_ 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'(?:(?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')
  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_url': 're:https?://(?:www\.)?vimeo\.com/user7108434',
  97                 'uploader_id': 'user7108434',
  98                 'uploader': 'Filippo Valsorda',
  99                 'duration': 10,
 100             },
 101         },
 102         {
 103             'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
 104             'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
 105             'note': 'Vimeo Pro video (#1197)',
 106             'info_dict': {
 107                 'id': '68093876',
 108                 'ext': 'mp4',
 109                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
 110                 'uploader_id': 'openstreetmapus',
 111                 'uploader': 'OpenStreetMap US',
 112                 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
 113                 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30',
 114                 'duration': 1595,
 115             },
 116         },
 117         {
 118             'url': 'http://player.vimeo.com/video/54469442',
 119             'md5': '619b811a4417aa4abe78dc653becf511',
 120             'note': 'Videos that embed the url in the player page',
 121             'info_dict': {
 122                 'id': '54469442',
 123                 'ext': 'mp4',
 124                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
 125                 'uploader': 'The BLN & Business of Software',
 126                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware',
 127                 'uploader_id': 'theblnbusinessofsoftware',
 128                 'duration': 3610,
 129                 'description': None,
 130             },
 131         },
 132         {
 133             'url': 'http://vimeo.com/68375962',
 134             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 135             'note': 'Video protected with password',
 136             'info_dict': {
 137                 'id': '68375962',
 138                 'ext': 'mp4',
 139                 'title': 'youtube-dl password protected test video',
 140                 'upload_date': '20130614',
 141                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user18948128',
 142                 'uploader_id': 'user18948128',
 143                 'uploader': 'Jaime Marquínez Ferrándiz',
 144                 'duration': 10,
 145                 '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',
 146             },
 147             'params': {
 148                 'videopassword': 'youtube-dl',
 149             },
 150         },
 151         {
 152             'url': 'http://vimeo.com/channels/keypeele/75629013',
 153             'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
 154             'note': 'Video is freely available via original URL '
 155                     'and protected with password when accessed via http://vimeo.com/75629013',
 156             'info_dict': {
 157                 'id': '75629013',
 158                 'ext': 'mp4',
 159                 'title': 'Key & Peele: Terrorist Interrogation',
 160                 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
 161                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/atencio',
 162                 'uploader_id': 'atencio',
 163                 'uploader': 'Peter Atencio',
 164                 'upload_date': '20130927',
 165                 'duration': 187,
 166             },
 167         },
 168         {
 169             'url': 'http://vimeo.com/76979871',
 170             'note': 'Video with subtitles',
 171             'info_dict': {
 172                 'id': '76979871',
 173                 'ext': 'mp4',
 174                 'title': 'The New Vimeo Player (You Know, For Videos)',
 175                 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
 176                 'upload_date': '20131015',
 177                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/staff',
 178                 'uploader_id': 'staff',
 179                 'uploader': 'Vimeo Staff',
 180                 'duration': 62,
 181             }
 182         },
 183         {
 184             # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
 185             'url': 'https://player.vimeo.com/video/98044508',
 186             'note': 'The js code contains assignments to the same variable as the config',
 187             'info_dict': {
 188                 'id': '98044508',
 189                 'ext': 'mp4',
 190                 'title': 'Pier Solar OUYA Official Trailer',
 191                 'uploader': 'Tulio Gonçalves',
 192                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user28849593',
 193                 'uploader_id': 'user28849593',
 194             },
 195         },
 196         {
 197             # contains original format
 198             'url': 'https://vimeo.com/33951933',
 199             'md5': '53c688fa95a55bf4b7293d37a89c5c53',
 200             'info_dict': {
 201                 'id': '33951933',
