_ 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_urllib_request,
  12     compat_urlparse,
  13 )
  14 from ..utils import (
  15     encode_dict,
  16     ExtractorError,
  17     InAdvancePagedList,
  18     int_or_none,
  19     RegexNotFoundError,
  20     smuggle_url,
  21     std_headers,
  22     unified_strdate,
  23     unsmuggle_url,
  24     urlencode_postdata,
  25     unescapeHTML,
  26 )
  27
  28
  29 class VimeoBaseInfoExtractor(InfoExtractor):
  30     _NETRC_MACHINE = 'vimeo'
  31     _LOGIN_REQUIRED = False
  32     _LOGIN_URL = 'https://vimeo.com/log_in'
  33
  34     def _login(self):
  35         (username, password) = self._get_login_info()
  36         if username is None:
  37             if self._LOGIN_REQUIRED:
  38                 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
  39             return
  40         self.report_login()
  41         webpage = self._download_webpage(self._LOGIN_URL, None, False)
  42         token, vuid = self._extract_xsrft_and_vuid(webpage)
  43         data = urlencode_postdata(encode_dict({
  44             'action': 'login',
  45             'email': username,
  46             'password': password,
  47             'service': 'vimeo',
  48             'token': token,
  49         }))
  50         login_request = compat_urllib_request.Request(self._LOGIN_URL, data)
  51         login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  52         login_request.add_header('Referer', self._LOGIN_URL)
  53         self._set_vimeo_cookie('vuid', vuid)
  54         self._download_webpage(login_request, None, False, 'Wrong login info')
  55
  56     def _extract_xsrft_and_vuid(self, webpage):
  57         xsrft = self._search_regex(
  58             r'xsrft\s*[=:]\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
  59             webpage, 'login token', group='xsrft')
  60         vuid = self._search_regex(
  61             r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
  62             webpage, 'vuid', group='vuid')
  63         return xsrft, vuid
  64
  65     def _set_vimeo_cookie(self, name, value):
  66         self._set_cookie('vimeo.com', name, value)
  67
  68
  69 class VimeoIE(VimeoBaseInfoExtractor):
  70     """Information extractor for vimeo.com."""
  71
  72     # _VALID_URL matches Vimeo URLs
  73     _VALID_URL = r'''(?x)
  74         https?://
  75         (?:(?:www|(?P<player>player))\.)?
  76         vimeo(?P<pro>pro)?\.com/
  77         (?!channels/[^/?#]+/?(?:$|[?#])|album/)
  78         (?:.*?/)?
  79         (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)?
  80         (?:videos?/)?
  81         (?P<id>[0-9]+)
  82         /?(?:[?&].*)?(?:[#].*)?$'''
  83     IE_NAME = 'vimeo'
  84     _TESTS = [
  85         {
  86             'url': 'http://vimeo.com/56015672#at=0',
  87             'md5': '8879b6cc097e987f02484baf890129e5',
  88             'info_dict': {
  89                 'id': '56015672',
  90                 'ext': 'mp4',
  91                 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
  92                 'description': 'md5:2d3305bad981a06ff79f027f19865021',
  93                 'upload_date': '20121220',
  94                 'uploader_id': 'user7108434',
  95                 'uploader': 'Filippo Valsorda',
  96                 'duration': 10,
  97             },
  98         },
  99         {
 100             'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
 101             'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
 102             'note': 'Vimeo Pro video (#1197)',
 103             'info_dict': {
 104                 'id': '68093876',
 105                 'ext': 'mp4',
 106                 'uploader_id': 'openstreetmapus',
 107                 'uploader': 'OpenStreetMap US',
 108                 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
 109                 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30',
 110                 'duration': 1595,
 111             },
 112         },
 113         {
 114             'url': 'http://player.vimeo.com/video/54469442',
 115             'md5': '619b811a4417aa4abe78dc653becf511',
 116             'note': 'Videos that embed the url in the player page',
 117             'info_dict': {
 118                 'id': '54469442',
 119                 'ext': 'mp4',
 120                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
 121                 'uploader': 'The BLN & Business of Software',
 122                 'uploader_id': 'theblnbusinessofsoftware',
 123                 'duration': 3610,
 124                 'description': None,
 125             },
 126         },
 127         {
 128             'url': 'http://vimeo.com/68375962',
