headers' in data:
293 headers.update(data['http_headers'])
294 if 'Referer' not in headers:
295 headers['Referer'] = url
297 # Extract ID from URL
298 mobj = re.match(self._VALID_URL, url)
299 video_id = mobj.group('id')
301 if mobj.group('pro') or mobj.group('player'):
302 url = 'https://player.vimeo.com/video/' + video_id
304 url = 'https://vimeo.com/' + video_id
306 # Retrieve video webpage to extract further information
307 request = sanitized_Request(url, headers=headers)
309 webpage = self._download_webpage(request, video_id)
310 except ExtractorError as ee:
311 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
312 errmsg = ee.cause.read()
313 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
314 raise ExtractorError(
315 'Cannot download embed-only video without embedding '
316 'URL. Please call youtube-dl with the URL of the page '
317 'that embeds this video.',
321 # Now we begin extracting as much information as we can from what we
322 # retrieved. First we extract the information common to all extractors,
323 # and latter we extract those that are Vimeo specific.
324 self.report_extraction(video_id)
326 vimeo_config = self._search_regex(
327 r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage,
328 'vimeo config', default=None)
330 seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
331 if seed_status.get('state') == 'failed':
332 raise ExtractorError(
333 '%s said: %s' % (self.IE_NAME, seed_status['title']),
336 # Extract the config JSON
339 config_url = self._html_search_regex(
340 r' data-config-url="(.+?)"', webpage,
341 'config URL', default=None)
343 # Sometimes new react-based page is served instead of old one that require
344 # different config URL extraction approach (see
345 # https://github.com/rg3/youtube-dl/pull/7209)
346 vimeo_clip_page_config = self._search_regex(
347 r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
348 'vimeo clip page config')
349 config_url = self._parse_json(
350 vimeo_clip_page_config, video_id)['player']['config_url']
351 config_json = self._download_webpage(config_url, video_id)
352 config = json.loads(config_json)
353 except RegexNotFoundError:
354 # For pro videos or player.vimeo.com urls
355 # We try to find out to which variable is assigned the config dic
356 m_variable_name = re.search('(\w)\.video\.id', webpage)
357 if m_variable_name is not None:
358 config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))
360 config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
361 config = self._search_regex(config_re, webpage, 'info section',
363 config = json.loads(config)
364 except Exception as e:
365 if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
366 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
368 if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
369 if '_video_password_verified' in data:
370 raise ExtractorError('video password verification failed!')
371 self._verify_video_password(url, video_id, webpage)
372 return self._real_extract(
373 smuggle_url(url, {'_video_password_verified': 'verified'}))
375 raise ExtractorError('Unable to extract info section',
378 if config.get('view') == 4:
379 config = self._verify_player_video_password(url, video_id)
381 if '>You rented this title.<' in webpage:
382 feature_id = config.get('video', {}).get('vod', {}).get('feature_id')
383 if feature_id and not data.get('force_feature_id', False):
384 return self.url_result(smuggle_url(
385 'https://player.vimeo.com/player/%s' % feature_id,
386 {'force_feature_id': True}), 'Vimeo')
389 video_title = config['video']['title']
391 # Extract uploader, uploader_url and uploader_id
392 video_uploader = config['video'].get('owner', {}).get('name')
393 video_uploader_url = config['video'].get('owner', {}).get('url')
394 video_uploader_id = video_uploader_url.split('/')[-1] if video_uploader_url else None
396 # Extract video thumbnail
397 video_thumbnail = config['video'].get('thumbnail')
398 if video_thumbnail is None:
399 video_thumbs = config['video'].get('thumbs')
400 if video_thumbs and isinstance(video_thumbs, dict):
401 _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
403 # Extract video description
405 video_description = self._html_search_regex(
406 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
407 webpage, 'description', default=None)
408 if not video_description:
409 video_description = self._html_search_meta(
410 'description', webpage, default=None)
411 if not video_description and mobj.group('pro'):
412 orig_webpage = self._download_webpage(
414 note='Downloading webpage for description',
417 video_description = self._html_search_meta(
418 'description', orig_webpage, default=None)
419 if not video_description and not mobj.group('player'):
420 self._downloader.report_warning('Cannot find video description')
422 # Extract video duration
423 video_duration = int_or_none(config['video'].get('duration'))
425 # Extract upload date
426 video_upload_date = None
427 mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage)
429 video_upload_date = unified_strdate(mobj.group(1))
432 view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
433 like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
434 comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
435 except RegexNotFoundError:
436 # This info is only available in vimeo.com/{id} urls
442 download_request = sanitized_Request('https://vimeo.com/%s?action=load_download_config' % video_id, headers={
443 'X-Requested-With': 'XMLHttpRequest'})
444 download_data = self._download_json(download_request, video_id, fatal=False)
446 source_file = download_data.get('source_file')
447 if isinstance(source_file, dict):
448 download_url = source_file.get('download_url')
449 if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
450 source_name = source_file.get('public_name', 'Original')
451 if self._is_valid_url(download_url, video_id, '%s video' % source_name):
452 ext = source_file.get('extension', determine_ext(download_url)).lower()
456 'width': int_or_none(source_file.get('width')),
457 'height': int_or_none(source_file.get('height')),
458 'filesize': parse_filesize(source_file.get('size')),
459 'format_id': source_name,
462 config_files = config['video'].get('files') or config['request'].get('files', {})
463 for f in config_files.get('progressive', []):
464 video_url = f.get('url')
469 'format_id': 'http-%s' % f.get('quality'),
470 'width': int_or_none(f.get('width')),
471 'height': int_or_none(f.get('height')),
472 'fps': int_or_none(f.get('fps')),
473 'tbr': int_or_none(f.get('bitrate')),
475 m3u8_url = config_files.get('hls', {}).get('url')
477 formats.extend(self._extract_m3u8_formats(
478 m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
479 # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
480 # at the same time without actual units specified. This lead to wrong sorting.