 202                 'ext': 'mp4',
 203                 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
 204                 'uploader': 'The DMCI',
 205                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/dmci',
 206                 'uploader_id': 'dmci',
 207                 'upload_date': '20111220',
 208                 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
 209             },
 210         },
 211         {
 212             'url': 'https://vimeo.com/109815029',
 213             'note': 'Video not completely processed, "failed" seed status',
 214             'only_matching': True,
 215         },
 216         {
 217             'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
 218             'only_matching': True,
 219         },
 220         {
 221             # source file returns 403: Forbidden
 222             'url': 'https://vimeo.com/7809605',
 223             'only_matching': True,
 224         },
 225     ]
 226
 227     @staticmethod
 228     def _extract_vimeo_url(url, webpage):
 229         # Look for embedded (iframe) Vimeo player
 230         mobj = re.search(
 231             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
 232         if mobj:
 233             player_url = unescapeHTML(mobj.group('url'))
 234             surl = smuggle_url(player_url, {'http_headers': {'Referer': url}})
 235             return surl
 236         # Look for embedded (swf embed) Vimeo player
 237         mobj = re.search(
 238             r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
 239         if mobj:
 240             return mobj.group(1)
 241
 242     def _verify_video_password(self, url, video_id, webpage):
 243         password = self._downloader.params.get('videopassword')
 244         if password is None:
 245             raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
 246         token, vuid = self._extract_xsrft_and_vuid(webpage)
 247         data = urlencode_postdata(encode_dict({
 248             'password': password,
 249             'token': token,
 250         }))
 251         if url.startswith('http://'):
 252             # vimeo only supports https now, but the user can give an http url
 253             url = url.replace('http://', 'https://')
 254         password_request = sanitized_Request(url + '/password', data)
 255         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 256         password_request.add_header('Referer', url)
 257         self._set_vimeo_cookie('vuid', vuid)
 258         return self._download_webpage(
 259             password_request, video_id,
 260             'Verifying the password', 'Wrong password')
 261
 262     def _verify_player_video_password(self, url, video_id):
 263         password = self._downloader.params.get('videopassword')
 264         if password is None:
 265             raise ExtractorError('This video is protected by a password, use the --video-password option')
 266         data = urlencode_postdata(encode_dict({'password': password}))
 267         pass_url = url + '/check-password'
 268         password_request = sanitized_Request(pass_url, data)
 269         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 270         return self._download_json(
 271             password_request, video_id,
 272             'Verifying the password',
 273             'Wrong password')
 274
 275     def _real_initialize(self):
 276         self._login()
 277
 278     def _real_extract(self, url):
 279         url, data = unsmuggle_url(url, {})
 280         headers = std_headers
 281         if 'http_headers' in data:
 282             headers = headers.copy()
 283             headers.update(data['http_headers'])
 284         if 'Referer' not in headers:
 285             headers['Referer'] = url
 286
 287         # Extract ID from URL
 288         mobj = re.match(self._VALID_URL, url)
 289         video_id = mobj.group('id')
 290         orig_url = url
 291         if mobj.group('pro') or mobj.group('player'):
 292             url = 'https://player.vimeo.com/video/' + video_id
 293         else:
 294             url = 'https://vimeo.com/' + video_id
 295
 296         # Retrieve video webpage to extract further information
 297         request = sanitized_Request(url, None, headers)
 298         try:
 299             webpage = self._download_webpage(request, video_id)
 300         except ExtractorError as ee:
 301             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
 302                 errmsg = ee.cause.read()
 303                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 304                     raise ExtractorError(
 305                         'Cannot download embed-only video without embedding '
 306                         'URL. Please call youtube-dl with the URL of the page '
 307                         'that embeds this video.',
 308                         expected=True)
 309             raise
 310
 311         # Now we begin extracting as much information as we can from what we
 312         # retrieved. First we extract the information common to all extractors,
 313         # and latter we extract those that are Vimeo specific.