 129             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 130             'note': 'Video protected with password',
 131             'info_dict': {
 132                 'id': '68375962',
 133                 'ext': 'mp4',
 134                 'title': 'youtube-dl password protected test video',
 135                 'upload_date': '20130614',
 136                 'uploader_id': 'user18948128',
 137                 'uploader': 'Jaime Marquínez Ferrándiz',
 138                 'duration': 10,
 139                 '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',
 140             },
 141             'params': {
 142                 'videopassword': 'youtube-dl',
 143             },
 144         },
 145         {
 146             'url': 'http://vimeo.com/channels/keypeele/75629013',
 147             'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
 148             'note': 'Video is freely available via original URL '
 149                     'and protected with password when accessed via http://vimeo.com/75629013',
 150             'info_dict': {
 151                 'id': '75629013',
 152                 'ext': 'mp4',
 153                 'title': 'Key & Peele: Terrorist Interrogation',
 154                 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
 155                 'uploader_id': 'atencio',
 156                 'uploader': 'Peter Atencio',
 157                 'upload_date': '20130927',
 158                 'duration': 187,
 159             },
 160         },
 161         {
 162             'url': 'http://vimeo.com/76979871',
 163             'note': 'Video with subtitles',
 164             'info_dict': {
 165                 'id': '76979871',
 166                 'ext': 'mp4',
 167                 'title': 'The New Vimeo Player (You Know, For Videos)',
 168                 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
 169                 'upload_date': '20131015',
 170                 'uploader_id': 'staff',
 171                 'uploader': 'Vimeo Staff',
 172                 'duration': 62,
 173             }
 174         },
 175         {
 176             # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
 177             'url': 'https://player.vimeo.com/video/98044508',
 178             'note': 'The js code contains assignments to the same variable as the config',
 179             'info_dict': {
 180                 'id': '98044508',
 181                 'ext': 'mp4',
 182                 'title': 'Pier Solar OUYA Official Trailer',
 183                 'uploader': 'Tulio Gonçalves',
 184                 'uploader_id': 'user28849593',
 185             },
 186         },
 187         {
 188             'url': 'https://vimeo.com/109815029',
 189             'note': 'Video not completely processed, "failed" seed status',
 190             'only_matching': True,
 191         },
 192     ]
 193
 194     @staticmethod
 195     def _extract_vimeo_url(url, webpage):
 196         # Look for embedded (iframe) Vimeo player
 197         mobj = re.search(
 198             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
 199         if mobj:
 200             player_url = unescapeHTML(mobj.group('url'))
 201             surl = smuggle_url(player_url, {'Referer': url})
 202             return surl
 203         # Look for embedded (swf embed) Vimeo player
 204         mobj = re.search(
 205             r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
 206         if mobj:
 207             return mobj.group(1)
 208
 209     def _verify_video_password(self, url, video_id, webpage):
 210         password = self._downloader.params.get('videopassword', None)
 211         if password is None:
 212             raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
 213         token, vuid = self._extract_xsrft_and_vuid(webpage)
 214         data = urlencode_postdata(encode_dict({
 215             'password': password,
 216             'token': token,
 217         }))
 218         if url.startswith('http://'):
 219             # vimeo only supports https now, but the user can give an http url
 220             url = url.replace('http://', 'https://')
 221         password_request = compat_urllib_request.Request(url + '/password', data)
 222         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 223         password_request.add_header('Referer', url)
 224         self._set_vimeo_cookie('vuid', vuid)
 225         return self._download_webpage(
 226             password_request, video_id,
 227             'Verifying the password', 'Wrong password')
 228
 229     def _verify_player_video_password(self, url, video_id):
 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')
 233         data = urlencode_postdata(encode_dict({'password': password}))
 234         pass_url = url + '/check-password'
