_ Git - youtube-dl/blob - youtube_dl/extractor/vimeo.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import re
   6 import itertools
   7
   8 from .common import InfoExtractor
   9 from ..compat import (
  10     compat_HTTPError,
  11     compat_urlparse,
  12 )
  13 from ..utils import (
  14     determine_ext,
  15     encode_dict,
  16     ExtractorError,
  17     InAdvancePagedList,
  18     int_or_none,
  19     RegexNotFoundError,
  20     sanitized_Request,
  21     smuggle_url,
  22     std_headers,
  23     unified_strdate,
  24     unsmuggle_url,
  25     urlencode_postdata,
  26     unescapeHTML,
  27     parse_filesize,
  28 )
  29
  30
  31 class VimeoBaseInfoExtractor(InfoExtractor):
  32     _NETRC_MACHINE = 'vimeo'
  33     _LOGIN_REQUIRED = False
  34     _LOGIN_URL = 'https://vimeo.com/log_in'
  35
  36     def _login(self):
  37         (username, password) = self._get_login_info()
  38         if username is None:
  39             if self._LOGIN_REQUIRED:
  40                 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
  41             return
  42         self.report_login()
  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({
  46             'action': 'login',
  47             'email': username,
  48             'password': password,
  49             'service': 'vimeo',
  50             'token': token,
  51         }))
  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')
  57
  58     def _extract_xsrft_and_vuid(self, webpage):
  59         xsrft = self._search_regex(
  60             r'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')
  65         return xsrft, vuid
  66
  67     def _set_vimeo_cookie(self, name, value):
  68         self._set_cookie('vimeo.com', name, value)
  69
  70
  71 class VimeoIE(VimeoBaseInfoExtractor):
  72     """Information extractor for vimeo.com."""
  73
  74     # _VALID_URL matches Vimeo URLs
  75     _VALID_URL = r'''(?x)
  76         https?://
  77         (?:(?:www|(?P<player>player))\.)?
  78         vimeo(?P<pro>pro)?\.com/
  79         (?!channels/[^/?#]+/?(?:$|[?#])|album/)
  80         (?:.*?/)?
  81         (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)?
  82         (?:videos?/)?
  83         (?P<id>[0-9]+)
  84         /?(?:[?&].*)?(?:[#].*)?$'''
  85     IE_NAME = 'vimeo'
  86     _TESTS = [
  87         {
  88             'url': 'http://vimeo.com/56015672#at=0',
  89             'md5': '8879b6cc097e987f02484baf890129e5',
  90             'info_dict': {
  91                 'id': '56015672',
  92                 'ext': 'mp4',
  93                 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
  94                 'description': 'md5:2d3305bad981a06ff79f027f19865021',
  95                 'upload_date': '20121220',
  96                 'uploader_id': 'user7108434',
  97                 'uploader': 'Filippo Valsorda',
  98                 'duration': 10,
  99             },
 100         },
 101         {
 102             'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
 103             'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
 104             'note': 'Vimeo Pro video (#1197)',
 105             'info_dict': {
 106                 'id': '68093876',
 107                 'ext': 'mp4',
 108                 'uploader_id': 'openstreetmapus',
 109                 'uploader': 'OpenStreetMap US',
 110                 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
 111                 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30',
 112                 'duration': 1595,
 113             },
 114         },
 115         {
 116             'url': 'http://player.vimeo.com/video/54469442',
 117             'md5': '619b811a4417aa4abe78dc653becf511',
 118             'note': 'Videos that embed the url in the player page',
 119             'info_dict': {
 120                 'id': '54469442',
 121                 'ext': 'mp4',
 122                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
 123                 'uploader': 'The BLN & Business of Software',
 124                 'uploader_id': 'theblnbusinessofsoftware',
 125                 'duration': 3610,
 126                 'description': None,
 127             },
 128         },
 129         {
 130             'url': 'http://vimeo.com/68375962',
 131             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 132             'note': 'Video protected with password',
 133             'info_dict': {
 134                 'id': '68375962',
 135                 'ext': 'mp4',
 136                 'title': 'youtube-dl password protected test video',
 137                 'upload_date': '20130614',
 138                 'uploader_id': 'user18948128',
 139                 'uploader': 'Jaime Marquínez Ferrándiz',
 140                 'duration': 10,
 141                 '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',
 142             },
 143             'params': {