 314         self.report_extraction(video_id)
 315
 316         vimeo_config = self._search_regex(
 317             r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage,
 318             'vimeo config', default=None)
 319         if vimeo_config:
 320             seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
 321             if seed_status.get('state') == 'failed':
 322                 raise ExtractorError(
 323                     '%s said: %s' % (self.IE_NAME, seed_status['title']),
 324                     expected=True)
 325
 326         # Extract the config JSON
 327         try:
 328             try:
 329                 config_url = self._html_search_regex(
 330                     r' data-config-url="(.+?)"', webpage,
 331                     'config URL', default=None)
 332                 if not config_url:
 333                     # Sometimes new react-based page is served instead of old one that require
 334                     # different config URL extraction approach (see
 335                     # https://github.com/rg3/youtube-dl/pull/7209)
 336                     vimeo_clip_page_config = self._search_regex(
 337                         r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
 338                         'vimeo clip page config')
 339                     config_url = self._parse_json(
 340                         vimeo_clip_page_config, video_id)['player']['config_url']
 341                 config_json = self._download_webpage(config_url, video_id)
 342                 config = json.loads(config_json)
 343             except RegexNotFoundError:
 344                 # For pro videos or player.vimeo.com urls
 345                 # We try to find out to which variable is assigned the config dic
 346                 m_variable_name = re.search('(\w)\.video\.id', webpage)
 347                 if m_variable_name is not None:
 348                     config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))
 349                 else:
 350                     config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
 351                 config = self._search_regex(config_re, webpage, 'info section',
 352                                             flags=re.DOTALL)
 353                 config = json.loads(config)
 354         except Exception as e:
 355             if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
 356                 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
 357
 358             if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
 359                 if '_video_password_verified' in data:
 360                     raise ExtractorError('video password verification failed!')
 361                 self._verify_video_password(url, video_id, webpage)
 362                 return self._real_extract(
 363                     smuggle_url(url, {'_video_password_verified': 'verified'}))
 364             else:
 365                 raise ExtractorError('Unable to extract info section',
 366                                      cause=e)
 367         else:
 368             if config.get('view') == 4:
 369                 config = self._verify_player_video_password(url, video_id)
 370
 371         if '>You rented this title.<' in webpage:
 372             feature_id = config.get('video', {}).get('vod', {}).get('feature_id')
 373             if feature_id and not data.get('force_feature_id', False):
 374                 return self.url_result(smuggle_url(
 375                     'https://player.vimeo.com/player/%s' % feature_id,
 376                     {'force_feature_id': True}), 'Vimeo')
 377
 378         # Extract title
 379         video_title = config['video']['title']
 380
 381         # Extract uploader, uploader_url and uploader_id
 382         video_uploader = config['video'].get('owner', {}).get('name')
 383         video_uploader_url = config['video'].get('owner', {}).get('url')
 384         video_uploader_id = video_uploader_url.split('/')[-1] if video_uploader_url else None
 385
 386         # Extract video thumbnail
 387         video_thumbnail = config['video'].get('thumbnail')
 388         if video_thumbnail is None:
 389             video_thumbs = config['video'].get('thumbs')
 390             if video_thumbs and isinstance(video_thumbs, dict):
 391                 _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
 392
 393         # Extract video description
 394
 395         video_description = self._html_search_regex(
 396             r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 397             webpage, 'description', default=None)
 398         if not video_description:
 399             video_description = self._html_search_meta(
 400                 'description', webpage, default=None)
 401         if not video_description and mobj.group('pro'):
 402             orig_webpage = self._download_webpage(
 403                 orig_url, video_id,
 404                 note='Downloading webpage for description',
 405                 fatal=False)
 406             if orig_webpage:
 407                 video_description = self._html_search_meta(
 408                     'description', orig_webpage, default=None)
 409         if not video_description and not mobj.group('player'):
 410             self._downloader.report_warning('Cannot find video description')
 411
 412         # Extract video duration
 413         video_duration = int_or_none(config['video'].get('duration'))
 414
 415         # Extract upload date
 416         video_upload_date = None
 417         mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage)
 418         if mobj is not None:
 419             video_upload_date = unified_strdate(mobj.group(1))
 420
 421         try:
 422             view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
 423             like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
 424             comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
 425         except RegexNotFoundError:
 426             # This info is only available in vimeo.com/{id} urls
 427             view_count = None
 428             like_count = None
 429             comment_count = None
 430
 431         formats = []
 432         download_request = sanitized_Request('https://vimeo.com/%s?action=load_download_config' % video_id, headers={
 433             'X-Requested-With': 'XMLHttpRequest'})
 434         download_data = self._download_json(download_request, video_id, fatal=False)
 435         if download_data:
 436             source_file = download_data.get('source_file')
 437             if isinstance(source_file, dict):
 438                 download_url = source_file.get('download_url')
 439                 if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
 440                     source_name = source_file.get('public_name', 'Original')
 441                     if self._is_valid_url(download_url, video_id, '%s video' % source_name):
 442                         ext = source_file.get('extension', determine_ext(download_url)).lower()
 443                         formats.append({
 444                             'url': download_url,
 445                             'ext': ext,
 446                             'width': int_or_none(source_file.get('width')),
 447                             'height': int_or_none(source_file.get('height')),
 448                             'filesize': parse_filesize(source_file.get('size')),
 449                             'format_id': source_name,
 450                             'preference': 1,
 451                         })
 452         config_files = config['video'].get('files') or config['request'].get('files', {})
 453         for f in config_files.get('progressive', []):
 454             video_url = f.get('url')
 455             if not video_url:
 456                 continue
 457             formats.append({
 458                 'url': video_url,
 459                 'format_id': 'http-%s' % f.get('quality'),
 460                 'width': int_or_none(f.get('width')),
 461                 'height': int_or_none(f.get('height')),
 462                 'fps': int_or_none(f.get('fps')),
 463                 'tbr': int_or_none(f.get('bitrate')),
 464             })
 465         m3u8_url = config_files.get('hls', {}).get('url')
 466         if m3u8_url:
 467             formats.extend(self._extract_m3u8_formats(
 468                 m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
 469         # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
 470         # at the same time without actual units specified. This lead to wrong sorting.
 471         self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'format_id'))
 472
 473         subtitles = {}
 474         text_tracks = config['request'].get('text_tracks')
 475         if text_tracks:
 476             for tt in text_tracks:
 477                 subtitles[tt['lang']] = [{
 478                     'ext': 'vtt',
 479                     'url': 'https://vimeo.com' + tt['url'],
 480                 }]
 481
 482         return {
 483             'id': video_id,
 484             'uploader': video_uploader,
 485             'uploader_url': video_uploader_url,
 486             'uploader_id': video_uploader_id,
 487             'upload_date': video_upload_date,
 488             'title': video_title,
 489             'thumbnail': video_thumbnail,
 490             'description': video_description,
 491             'duration': video_duration,
 492             'formats': formats,
 493             'webpage_url': url,
 494             'view_count': view_count,
 495             'like_count': like_count,
 496             'comment_count': comment_count,
 497             'subtitles': subtitles,
 498         }
 499
 500
 501 class VimeoChannelIE(VimeoBaseInfoExtractor):
 502     IE_NAME = 'vimeo:channel'
 503     _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
 504     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
 505     _TITLE = None
 506     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
 507     _TESTS = [{
 508         'url': 'https://vimeo.com/channels/tributes',