 235         password_request = compat_urllib_request.Request(pass_url, data)
 236         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 237         return self._download_json(
 238             password_request, video_id,
 239             'Verifying the password',
 240             'Wrong password')
 241
 242     def _real_initialize(self):
 243         self._login()
 244
 245     def _real_extract(self, url):
 246         url, data = unsmuggle_url(url)
 247         headers = std_headers
 248         if data is not None:
 249             headers = headers.copy()
 250             headers.update(data)
 251         if 'Referer' not in headers:
 252             headers['Referer'] = url
 253
 254         # Extract ID from URL
 255         mobj = re.match(self._VALID_URL, url)
 256         video_id = mobj.group('id')
 257         orig_url = url
 258         if mobj.group('pro') or mobj.group('player'):
 259             url = 'https://player.vimeo.com/video/' + video_id
 260         else:
 261             url = 'https://vimeo.com/' + video_id
 262
 263         # Retrieve video webpage to extract further information
 264         request = compat_urllib_request.Request(url, None, headers)
 265         try:
 266             webpage = self._download_webpage(request, video_id)
 267         except ExtractorError as ee:
 268             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
 269                 errmsg = ee.cause.read()
 270                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 271                     raise ExtractorError(
 272                         'Cannot download embed-only video without embedding '
 273                         'URL. Please call youtube-dl with the URL of the page '
 274                         'that embeds this video.',
 275                         expected=True)
 276             raise
 277
 278         # Now we begin extracting as much information as we can from what we
 279         # retrieved. First we extract the information common to all extractors,
 280         # and latter we extract those that are Vimeo specific.
 281         self.report_extraction(video_id)
 282
 283         vimeo_config = self._search_regex(
 284             r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage,
 285             'vimeo config', default=None)
 286         if vimeo_config:
 287             seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
 288             if seed_status.get('state') == 'failed':
 289                 raise ExtractorError(
 290                     '%s said: %s' % (self.IE_NAME, seed_status['title']),
 291                     expected=True)
 292
 293         # Extract the config JSON
 294         try:
 295             try:
 296                 config_url = self._html_search_regex(
 297                     r' data-config-url="(.+?)"', webpage,
 298                     'config URL', default=None)
 299                 if not config_url:
 300                     # Sometimes new react-based page is served instead of old one that require
 301                     # different config URL extraction approach (see
 302                     # https://github.com/rg3/youtube-dl/pull/7209)
 303                     vimeo_clip_page_config = self._search_regex(
 304                         r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
 305                         'vimeo clip page config')
 306                     config_url = self._parse_json(
 307                         vimeo_clip_page_config, video_id)['player']['config_url']
 308                 config_json = self._download_webpage(config_url, video_id)
 309                 config = json.loads(config_json)
 310             except RegexNotFoundError:
 311                 # For pro videos or player.vimeo.com urls
 312                 # We try to find out to which variable is assigned the config dic
 313                 m_variable_name = re.search('(\w)\.video\.id', webpage)
 314                 if m_variable_name is not None:
 315                     config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))
 316                 else:
 317                     config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
 318                 config = self._search_regex(config_re, webpage, 'info section',
 319                                             flags=re.DOTALL)
 320                 config = json.loads(config)
 321         except Exception as e:
 322             if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
 323                 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
 324
 325             if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
 326                 if data and '_video_password_verified' in data:
 327                     raise ExtractorError('video password verification failed!')