 144                 'videopassword': 'youtube-dl',
 145             },
 146         },
 147         {
 148             'url': 'http://vimeo.com/channels/keypeele/75629013',
 149             'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
 150             'note': 'Video is freely available via original URL '
 151                     'and protected with password when accessed via http://vimeo.com/75629013',
 152             'info_dict': {
 153                 'id': '75629013',
 154                 'ext': 'mp4',
 155                 'title': 'Key & Peele: Terrorist Interrogation',
 156                 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
 157                 'uploader_id': 'atencio',
 158                 'uploader': 'Peter Atencio',
 159                 'upload_date': '20130927',
 160                 'duration': 187,
 161             },
 162         },
 163         {
 164             'url': 'http://vimeo.com/76979871',
 165             'note': 'Video with subtitles',
 166             'info_dict': {
 167                 'id': '76979871',
 168                 'ext': 'mp4',
 169                 'title': 'The New Vimeo Player (You Know, For Videos)',
 170                 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
 171                 'upload_date': '20131015',
 172                 'uploader_id': 'staff',
 173                 'uploader': 'Vimeo Staff',
 174                 'duration': 62,
 175             }
 176         },
 177         {
 178             # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
 179             'url': 'https://player.vimeo.com/video/98044508',
 180             'note': 'The js code contains assignments to the same variable as the config',
 181             'info_dict': {
 182                 'id': '98044508',
 183                 'ext': 'mp4',
 184                 'title': 'Pier Solar OUYA Official Trailer',
 185                 'uploader': 'Tulio Gonçalves',
 186                 'uploader_id': 'user28849593',
 187             },
 188         },
 189         {
 190             # contains original format
 191             'url': 'https://vimeo.com/33951933',
 192             'md5': '53c688fa95a55bf4b7293d37a89c5c53',
 193             'info_dict': {
 194                 'id': '33951933',
 195                 'ext': 'mp4',
 196                 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
 197                 'uploader': 'The DMCI',
 198                 'uploader_id': 'dmci',
 199                 'upload_date': '20111220',
 200                 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
 201             },
 202         },
 203         {
 204             'url': 'https://vimeo.com/109815029',
 205             'note': 'Video not completely processed, "failed" seed status',
 206             'only_matching': True,
 207         },
 208         {
 209             'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
 210             'only_matching': True,
 211         },
 212     ]
 213
 214     @staticmethod
 215     def _extract_vimeo_url(url, webpage):
 216         # Look for embedded (iframe) Vimeo player
 217         mobj = re.search(
 218             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
 219         if mobj:
 220             player_url = unescapeHTML(mobj.group('url'))
 221             surl = smuggle_url(player_url, {'http_headers': {'Referer': url}})
 222             return surl
 223         # Look for embedded (swf embed) Vimeo player
 224         mobj = re.search(
 225             r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
 226         if mobj:
 227             return mobj.group(1)
 228
 229     def _verify_video_password(self, url, video_id, webpage):
 230         password = self._downloader.params.get('videopassword', None)
 231         if password is None:
 232             raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
 233         token, vuid = self._extract_xsrft_and_vuid(webpage)
 234         data = urlencode_postdata(encode_dict({
 235             'password': password,
 236             'token': token,
 237         }))
 238         if url.startswith('http://'):
 239             # vimeo only supports https now, but the user can give an http url
 240             url = url.replace('http://', 'https://')
 241         password_request = sanitized_Request(url + '/password', data)
 242         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 243         password_request.add_header('Referer', url)
 244         self._set_vimeo_cookie('vuid', vuid)
 245         return self._download_webpage(
 246             password_request, video_id,
 247             'Verifying the password', 'Wrong password')
 248
 249     def _verify_player_video_password(self, url, video_id):
 250         password = self._downloader.params.get('videopassword', None)
 251         if password is None:
 252             raise ExtractorError('This video is protected by a password, use the --video-password option')
