_ 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     encode_dict,
  15     ExtractorError,
  16     InAdvancePagedList,
  17     int_or_none,
  18     RegexNotFoundError,
  19     sanitized_Request,
  20     smuggle_url,
  21     std_headers,
  22     unified_strdate,
  23     unsmuggle_url,
  24     urlencode_postdata,
  25     unescapeHTML,
  26     parse_filesize,
  27 )
  28
  29
  30 class VimeoBaseInfoExtractor(InfoExtractor):
  31     _NETRC_MACHINE = 'vimeo'
  32     _LOGIN_REQUIRED = False
  33     _LOGIN_URL = 'https://vimeo.com/log_in'
  34
  35     def _login(self):
  36         (username, password) = self._get_login_info()
  37         if username is None:
  38             if self._LOGIN_REQUIRED:
  39                 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
  40             return
  41         self.report_login()
  42         webpage = self._download_webpage(self._LOGIN_URL, None, False)
  43         token, vuid = self._extract_xsrft_and_vuid(webpage)
  44         data = urlencode_postdata(encode_dict({
  45             'action': 'login',
  46             'email': username,
  47             'password': password,
  48             'service': 'vimeo',
  49             'token': token,
  50         }))
  51         login_request = sanitized_Request(self._LOGIN_URL, data)
  52         login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  53         login_request.add_header('Referer', self._LOGIN_URL)
  54         self._set_vimeo_cookie('vuid', vuid)
  55         self._download_webpage(login_request, None, False, 'Wrong login info')
  56
  57     def _extract_xsrft_and_vuid(self, webpage):
  58         xsrft = self._search_regex(
  59             r'xsrft\s*[=:]\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
  60             webpage, 'login token', group='xsrft')
  61         vuid = self._search_regex(
  62             r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
  63             webpage, 'vuid', group='vuid')
  64         return xsrft, vuid
  65
  66     def _set_vimeo_cookie(self, name, value):
  67         self._set_cookie('vimeo.com', name, value)
  68
  69
  70 class VimeoIE(VimeoBaseInfoExtractor):
  71     """Information extractor for vimeo.com."""
  72
  73     # _VALID_URL matches Vimeo URLs
  74     _VALID_URL = r'''(?x)
  75         https?://
  76         (?:(?:www|(?P<player>player))\.)?
  77         vimeo(?P<pro>pro)?\.com/
  78         (?!channels/[^/?#]+/?(?:$|[?#])|album/)
  79         (?:.*?/)?
  80         (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)?
  81         (?:videos?/)?
  82         (?P<id>[0-9]+)
  83         /?(?:[?&].*)?(?:[#].*)?$'''
  84     IE_NAME = 'vimeo'
  85     _TESTS = [
  86         {
  87             'url': 'http://vimeo.com/56015672#at=0',
  88             'md5': '8879b6cc097e987f02484baf890129e5',
  89             'info_dict': {
  90                 'id': '56015672',
  91                 'ext': 'mp4',
  92                 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
  93                 'description': 'md5:2d3305bad981a06ff79f027f19865021',
  94                 'upload_date': '20121220',
  95                 'uploader_id': 'user7108434',
  96                 'uploader': 'Filippo Valsorda',
  97                 'duration': 10,
  98             },
  99         },
 100         {
 101             'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
 102             'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
 103             'note': 'Vimeo Pro video (#1197)',
 104             'info_dict': {
 105                 'id': '68093876',
 106                 'ext': 'mp4',
 107                 'uploader_id': 'openstreetmapus',
 108                 'uploader': 'OpenStreetMap US',
 109                 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
 110                 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30',
 111                 'duration': 1595,
 112             },
 113         },
 114         {
 115             'url': 'http://player.vimeo.com/video/54469442',
 116             'md5': '619b811a4417aa4abe78dc653becf511',
 117             'note': 'Videos that embed the url in the player page',
 118             'info_dict': {
 119                 'id': '54469442',
 120                 'ext': 'mp4',
 121                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
 122                 'uploader': 'The BLN & Business of Software',
 123                 'uploader_id': 'theblnbusinessofsoftware',
 124                 'duration': 3610,
 125                 'description': None,
 126             },
 127         },
 128         {
 129             'url': 'http://vimeo.com/68375962',
 130             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 131             'note': 'Video protected with password',
 132             'info_dict': {
 133                 'id': '68375962',
 134                 'ext': 'mp4',
 135                 'title': 'youtube-dl password protected test video',
 136                 'upload_date': '20130614',
 137                 'uploader_id': 'user18948128',
 138                 'uploader': 'Jaime Marquínez Ferrándiz',
 139                 'duration': 10,
 140                 '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',
 141             },
 142             'params': {
 143                 'videopassword': 'youtube-dl',
 144             },
 145         },
 146         {
 147             'url': 'http://vimeo.com/channels/keypeele/75629013',
 148             'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
 149             'note': 'Video is freely available via original URL '
 150                     'and protected with password when accessed via http://vimeo.com/75629013',
 151             'info_dict': {
 152                 'id': '75629013',
 153                 'ext': 'mp4',
 154                 'title': 'Key & Peele: Terrorist Interrogation',