 328                 self._verify_video_password(url, video_id, webpage)
 329                 return self._real_extract(
 330                     smuggle_url(url, {'_video_password_verified': 'verified'}))
 331             else:
 332                 raise ExtractorError('Unable to extract info section',
 333                                      cause=e)
 334         else:
 335             if config.get('view') == 4:
 336                 config = self._verify_player_video_password(url, video_id)
 337
 338         # Extract title
 339         video_title = config["video"]["title"]
 340
 341         # Extract uploader and uploader_id
 342         video_uploader = config["video"]["owner"]["name"]
 343         video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None
 344
 345         # Extract video thumbnail
 346         video_thumbnail = config["video"].get("thumbnail")
 347         if video_thumbnail is None:
 348             video_thumbs = config["video"].get("thumbs")
 349             if video_thumbs and isinstance(video_thumbs, dict):
 350                 _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
 351
 352         # Extract video description
 353
 354         video_description = self._html_search_regex(
 355             r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 356             webpage, 'description', default=None)
 357         if not video_description:
 358             video_description = self._html_search_meta(
 359                 'description', webpage, default=None)
 360         if not video_description and mobj.group('pro'):
 361             orig_webpage = self._download_webpage(
 362                 orig_url, video_id,
 363                 note='Downloading webpage for description',
 364                 fatal=False)
 365             if orig_webpage:
 366                 video_description = self._html_search_meta(
 367                     'description', orig_webpage, default=None)
 368         if not video_description and not mobj.group('player'):
 369             self._downloader.report_warning('Cannot find video description')
 370
 371         # Extract video duration
 372         video_duration = int_or_none(config["video"].get("duration"))
 373
 374         # Extract upload date
 375         video_upload_date = None
 376         mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage)
 377         if mobj is not None:
 378             video_upload_date = unified_strdate(mobj.group(1))
 379
 380         try:
 381             view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
 382             like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
 383             comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
 384         except RegexNotFoundError:
 385             # This info is only available in vimeo.com/{id} urls
 386             view_count = None
 387             like_count = None
 388             comment_count = None
 389
 390         formats = []
 391         config_files = config['video'].get('files') or config['request'].get('files', {})
 392         for f in config_files.get('progressive', []):
 393             video_url = f.get('url')
 394             if not video_url:
 395                 continue
 396             formats.append({
 397                 'url': video_url,
 398                 'format_id': 'http-%s' % f.get('quality'),
 399                 'width': int_or_none(f.get('width')),
 400                 'height': int_or_none(f.get('height')),
 401                 'fps': int_or_none(f.get('fps')),
 402                 'tbr': int_or_none(f.get('bitrate')),
 403             })
 404         m3u8_url = config_files.get('hls', {}).get('url')
 405         if m3u8_url:
 406             m3u8_formats = self._extract_m3u8_formats(
 407                 m3u8_url, video_id, 'mp4', 'm3u8_native', 0, 'hls', fatal=False)
 408             if m3u8_formats:
 409                 formats.extend(m3u8_formats)
 410         # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
 411         # at the same time without actual units specified. This lead to wrong sorting.
 412         self._sort_formats(formats, field_preference=('height', 'width', 'fps', 'format_id'))
 413
 414         subtitles = {}
 415         text_tracks = config['request'].get('text_tracks')
 416         if text_tracks:
 417             for tt in text_tracks:
 418                 subtitles[tt['lang']] = [{
 419                     'ext': 'vtt',
 420                     'url': 'https://vimeo.com' + tt['url'],
 421                 }]
 422
 423         return {
 424             'id': video_id,
 425             'uploader': video_uploader,
 426             'uploader_id': video_uploader_id,
 427             'upload_date': video_upload_date,
 428             'title': video_title,
 429             'thumbnail': video_thumbnail,
 430             'description': video_description,
 431             'duration': video_duration,
 432             'formats': formats,
 433             'webpage_url': url,
 434             'view_count': view_count,
 435             'like_count': like_count,
 436             'comment_count': comment_count,
 437             'subtitles': subtitles,
 438         }
 439
 440
 441 class VimeoChannelIE(VimeoBaseInfoExtractor):