 253         data = urlencode_postdata(encode_dict({'password': password}))
 254         pass_url = url + '/check-password'
 255         password_request = sanitized_Request(pass_url, data)
 256         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 257         return self._download_json(
 258             password_request, video_id,
 259             'Verifying the password',
 260             'Wrong password')
 261
 262     def _real_initialize(self):
 263         self._login()
 264
 265     def _real_extract(self, url):
 266         url, data = unsmuggle_url(url, {})
 267         headers = std_headers
 268         if 'http_headers' in data:
 269             headers = headers.copy()
 270             headers.update(data['http_headers'])
 271         if 'Referer' not in headers:
 272             headers['Referer'] = url
 273
 274         # Extract ID from URL
 275         mobj = re.match(self._VALID_URL, url)
 276         video_id = mobj.group('id')
 277         orig_url = url
 278         if mobj.group('pro') or mobj.group('player'):
 279             url = 'https://player.vimeo.com/video/' + video_id
 280         else:
 281             url = 'https://vimeo.com/' + video_id
 282
 283         # Retrieve video webpage to extract further information
 284         request = sanitized_Request(url, None, headers)
 285         try:
 286             webpage = self._download_webpage(request, video_id)
 287         except ExtractorError as ee:
 288             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
 289                 errmsg = ee.cause.read()
 290                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 291                     raise ExtractorError(
 292                         'Cannot download embed-only video without embedding '
 293                         'URL. Please call youtube-dl with the URL of the page '
 294                         'that embeds this video.',
 295                         expected=True)
 296             raise
 297
 298         # Now we begin extracting as much information as we can from what we
 299         # retrieved. First we extract the information common to all extractors,
 300         # and latter we extract those that are Vimeo specific.
 301         self.report_extraction(video_id)
 302
 303         vimeo_config = self._search_regex(
 304             r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage,
 305             'vimeo config', default=None)
 306         if vimeo_config:
 307             seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
 308             if seed_status.get('state') == 'failed':
 309                 raise ExtractorError(
 310                     '%s said: %s' % (self.IE_NAME, seed_status['title']),
 311                     expected=True)
 312
 313         # Extract the config JSON
 314         try:
 315             try:
 316                 config_url = self._html_search_regex(
 317                     r' data-config-url="(.+?)"', webpage,
 318                     'config URL', default=None)
 319                 if not config_url:
 320                     # Sometimes new react-based page is served instead of old one that require
 321                     # different config URL extraction approach (see
 322                     # https://github.com/rg3/youtube-dl/pull/7209)
 323                     vimeo_clip_page_config = self._search_regex(
 324                         r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
 325                         'vimeo clip page config')
 326                     config_url = self._parse_json(
 327                         vimeo_clip_page_config, video_id)['player']['config_url']
 328                 config_json = self._download_webpage(config_url, video_id)
 329                 config = json.loads(config_json)
 330             except RegexNotFoundError:
 331                 # For pro videos or player.vimeo.com urls
 332                 # We try to find out to which variable is assigned the config dic
 333                 m_variable_name = re.search('(\w)\.video\.id', webpage)
 334                 if m_variable_name is not None:
 335                     config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))
 336                 else:
 337                     config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
 338                 config = self._search_regex(config_re, webpage, 'info section',
 339                                             flags=re.DOTALL)
 340                 config = json.loads(config)
 341         except Exception as e:
 342             if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
 343                 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
 344
 345             if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
 346                 if '_video_password_verified' in data:
 347                     raise ExtractorError('video password verification failed!')