 509         'info_dict': {
 510             'id': 'tributes',
 511             'title': 'Vimeo Tributes',
 512         },
 513         'playlist_mincount': 25,
 514     }]
 515
 516     def _page_url(self, base_url, pagenum):
 517         return '%s/videos/page:%d/' % (base_url, pagenum)
 518
 519     def _extract_list_title(self, webpage):
 520         return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title')
 521
 522     def _login_list_password(self, page_url, list_id, webpage):
 523         login_form = self._search_regex(
 524             r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
 525             webpage, 'login form', default=None)
 526         if not login_form:
 527             return webpage
 528
 529         password = self._downloader.params.get('videopassword')
 530         if password is None:
 531             raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
 532         fields = self._hidden_inputs(login_form)
 533         token, vuid = self._extract_xsrft_and_vuid(webpage)
 534         fields['token'] = token
 535         fields['password'] = password
 536         post = urlencode_postdata(encode_dict(fields))
 537         password_path = self._search_regex(
 538             r'action="([^"]+)"', login_form, 'password URL')
 539         password_url = compat_urlparse.urljoin(page_url, password_path)
 540         password_request = sanitized_Request(password_url, post)
 541         password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
 542         self._set_vimeo_cookie('vuid', vuid)
 543         self._set_vimeo_cookie('xsrft', token)
 544
 545         return self._download_webpage(
 546             password_request, list_id,
 547             'Verifying the password', 'Wrong password')
 548
 549     def _title_and_entries(self, list_id, base_url):
 550         for pagenum in itertools.count(1):
 551             page_url = self._page_url(base_url, pagenum)
 552             webpage = self._download_webpage(
 553                 page_url, list_id,
 554                 'Downloading page %s' % pagenum)
 555
 556             if pagenum == 1:
 557                 webpage = self._login_list_password(page_url, list_id, webpage)
 558                 yield self._extract_list_title(webpage)
 559
 560             for video_id in re.findall(r'id="clip_(\d+?)"', webpage):
 561                 yield self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo')
 562
 563             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
 564                 break
 565
 566     def _extract_videos(self, list_id, base_url):
 567         title_and_entries = self._title_and_entries(list_id, base_url)
 568         list_title = next(title_and_entries)
 569         return self.playlist_result(title_and_entries, list_id, list_title)
 570
 571     def _real_extract(self, url):
 572         mobj = re.match(self._VALID_URL, url)
 573         channel_id = mobj.group('id')
 574         return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
 575
 576
 577 class VimeoUserIE(VimeoChannelIE):
 578     IE_NAME = 'vimeo:user'
 579     _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
 580     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
 581     _TESTS = [{
 582         'url': 'https://vimeo.com/nkistudio/videos',
 583         'info_dict': {
 584             'title': 'Nki',
 585             'id': 'nkistudio',
 586         },
 587         'playlist_mincount': 66,
 588     }]
 589
 590     def _real_extract(self, url):
 591         mobj = re.match(self._VALID_URL, url)
 592         name = mobj.group('name')
 593         return self._extract_videos(name, 'https://vimeo.com/%s' % name)
 594
 595
 596 class VimeoAlbumIE(VimeoChannelIE):
 597     IE_NAME = 'vimeo:album'
 598     _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)'
 599     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
 600     _TESTS = [{
 601         'url': 'https://vimeo.com/album/2632481',
 602         'info_dict': {
 603             'id': '2632481',
 604             'title': 'Staff Favorites: November 2013',
 605         },
 606         'playlist_mincount': 13,
 607     }, {
 608         'note': 'Password-protected album',
 609         'url': 'https://vimeo.com/album/3253534',
 610         'info_dict': {
 611             'title': 'test',
 612             'id': '3253534',
 613         },
 614         'playlist_count': 1,
 615         'params': {
 616             'videopassword': 'youtube-dl',
 617         }
 618     }]
 619
 620     def _page_url(self, base_url, pagenum):
 621         return '%s/page:%d/' % (base_url, pagenum)
 622
 623     def _real_extract(self, url):
 624         album_id = self._match_id(url)
 625         return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id)
 626
 627
 628 class VimeoGroupsIE(VimeoAlbumIE):
 629     IE_NAME = 'vimeo:group'
 630     _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)'
 631     _TESTS = [{
 632         'url': 'https://vimeo.com/groups/rolexawards',
 633         'info_dict': {
 634             'id': 'rolexawards',