 442     IE_NAME = 'vimeo:channel'
 443     _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
 444     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
 445     _TITLE = None
 446     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
 447     _TESTS = [{
 448         'url': 'https://vimeo.com/channels/tributes',
 449         'info_dict': {
 450             'id': 'tributes',
 451             'title': 'Vimeo Tributes',
 452         },
 453         'playlist_mincount': 25,
 454     }]
 455
 456     def _page_url(self, base_url, pagenum):
 457         return '%s/videos/page:%d/' % (base_url, pagenum)
 458
 459     def _extract_list_title(self, webpage):
 460         return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title')
 461
 462     def _login_list_password(self, page_url, list_id, webpage):
 463         login_form = self._search_regex(
 464             r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
 465             webpage, 'login form', default=None)
 466         if not login_form:
 467             return webpage
 468
 469         password = self._downloader.params.get('videopassword', None)
 470         if password is None:
 471             raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
 472         fields = self._hidden_inputs(login_form)
 473         token, vuid = self._extract_xsrft_and_vuid(webpage)
 474         fields['token'] = token
 475         fields['password'] = password
 476         post = urlencode_postdata(encode_dict(fields))
 477         password_path = self._search_regex(
 478             r'action="([^"]+)"', login_form, 'password URL')
 479         password_url = compat_urlparse.urljoin(page_url, password_path)
 480         password_request = compat_urllib_request.Request(password_url, post)
 481         password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
 482         self._set_vimeo_cookie('vuid', vuid)
 483         self._set_vimeo_cookie('xsrft', token)
 484
 485         return self._download_webpage(
 486             password_request, list_id,
 487             'Verifying the password', 'Wrong password')
 488
 489     def _title_and_entries(self, list_id, base_url):
 490         for pagenum in itertools.count(1):
 491             page_url = self._page_url(base_url, pagenum)
 492             webpage = self._download_webpage(
 493                 page_url, list_id,
 494                 'Downloading page %s' % pagenum)
 495
 496             if pagenum == 1:
 497                 webpage = self._login_list_password(page_url, list_id, webpage)
 498                 yield self._extract_list_title(webpage)
 499
 500             for video_id in re.findall(r'id="clip_(\d+?)"', webpage):
 501                 yield self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo')
 502
 503             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
 504                 break
 505
 506     def _extract_videos(self, list_id, base_url):
 507         title_and_entries = self._title_and_entries(list_id, base_url)
 508         list_title = next(title_and_entries)
 509         return self.playlist_result(title_and_entries, list_id, list_title)
 510
 511     def _real_extract(self, url):
 512         mobj = re.match(self._VALID_URL, url)
 513         channel_id = mobj.group('id')
 514         return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
 515
 516
 517 class VimeoUserIE(VimeoChannelIE):
 518     IE_NAME = 'vimeo:user'
 519     _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
 520     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
 521     _TESTS = [{
 522         'url': 'https://vimeo.com/nkistudio/videos',
 523         'info_dict': {
 524             'title': 'Nki',
 525             'id': 'nkistudio',
 526         },
 527         'playlist_mincount': 66,
 528     }]
 529
 530     def _real_extract(self, url):
 531         mobj = re.match(self._VALID_URL, url)
 532         name = mobj.group('name')
 533         return self._extract_videos(name, 'https://vimeo.com/%s' % name)
 534
 535
 536 class VimeoAlbumIE(VimeoChannelIE):
 537     IE_NAME = 'vimeo:album'
 538     _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)'
 539     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
 540     _TESTS = [{
 541         'url': 'https://vimeo.com/album/2632481',
 542         'info_dict': {
 543             'id': '2632481',
 544             'title': 'Staff Favorites: November 2013',
 545         },
 546         'playlist_mincount': 13,
 547     }, {
 548         'note': 'Password-protected album',
 549         'url': 'https://vimeo.com/album/3253534',
 550         'info_dict': {
 551             'title': 'test',
 552             'id': '3253534',
 553         },
 554         'playlist_count': 1,
 555         'params': {
 556             'videopassword': 'youtube-dl',
 557         }
 558     }]
 559
 560     def _page_url(self, base_url, pagenum):
 561         return '%s/page:%d/' % (base_url, pagenum)
 562
 563     def _real_extract(self, url):
 564         album_id = self._match_id(url)
 565         return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id)
 566
 567
 568 class VimeoGroupsIE(VimeoAlbumIE):
 569     IE_NAME = 'vimeo:group'
 570     _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)'