 348                 self._verify_video_password(url, video_id, webpage)
 349                 return self._real_extract(
 350                     smuggle_url(url, {'_video_password_verified': 'verified'}))
 351             else:
 352                 raise ExtractorError('Unable to extract info section',
 353                                      cause=e)
 354         else:
 355             if config.get('view') == 4:
 356                 config = self._verify_player_video_password(url, video_id)
 357
 358         if '>You rented this title.<' in webpage:
 359             feature_id = config.get('video', {}).get('vod', {}).get('feature_id')
 360             if feature_id and not data.get('force_feature_id', False):
 361                 return self.url_result(smuggle_url(
 362                     'https://player.vimeo.com/player/%s' % feature_id,
 363                     {'force_feature_id': True}), 'Vimeo')
 364
 365         # Extract title
 366         video_title = config["video"]["title"]
 367
 368         # Extract uploader and uploader_id
 369         video_uploader = config["video"]["owner"]["name"]
 370         video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None
 371
 372         # Extract video thumbnail
 373         video_thumbnail = config["video"].get("thumbnail")
 374         if video_thumbnail is None:
 375             video_thumbs = config["video"].get("thumbs")
 376             if video_thumbs and isinstance(video_thumbs, dict):
 377                 _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
 378
 379         # Extract video description
 380
 381         video_description = self._html_search_regex(
 382             r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 383             webpage, 'description', default=None)
 384         if not video_description:
 385             video_description = self._html_search_meta(
 386                 'description', webpage, default=None)
 387         if not video_description and mobj.group('pro'):
 388             orig_webpage = self._download_webpage(
 389                 orig_url, video_id,
 390                 note='Downloading webpage for description',
 391                 fatal=False)
 392             if orig_webpage:
 393                 video_description = self._html_search_meta(
 394                     'description', orig_webpage, default=None)
 395         if not video_description and not mobj.group('player'):
 396             self._downloader.report_warning('Cannot find video description')
 397
 398         # Extract video duration
 399         video_duration = int_or_none(config["video"].get("duration"))
 400
 401         # Extract upload date
 402         video_upload_date = None
 403         mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage)
 404         if mobj is not None:
 405             video_upload_date = unified_strdate(mobj.group(1))
 406
 407         try:
 408             view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
 409             like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
 410             comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
 411         except RegexNotFoundError:
 412             # This info is only available in vimeo.com/{id} urls
 413             view_count = None
 414             like_count = None
 415             comment_count = None
 416
 417         formats = []
 418         download_request = sanitized_Request('https://vimeo.com/%s?action=load_download_config' % video_id, headers={
 419             'X-Requested-With': 'XMLHttpRequest'})
 420         download_data = self._download_json(download_request, video_id, fatal=False)
 421         if download_data:
 422             source_file = download_data.get('source_file')
 423             if isinstance(source_file, dict):
 424                 download_url = source_file.get('download_url')
 425                 if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
 426                     source_name = source_file.get('public_name', 'Original')
 427                     if self._is_valid_url(download_url, video_id, '%s video' % source_name):
 428                         ext = source_file.get('extension', determine_ext(download_url)).lower(),
 429                         formats.append({
 430                             'url': download_url,
 431                             'ext': ext,
 432                             'width': int_or_none(source_file.get('width')),
 433                             'height': int_or_none(source_file.get('height')),
 434                             'filesize': parse_filesize(source_file.get('size')),
 435                             'format_id': source_name,
 436                             'preference': 1,
 437                         })
 438         config_files = config['video'].get('files') or config['request'].get('files', {})
 439         for f in config_files.get('progressive', []):
 440             video_url = f.get('url')
 441             if not video_url:
 442                 continue
 443             formats.append({
 444                 'url': video_url,
 445                 'format_id': 'http-%s' % f.get('quality'),
 446                 'width': int_or_none(f.get('width')),
 447                 'height': int_or_none(f.get('height')),
 448                 'fps': int_or_none(f.get('fps')),
 449                 'tbr': int_or_none(f.get('bitrate')),
 450             })
 451         m3u8_url = config_files.get('hls', {}).get('url')
 452         if m3u8_url:
 453             formats.extend(self._extract_m3u8_formats(
 454                 m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
 455         # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
 456         # at the same time without actual units specified. This lead to wrong sorting.