 155                 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
 156                 'uploader_id': 'atencio',
 157                 'uploader': 'Peter Atencio',
 158                 'upload_date': '20130927',
 159                 'duration': 187,
 160             },
 161         },
 162         {
 163             'url': 'http://vimeo.com/76979871',
 164             'note': 'Video with subtitles',
 165             'info_dict': {
 166                 'id': '76979871',
 167                 'ext': 'mp4',
 168                 'title': 'The New Vimeo Player (You Know, For Videos)',
 169                 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
 170                 'upload_date': '20131015',
 171                 'uploader_id': 'staff',
 172                 'uploader': 'Vimeo Staff',
 173                 'duration': 62,
 174             }
 175         },
 176         {
 177             # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
 178             'url': 'https://player.vimeo.com/video/98044508',
 179             'note': 'The js code contains assignments to the same variable as the config',
 180             'info_dict': {
 181                 'id': '98044508',
 182                 'ext': 'mp4',
 183                 'title': 'Pier Solar OUYA Official Trailer',
 184                 'uploader': 'Tulio Gonçalves',
 185                 'uploader_id': 'user28849593',
 186             },
 187         },
 188         {
 189             'url': 'https://vimeo.com/109815029',
 190             'note': 'Video not completely processed, "failed" seed status',
 191             'only_matching': True,
 192         },
 193         {
 194             'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
 195             'only_matching': True,
 196         },
 197     ]
 198
 199     @staticmethod
 200     def _extract_vimeo_url(url, webpage):
 201         # Look for embedded (iframe) Vimeo player
 202         mobj = re.search(
 203             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
 204         if mobj:
 205             player_url = unescapeHTML(mobj.group('url'))
 206             surl = smuggle_url(player_url, {'Referer': url})
 207             return surl
 208         # Look for embedded (swf embed) Vimeo player
 209         mobj = re.search(
 210             r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
 211         if mobj:
 212             return mobj.group(1)
 213
 214     def _verify_video_password(self, url, video_id, webpage):
 215         password = self._downloader.params.get('videopassword', None)
 216         if password is None:
 217             raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
 218         token, vuid = self._extract_xsrft_and_vuid(webpage)
 219         data = urlencode_postdata(encode_dict({
 220             'password': password,
 221             'token': token,
 222         }))
 223         if url.startswith('http://'):
 224             # vimeo only supports https now, but the user can give an http url
 225             url = url.replace('http://', 'https://')
 226         password_request = sanitized_Request(url + '/password', data)
 227         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 228         password_request.add_header('Referer', url)
 229         self._set_vimeo_cookie('vuid', vuid)
 230         return self._download_webpage(
 231             password_request, video_id,
 232             'Verifying the password', 'Wrong password')
 233
 234     def _verify_player_video_password(self, url, video_id):
 235         password = self._downloader.params.get('videopassword', None)
 236         if password is None:
 237             raise ExtractorError('This video is protected by a password, use the --video-password option')
 238         data = urlencode_postdata(encode_dict({'password': password}))
 239         pass_url = url + '/check-password'
 240         password_request = sanitized_Request(pass_url, data)
 241         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 242         return self._download_json(
 243             password_request, video_id,
 244             'Verifying the password',
 245             'Wrong password')
 246
 247     def _real_initialize(self):
 248         self._login()
 249
 250     def _real_extract(self, url):
 251         url, data = unsmuggle_url(url)
 252         headers = std_headers
 253         if data is not None:
 254             headers = headers.copy()
 255             headers.update(data)
 256         if 'Referer' not in headers:
 257             headers['Referer'] = url
 258
 259         # Extract ID from URL
 260         mobj = re.match(self._VALID_URL, url)
 261         video_id = mobj.group('id')
 262         orig_url = url
 263         if mobj.group('pro') or mobj.group('player'):
 264             url = 'https://player.vimeo.com/video/' + video_id
 265         else:
 266             url = 'https://vimeo.com/' + video_id
 267
 268         # Retrieve video webpage to extract further information
 269         request = sanitized_Request(url, None, headers)
 270         try:
 271             webpage = self._download_webpage(request, video_id)
 272         except ExtractorError as ee:
 273             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
 274                 errmsg = ee.cause.read()
 275                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 276                     raise ExtractorError(
 277                         'Cannot download embed-only video without embedding '
 278                         'URL. Please call youtube-dl with the URL of the page '
 279                         'that embeds this video.',
 280                         expected=True)
 281             raise
 282
 283         # Now we begin extracting as much information as we can from what we
 284         # retrieved. First we extract the information common to all extractors,
 285         # and latter we extract those that are Vimeo specific.