 635             'title': 'Rolex Awards for Enterprise',
 636         },
 637         'playlist_mincount': 73,
 638     }]
 639
 640     def _extract_list_title(self, webpage):
 641         return self._og_search_title(webpage)
 642
 643     def _real_extract(self, url):
 644         mobj = re.match(self._VALID_URL, url)
 645         name = mobj.group('name')
 646         return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
 647
 648
 649 class VimeoReviewIE(InfoExtractor):
 650     IE_NAME = 'vimeo:review'
 651     IE_DESC = 'Review pages on vimeo'
 652     _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
 653     _TESTS = [{
 654         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
 655         'md5': 'c507a72f780cacc12b2248bb4006d253',
 656         'info_dict': {
 657             'id': '75524534',
 658             'ext': 'mp4',
 659             'title': "DICK HARDWICK 'Comedian'",
 660             'uploader': 'Richard Hardwick',
 661         }
 662     }, {
 663         'note': 'video player needs Referer',
 664         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
 665         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
 666         'info_dict': {
 667             'id': '91613211',
 668             'ext': 'mp4',
 669             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
 670             'uploader': 'DevWeek Events',
 671             'duration': 2773,
 672             'thumbnail': 're:^https?://.*\.jpg$',
 673         }
 674     }]
 675
 676     def _real_extract(self, url):
 677         mobj = re.match(self._VALID_URL, url)
 678         video_id = mobj.group('id')
 679         player_url = 'https://player.vimeo.com/player/' + video_id
 680         return self.url_result(player_url, 'Vimeo', video_id)
 681
 682
 683 class VimeoWatchLaterIE(VimeoChannelIE):
 684     IE_NAME = 'vimeo:watchlater'
 685     IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
 686     _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
 687     _TITLE = 'Watch Later'
 688     _LOGIN_REQUIRED = True
 689     _TESTS = [{
 690         'url': 'https://vimeo.com/watchlater',
 691         'only_matching': True,
 692     }]
 693
 694     def _real_initialize(self):
 695         self._login()
 696
 697     def _page_url(self, base_url, pagenum):
 698         url = '%s/page:%d/' % (base_url, pagenum)
 699         request = sanitized_Request(url)
 700         # Set the header to get a partial html page with the ids,
 701         # the normal page doesn't contain them.
 702         request.add_header('X-Requested-With', 'XMLHttpRequest')
 703         return request
 704
 705     def _real_extract(self, url):
 706         return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
 707
 708
 709 class VimeoLikesIE(InfoExtractor):
 710     _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
 711     IE_NAME = 'vimeo:likes'
 712     IE_DESC = 'Vimeo user likes'
 713     _TEST = {
 714         'url': 'https://vimeo.com/user755559/likes/',
 715         'playlist_mincount': 293,
 716         'info_dict': {
 717             'id': 'user755559_likes',
 718             'description': 'See all the videos urza likes',
 719             'title': 'Videos urza likes',
 720         },
 721     }
 722
 723     def _real_extract(self, url):
 724         user_id = self._match_id(url)
 725         webpage = self._download_webpage(url, user_id)
 726         page_count = self._int(
 727             self._search_regex(
 728                 r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
 729                     .*?</a></li>\s*<li\s+class="pagination_next">
 730                 ''', webpage, 'page count'),
 731             'page count', fatal=True)
 732         PAGE_SIZE = 12
 733         title = self._html_search_regex(
 734             r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
 735         description = self._html_search_meta('description', webpage)
 736
 737         def _get_page(idx):
 738             page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
 739                 user_id, idx + 1)
 740             webpage = self._download_webpage(
 741                 page_url, user_id,
 742                 note='Downloading page %d/%d' % (idx + 1, page_count))
 743             video_list = self._search_regex(
 744                 r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
 745                 webpage, 'video content')
 746             paths = re.findall(
 747                 r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
 748             for path in paths:
 749                 yield {
 750                     '_type': 'url',
 751                     'url': compat_urlparse.urljoin(page_url, path),
 752                 }
 753
 754         pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
 755
 756         return {
 757             '_type': 'playlist',
 758             'id': 'user%s_likes' % user_id,
 759             'title': title,
 760             'description': description,
 761             'entries': pl,
 762         }