 457         self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'format_id'))
 458
 459         subtitles = {}
 460         text_tracks = config['request'].get('text_tracks')
 461         if text_tracks:
 462             for tt in text_tracks:
 463                 subtitles[tt['lang']] = [{
 464                     'ext': 'vtt',
 465                     'url': 'https://vimeo.com' + tt['url'],
 466                 }]
 467
 468         return {
 469             'id': video_id,
 470             'uploader': video_uploader,
 471             'uploader_id': video_uploader_id,
 472             'upload_date': video_upload_date,
 473             'title': video_title,
 474             'thumbnail': video_thumbnail,
 475             'description': video_description,
 476             'duration': video_duration,
 477             'formats': formats,
 478             'webpage_url': url,
 479             'view_count': view_count,
 480             'like_count': like_count,
 481             'comment_count': comment_count,
 482             'subtitles': subtitles,
 483         }
 484
 485
 486 class VimeoChannelIE(VimeoBaseInfoExtractor):
 487     IE_NAME = 'vimeo:channel'
 488     _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
 489     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
 490     _TITLE = None
 491     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
 492     _TESTS = [{
 493         'url': 'https://vimeo.com/channels/tributes',
 494         'info_dict': {
 495             'id': 'tributes',
 496             'title': 'Vimeo Tributes',
 497         },
 498         'playlist_mincount': 25,
 499     }]
 500
 501     def _page_url(self, base_url, pagenum):
 502         return '%s/videos/page:%d/' % (base_url, pagenum)
 503
 504     def _extract_list_title(self, webpage):
 505         return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title')
 506
 507     def _login_list_password(self, page_url, list_id, webpage):
 508         login_form = self._search_regex(
 509             r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
 510             webpage, 'login form', default=None)
 511         if not login_form:
 512             return webpage
 513
 514         password = self._downloader.params.get('videopassword', None)
 515         if password is None:
 516             raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
 517         fields = self._hidden_inputs(login_form)
 518         token, vuid = self._extract_xsrft_and_vuid(webpage)
 519         fields['token'] = token
 520         fields['password'] = password
 521         post = urlencode_postdata(encode_dict(fields))
 522         password_path = self._search_regex(
 523             r'action="([^"]+)"', login_form, 'password URL')
 524         password_url = compat_urlparse.urljoin(page_url, password_path)
 525         password_request = sanitized_Request(password_url, post)
 526         password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
 527         self._set_vimeo_cookie('vuid', vuid)
 528         self._set_vimeo_cookie('xsrft', token)
 529
 530         return self._download_webpage(
 531             password_request, list_id,
 532             'Verifying the password', 'Wrong password')
 533
 534     def _title_and_entries(self, list_id, base_url):
 535         for pagenum in itertools.count(1):
 536             page_url = self._page_url(base_url, pagenum)
 537             webpage = self._download_webpage(
 538                 page_url, list_id,
 539                 'Downloading page %s' % pagenum)
 540
 541             if pagenum == 1:
 542                 webpage = self._login_list_password(page_url, list_id, webpage)
 543                 yield self._extract_list_title(webpage)
 544
 545             for video_id in re.findall(r'id="clip_(\d+?)"', webpage):
 546                 yield self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo')
 547
 548             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
 549                 break
 550
 551     def _extract_videos(self, list_id, base_url):
 552         title_and_entries = self._title_and_entries(list_id, base_url)
 553         list_title = next(title_and_entries)
 554         return self.playlist_result(title_and_entries, list_id, list_title)
 555
 556     def _real_extract(self, url):
 557         mobj = re.match(self._VALID_URL, url)
 558         channel_id = mobj.group('id')
 559         return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
 560
 561
 562 class VimeoUserIE(VimeoChannelIE):
 563     IE_NAME = 'vimeo:user'
 564     _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
 565     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
 566     _TESTS = [{
 567         'url': 'https://vimeo.com/nkistudio/videos',
 568         'info_dict': {
 569             'title': 'Nki',
 570             'id': 'nkistudio',
 571         },
 572         'playlist_mincount': 66,
 573     }]
 574
 575     def _real_extract(self, url):
 576         mobj = re.match(self._VALID_URL, url)
 577         name = mobj.group('name')
 578         return self._extract_videos(name, 'https://vimeo.com/%s' % name)
 579
 580
 581 class VimeoAlbumIE(VimeoChannelIE):
 582     IE_NAME = 'vimeo:album'
 583     _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)'
 584     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
 585     _TESTS = [{
 586         'url': 'https://vimeo.com/album/2632481',
 587         'info_dict': {
 588             'id': '2632481',
 589             'title': 'Staff Favorites: November 2013',
 590         },
 591         'playlist_mincount': 13,
 592     }, {
 593         'note': 'Password-protected album',
 594         'url': 'https://vimeo.com/album/3253534',
 595         'info_dict': {
 596             'title': 'test',