 286         self.report_extraction(video_id)
 287
 288         vimeo_config = self._search_regex(
 289             r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage,
 290             'vimeo config', default=None)
 291         if vimeo_config:
 292             seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
 293             if seed_status.get('state') == 'failed':
 294                 raise ExtractorError(
 295                     '%s said: %s' % (self.IE_NAME, seed_status['title']),
 296                     expected=True)
 297
 298         # Extract the config JSON
 299         try:
 300             try:
 301                 config_url = self._html_search_regex(
 302                     r' data-config-url="(.+?)"', webpage,
 303                     'config URL', default=None)
 304                 if not config_url:
 305                     # Sometimes new react-based page is served instead of old one that require
 306                     # different config URL extraction approach (see
 307                     # https://github.com/rg3/youtube-dl/pull/7209)
 308                     vimeo_clip_page_config = self._search_regex(
 309                         r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
 310                         'vimeo clip page config')
 311                     config_url = self._parse_json(
 312                         vimeo_clip_page_config, video_id)['player']['config_url']
 313                 config_json = self._download_webpage(config_url, video_id)
 314                 config = json.loads(config_json)
 315             except RegexNotFoundError:
 316                 # For pro videos or player.vimeo.com urls
 317                 # We try to find out to which variable is assigned the config dic
 318                 m_variable_name = re.search('(\w)\.video\.id', webpage)
 319                 if m_variable_name is not None:
 320                     config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))
 321                 else:
 322                     config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
 323                 config = self._search_regex(config_re, webpage, 'info section',
 324                                             flags=re.DOTALL)
 325                 config = json.loads(config)
 326         except Exception as e:
 327             if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
 328                 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
 329
 330             if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
 331                 if data and '_video_password_verified' in data:
 332                     raise ExtractorError('video password verification failed!')
 333                 self._verify_video_password(url, video_id, webpage)
 334                 return self._real_extract(
 335                     smuggle_url(url, {'_video_password_verified': 'verified'}))
 336             else:
 337                 raise ExtractorError('Unable to extract info section',
 338                                      cause=e)
 339         else:
 340             if config.get('view') == 4:
 341                 config = self._verify_player_video_password(url, video_id)
 342
 343         # Extract title
 344         video_title = config["video"]["title"]
 345
 346         # Extract uploader and uploader_id
 347         video_uploader = config["video"]["owner"]["name"]
 348         video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None
 349
 350         # Extract video thumbnail
 351         video_thumbnail = config["video"].get("thumbnail")
 352         if video_thumbnail is None:
 353             video_thumbs = config["video"].get("thumbs")
 354             if video_thumbs and isinstance(video_thumbs, dict):
 355                 _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
 356
 357         # Extract video description
 358
 359         video_description = self._html_search_regex(
 360             r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 361             webpage, 'description', default=None)
 362         if not video_description:
 363             video_description = self._html_search_meta(
 364                 'description', webpage, default=None)
 365         if not video_description and mobj.group('pro'):
 366             orig_webpage = self._download_webpage(
 367                 orig_url, video_id,
 368                 note='Downloading webpage for description',
 369                 fatal=False)
 370             if orig_webpage:
 371                 video_description = self._html_search_meta(
 372                     'description', orig_webpage, default=None)
 373         if not video_description and not mobj.group('player'):
 374             self._downloader.report_warning('Cannot find video description')
 375
 376         # Extract video duration
 377         video_duration = int_or_none(config["video"].get("duration"))
 378
 379         # Extract upload date
 380         video_upload_date = None
 381         mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage)
 382         if mobj is not None:
 383             video_upload_date = unified_strdate(mobj.group(1))
 384
 385         try:
 386             view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
 387             like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
 388             comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
 389         except RegexNotFoundError:
 390             # This info is only available in vimeo.com/{id} urls
 391             view_count = None
 392             like_count = None
 393             comment_count = None
 394
 395         formats = []
 396         download_request = sanitized_Request('https://vimeo.com/%s?action=load_download_config' % video_id, headers={
 397             'X-Requested-With': 'XMLHttpRequest'})
 398         download_data = self._download_json(download_request, video_id, fatal=False)
 399         if download_data:
 400             source_file = download_data.get('source_file')
 401             if source_file and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
 402                 formats.append({
 403                     'url': source_file['download_url'],
 404                     'ext': source_file['extension'].lower(),
 405                     'width': int_or_none(source_file.get('width')),
 406                     'height': int_or_none(source_file.get('height')),
 407                     'filesize': parse_filesize(source_file.get('size')),
 408                     'format_id': source_file.get('public_name', 'Original'),
 409                     'preference': 1,
 410                 })
 411         config_files = config['video'].get('files') or config['request'].get('files', {})
 412         for f in config_files.get('progressive', []):
 413             video_url = f.get('url')
 414             if not video_url:
 415                 continue
 416             formats.append({
 417                 'url': video_url,
 418                 'format_id': 'http-%s' % f.get('quality'),
 419                 'width': int_or_none(f.get('width')),
 420                 'height': int_or_none(f.get('height')),
 421                 'fps': int_or_none(f.get('fps')),
 422                 'tbr': int_or_none(f.get('bitrate')),
 423             })
 424         m3u8_url = config_files.get('hls', {}).get('url')
 425         if m3u8_url:
 426             m3u8_formats = self._extract_m3u8_formats(
 427                 m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
 428             if m3u8_formats:
 429                 formats.extend(m3u8_formats)
 430         # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
 431         # at the same time without actual units specified. This lead to wrong sorting.