481 self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'format_id'))
484 text_tracks = config['request'].get('text_tracks')
486 for tt in text_tracks:
487 subtitles[tt['lang']] = [{
489 'url': 'https://vimeo.com' + tt['url'],
494 'uploader': video_uploader,
495 'uploader_url': video_uploader_url,
496 'uploader_id': video_uploader_id,
497 'upload_date': video_upload_date,
498 'title': video_title,
499 'thumbnail': video_thumbnail,
500 'description': video_description,
501 'duration': video_duration,
504 'view_count': view_count,
505 'like_count': like_count,
506 'comment_count': comment_count,
507 'subtitles': subtitles,
511 class VimeoOndemandIE(VimeoBaseInfoExtractor):
512 IE_NAME = 'vimeo:ondemand'
513 _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?P<id>[^/?#&]+)'
515 # ondemand video not available via https://vimeo.com/id
516 'url': 'https://vimeo.com/ondemand/20704',
517 'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
521 'title': 'המעבדה - במאי יותם פלדמן',
522 'uploader': 'גם סרטים',
523 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/gumfilms',
524 'uploader_id': 'gumfilms',
527 'url': 'https://vimeo.com/ondemand/nazmaalik',
528 'only_matching': True,
530 'url': 'https://vimeo.com/ondemand/141692381',
531 'only_matching': True,
533 'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
534 'only_matching': True,
537 def _real_extract(self, url):
538 video_id = self._match_id(url)
539 webpage = self._download_webpage(url, video_id)
540 return self.url_result(self._og_search_video_url(webpage), VimeoIE.ie_key())
543 class VimeoChannelIE(VimeoBaseInfoExtractor):
544 IE_NAME = 'vimeo:channel'
545 _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
546 _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
548 _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
550 'url': 'https://vimeo.com/channels/tributes',
553 'title': 'Vimeo Tributes',
555 'playlist_mincount': 25,
558 def _page_url(self, base_url, pagenum):
559 return '%s/videos/page:%d/' % (base_url, pagenum)
561 def _extract_list_title(self, webpage):
562 return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title')
564 def _login_list_password(self, page_url, list_id, webpage):
565 login_form = self._search_regex(
566 r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
567 webpage, 'login form', default=None)
571 password = self._downloader.params.get('videopassword')
573 raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
574 fields = self._hidden_inputs(login_form)
575 token, vuid = self._extract_xsrft_and_vuid(webpage)
576 fields['token'] = token
577 fields['password'] = password
578 post = urlencode_postdata(encode_dict(fields))
579 password_path = self._search_regex(
580 r'action="([^"]+)"', login_form, 'password URL')
581 password_url = compat_urlparse.urljoin(page_url, password_path)
582 password_request = sanitized_Request(password_url, post)
583 password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
584 self._set_vimeo_cookie('vuid', vuid)
585 self._set_vimeo_cookie('xsrft', token)
587 return self._download_webpage(
588 password_request, list_id,
589 'Verifying the password', 'Wrong password')
591 def _title_and_entries(self, list_id, base_url):
592 for pagenum in itertools.count(1):
593 page_url = self._page_url(base_url, pagenum)
594 webpage = self._download_webpage(
596 'Downloading page %s' % pagenum)
599 webpage = self._login_list_password(page_url, list_id, webpage)
600 yield self._extract_list_title(webpage)
602 for video_id in re.findall(r'id="clip_(\d+?)"', webpage):
603 yield self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo')
605 if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
608 def _extract_videos(self, list_id, base_url):
609 title_and_entries = self._title_and_entries(list_id, base_url)
610 list_title = next(title_and_entries)
611 return self.playlist_result(title_and_entries, list_id, list_title)
613 def _real_extract(self, url):
614 mobj = re.match(self._VALID_URL, url)
615 channel_id = mobj.group('id')
616 return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
619 class VimeoUserIE(VimeoChannelIE):
620 IE_NAME = 'vimeo:user'
621 _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
622 _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
624 'url': 'https://vimeo.com/nkistudio/videos',