 597             'id': '3253534',
 598         },
 599         'playlist_count': 1,
 600         'params': {
 601             'videopassword': 'youtube-dl',
 602         }
 603     }]
 604
 605     def _page_url(self, base_url, pagenum):
 606         return '%s/page:%d/' % (base_url, pagenum)
 607
 608     def _real_extract(self, url):
 609         album_id = self._match_id(url)
 610         return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id)
 611
 612
 613 class VimeoGroupsIE(VimeoAlbumIE):
 614     IE_NAME = 'vimeo:group'
 615     _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)'
 616     _TESTS = [{
 617         'url': 'https://vimeo.com/groups/rolexawards',
 618         'info_dict': {
 619             'id': 'rolexawards',
 620             'title': 'Rolex Awards for Enterprise',
 621         },
 622         'playlist_mincount': 73,
 623     }]
 624
 625     def _extract_list_title(self, webpage):
 626         return self._og_search_title(webpage)
 627
 628     def _real_extract(self, url):
 629         mobj = re.match(self._VALID_URL, url)
 630         name = mobj.group('name')
 631         return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
 632
 633
 634 class VimeoReviewIE(InfoExtractor):
 635     IE_NAME = 'vimeo:review'
 636     IE_DESC = 'Review pages on vimeo'
 637     _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
 638     _TESTS = [{
 639         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
 640         'md5': 'c507a72f780cacc12b2248bb4006d253',
 641         'info_dict': {
 642             'id': '75524534',
 643             'ext': 'mp4',
 644             'title': "DICK HARDWICK 'Comedian'",
 645             'uploader': 'Richard Hardwick',
 646         }
 647     }, {
 648         'note': 'video player needs Referer',
 649         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
 650         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
 651         'info_dict': {
 652             'id': '91613211',
 653             'ext': 'mp4',
 654             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
 655             'uploader': 'DevWeek Events',
 656             'duration': 2773,
 657             'thumbnail': 're:^https?://.*\.jpg$',
 658         }
 659     }]
 660
 661     def _real_extract(self, url):
 662         mobj = re.match(self._VALID_URL, url)
 663         video_id = mobj.group('id')
 664         player_url = 'https://player.vimeo.com/player/' + video_id
 665         return self.url_result(player_url, 'Vimeo', video_id)
 666
 667
 668 class VimeoWatchLaterIE(VimeoChannelIE):
 669     IE_NAME = 'vimeo:watchlater'
 670     IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
 671     _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
 672     _TITLE = 'Watch Later'
 673     _LOGIN_REQUIRED = True
 674     _TESTS = [{
 675         'url': 'https://vimeo.com/watchlater',
 676         'only_matching': True,
 677     }]
 678
 679     def _real_initialize(self):
 680         self._login()
 681
 682     def _page_url(self, base_url, pagenum):
 683         url = '%s/page:%d/' % (base_url, pagenum)
 684         request = sanitized_Request(url)
 685         # Set the header to get a partial html page with the ids,
 686         # the normal page doesn't contain them.
 687         request.add_header('X-Requested-With', 'XMLHttpRequest')
 688         return request
 689
 690     def _real_extract(self, url):
 691         return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
 692
 693
 694 class VimeoLikesIE(InfoExtractor):
 695     _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
 696     IE_NAME = 'vimeo:likes'
 697     IE_DESC = 'Vimeo user likes'
 698     _TEST = {
 699         'url': 'https://vimeo.com/user755559/likes/',
 700         'playlist_mincount': 293,
 701         "info_dict": {
 702             'id': 'user755559_likes',
 703             "description": "See all the videos urza likes",
 704             "title": 'Videos urza likes',
 705         },
 706     }
 707
 708     def _real_extract(self, url):
 709         user_id = self._match_id(url)
 710         webpage = self._download_webpage(url, user_id)
 711         page_count = self._int(
 712             self._search_regex(
 713                 r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
 714                     .*?</a></li>\s*<li\s+class="pagination_next">
 715                 ''', webpage, 'page count'),
 716             'page count', fatal=True)
 717         PAGE_SIZE = 12
 718         title = self._html_search_regex(
 719             r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
 720         description = self._html_search_meta('description', webpage)
 721
 722         def _get_page(idx):
 723             page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
 724                 user_id, idx + 1)
 725             webpage = self._download_webpage(
 726                 page_url, user_id,
 727                 note='Downloading page %d/%d' % (idx + 1, page_count))
 728             video_list = self._search_regex(
 729                 r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
 730                 webpage, 'video content')
 731             paths = re.findall(
 732                 r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
 733             for path in paths:
 734                 yield {
 735                     '_type': 'url',
 736                     'url': compat_urlparse.urljoin(page_url, path),
 737                 }
 738
 739         pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
 740
 741         return {
 742             '_type': 'playlist',
 743             'id': 'user%s_likes' % user_id,
 744             'title': title,
 745             'description': description,
 746             'entries': pl,
 747         }