 571     _TESTS = [{
 572         'url': 'https://vimeo.com/groups/rolexawards',
 573         'info_dict': {
 574             'id': 'rolexawards',
 575             'title': 'Rolex Awards for Enterprise',
 576         },
 577         'playlist_mincount': 73,
 578     }]
 579
 580     def _extract_list_title(self, webpage):
 581         return self._og_search_title(webpage)
 582
 583     def _real_extract(self, url):
 584         mobj = re.match(self._VALID_URL, url)
 585         name = mobj.group('name')
 586         return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
 587
 588
 589 class VimeoReviewIE(InfoExtractor):
 590     IE_NAME = 'vimeo:review'
 591     IE_DESC = 'Review pages on vimeo'
 592     _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
 593     _TESTS = [{
 594         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
 595         'md5': 'c507a72f780cacc12b2248bb4006d253',
 596         'info_dict': {
 597             'id': '75524534',
 598             'ext': 'mp4',
 599             'title': "DICK HARDWICK 'Comedian'",
 600             'uploader': 'Richard Hardwick',
 601         }
 602     }, {
 603         'note': 'video player needs Referer',
 604         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
 605         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
 606         'info_dict': {
 607             'id': '91613211',
 608             'ext': 'mp4',
 609             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
 610             'uploader': 'DevWeek Events',
 611             'duration': 2773,
 612             'thumbnail': 're:^https?://.*\.jpg$',
 613         }
 614     }]
 615
 616     def _real_extract(self, url):
 617         mobj = re.match(self._VALID_URL, url)
 618         video_id = mobj.group('id')
 619         player_url = 'https://player.vimeo.com/player/' + video_id
 620         return self.url_result(player_url, 'Vimeo', video_id)
 621
 622
 623 class VimeoWatchLaterIE(VimeoChannelIE):
 624     IE_NAME = 'vimeo:watchlater'
 625     IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
 626     _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
 627     _TITLE = 'Watch Later'
 628     _LOGIN_REQUIRED = True
 629     _TESTS = [{
 630         'url': 'https://vimeo.com/watchlater',
 631         'only_matching': True,
 632     }]
 633
 634     def _real_initialize(self):
 635         self._login()
 636
 637     def _page_url(self, base_url, pagenum):
 638         url = '%s/page:%d/' % (base_url, pagenum)
 639         request = compat_urllib_request.Request(url)
 640         # Set the header to get a partial html page with the ids,
 641         # the normal page doesn't contain them.
 642         request.add_header('X-Requested-With', 'XMLHttpRequest')
 643         return request
 644
 645     def _real_extract(self, url):
 646         return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
 647
 648
 649 class VimeoLikesIE(InfoExtractor):
 650     _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
 651     IE_NAME = 'vimeo:likes'
 652     IE_DESC = 'Vimeo user likes'
 653     _TEST = {
 654         'url': 'https://vimeo.com/user755559/likes/',
 655         'playlist_mincount': 293,
 656         "info_dict": {
 657             'id': 'user755559_likes',
 658             "description": "See all the videos urza likes",
 659             "title": 'Videos urza likes',
 660         },
 661     }
 662
 663     def _real_extract(self, url):
 664         user_id = self._match_id(url)
 665         webpage = self._download_webpage(url, user_id)
 666         page_count = self._int(
 667             self._search_regex(
 668                 r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
 669                     .*?</a></li>\s*<li\s+class="pagination_next">
 670                 ''', webpage, 'page count'),
 671             'page count', fatal=True)
 672         PAGE_SIZE = 12
 673         title = self._html_search_regex(
 674             r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
 675         description = self._html_search_meta('description', webpage)
 676
 677         def _get_page(idx):
 678             page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
 679                 user_id, idx + 1)
 680             webpage = self._download_webpage(
 681                 page_url, user_id,
 682                 note='Downloading page %d/%d' % (idx + 1, page_count))
 683             video_list = self._search_regex(
 684                 r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
 685                 webpage, 'video content')
 686             paths = re.findall(
 687                 r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
 688             for path in paths:
 689                 yield {
 690                     '_type': 'url',
 691                     'url': compat_urlparse.urljoin(page_url, path),
 692                 }
 693
 694         pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
 695
 696         return {
 697             '_type': 'playlist',
 698             'id': 'user%s_likes' % user_id,
 699             'title': title,
 700             'description': description,
 701             'entries': pl,
 702         }