629 'playlist_mincount': 66,
632 def _real_extract(self, url):
633 mobj = re.match(self._VALID_URL, url)
634 name = mobj.group('name')
635 return self._extract_videos(name, 'https://vimeo.com/%s' % name)
638 class VimeoAlbumIE(VimeoChannelIE):
639 IE_NAME = 'vimeo:album'
640 _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)'
641 _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
643 'url': 'https://vimeo.com/album/2632481',
646 'title': 'Staff Favorites: November 2013',
648 'playlist_mincount': 13,
650 'note': 'Password-protected album',
651 'url': 'https://vimeo.com/album/3253534',
658 'videopassword': 'youtube-dl',
662 def _page_url(self, base_url, pagenum):
663 return '%s/page:%d/' % (base_url, pagenum)
665 def _real_extract(self, url):
666 album_id = self._match_id(url)
667 return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id)
670 class VimeoGroupsIE(VimeoAlbumIE):
671 IE_NAME = 'vimeo:group'
672 _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)'
674 'url': 'https://vimeo.com/groups/rolexawards',
677 'title': 'Rolex Awards for Enterprise',
679 'playlist_mincount': 73,
682 def _extract_list_title(self, webpage):
683 return self._og_search_title(webpage)
685 def _real_extract(self, url):
686 mobj = re.match(self._VALID_URL, url)
687 name = mobj.group('name')
688 return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
691 class VimeoReviewIE(InfoExtractor):
692 IE_NAME = 'vimeo:review'
693 IE_DESC = 'Review pages on vimeo'
694 _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
696 'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
697 'md5': 'c507a72f780cacc12b2248bb4006d253',
701 'title': "DICK HARDWICK 'Comedian'",
702 'uploader': 'Richard Hardwick',
705 'note': 'video player needs Referer',
706 'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
707 'md5': '6295fdab8f4bf6a002d058b2c6dce276',
711 'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
712 'uploader': 'DevWeek Events',
714 'thumbnail': 're:^https?://.*\.jpg$',
718 def _real_extract(self, url):
719 mobj = re.match(self._VALID_URL, url)
720 video_id = mobj.group('id')
721 player_url = 'https://player.vimeo.com/player/' + video_id
722 return self.url_result(player_url, 'Vimeo', video_id)
725 class VimeoWatchLaterIE(VimeoChannelIE):
726 IE_NAME = 'vimeo:watchlater'
727 IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
728 _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
729 _TITLE = 'Watch Later'
730 _LOGIN_REQUIRED = True
732 'url': 'https://vimeo.com/watchlater',
733 'only_matching': True,
736 def _real_initialize(self):
739 def _page_url(self, base_url, pagenum):
740 url = '%s/page:%d/' % (base_url, pagenum)
741 request = sanitized_Request(url)
742 # Set the header to get a partial html page with the ids,
743 # the normal page doesn't contain them.
744 request.add_header('X-Requested-With', 'XMLHttpRequest')
747 def _real_extract(self, url):
748 return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
751 class VimeoLikesIE(InfoExtractor):
752 _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
753 IE_NAME = 'vimeo:likes'
754 IE_DESC = 'Vimeo user likes'
756 'url': 'https://vimeo.com/user755559/likes/',
757 'playlist_mincount': 293,
759 'id': 'user755559_likes',
760 'description': 'See all the videos urza likes',
761 'title': 'Videos urza likes',
765 def _real_extract(self, url):
766 user_id = self._match_id(url)
767 webpage = self._download_webpage(url, user_id)
768 page_count = self._int(
770 r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
771 .*?</a></li>\s*<li\s+class="pagination_next">
772 ''', webpage, 'page count'),
773 'page count', fatal=True)
775 title = self._html_search_regex(
776 r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
777 description = self._html_search_meta('description', webpage)
780 page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
782 webpage = self._download_webpage(
784 note='Downloading page %d/%d' % (idx + 1, page_count))
785 video_list = self._search_regex(
786 r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
787 webpage, 'video content')
789 r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
793 'url': compat_urlparse.urljoin(page_url, path),
796 pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
800 'id': 'user%s_likes' % user_id,
802 'description': description,