 432         self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'format_id'))
 433
 434         subtitles = {}
 435         text_tracks = config['request'].get('text_tracks')
 436         if text_tracks:
 437             for tt in text_tracks:
 438                 subtitles[tt['lang']] = [{
 439                     'ext': 'vtt',
 440                     'url': 'https://vimeo.com' + tt['url'],
 441                 }]
 442
 443         return {
 444             'id': video_id,
 445             'uploader': video_uploader,
 446             'uploader_id': video_uploader_id,
 447             'upload_date': video_upload_date,
 448             'title': video_title,
 449             'thumbnail': video_thumbnail,
 450             'description': video_description,
 451             'duration': video_duration,
 452             'formats': formats,
 453             'webpage_url': url,
 454             'view_count': view_count,
 455             'like_count': like_count,
 456             'comment_count': comment_count,
 457             'subtitles': subtitles,
 458         }
 459
 460
 461 class VimeoChannelIE(VimeoBaseInfoExtractor):
 462     IE_NAME = 'vimeo:channel'
 463     _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
 464     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
 465     _TITLE = None
 466     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
 467     _TESTS = [{
 468         'url': 'https://vimeo.com/channels/tributes',
 469         'info_dict': {
 470             'id': 'tributes',
 471             'title': 'Vimeo Tributes',
 472         },
 473         'playlist_mincount': 25,
 474     }]
 475
 476     def _page_url(self, base_url, pagenum):
 477         return '%s/videos/page:%d/' % (base_url, pagenum)
 478
 479     def _extract_list_title(self, webpage):
 480         return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title')
 481
 482     def _login_list_password(self, page_url, list_id, webpage):
 483         login_form = self._search_regex(
 484             r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
 485             webpage, 'login form', default=None)
 486         if not login_form:
 487             return webpage
 488
 489         password = self._downloader.params.get('videopassword', None)
 490         if password is None:
 491             raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
 492         fields = self._hidden_inputs(login_form)
 493         token, vuid = self._extract_xsrft_and_vuid(webpage)
 494         fields['token'] = token
 495         fields['password'] = password
 496         post = urlencode_postdata(encode_dict(fields))
 497         password_path = self._search_regex(
 498             r'action="([^"]+)"', login_form, 'password URL')
 499         password_url = compat_urlparse.urljoin(page_url, password_path)
 500         password_request = sanitized_Request(password_url, post)
 501         password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
 502         self._set_vimeo_cookie('vuid', vuid)
 503         self._set_vimeo_cookie('xsrft', token)
 504
 505         return self._download_webpage(
 506             password_request, list_id,
 507             'Verifying the password', 'Wrong password')
 508
 509     def _title_and_entries(self, list_id, base_url):
 510         for pagenum in itertools.count(1):
 511             page_url = self._page_url(base_url, pagenum)
 512             webpage = self._download_webpage(
 513                 page_url, list_id,
 514                 'Downloading page %s' % pagenum)
 515
 516             if pagenum == 1:
 517                 webpage = self._login_list_password(page_url, list_id, webpage)
 518                 yield self._extract_list_title(webpage)
 519
 520             for video_id in re.findall(r'id="clip_(\d+?)"', webpage):
 521                 yield self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo')
 522
 523             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
 524                 break
 525
 526     def _extract_videos(self, list_id, base_url):
 527         title_and_entries = self._title_and_entries(list_id, base_url)
 528         list_title = next(title_and_entries)
 529         return self.playlist_result(title_and_entries, list_id, list_title)
 530
 531     def _real_extract(self, url):
 532         mobj = re.match(self._VALID_URL, url)
 533         channel_id = mobj.group('id')
 534         return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
 535
 536
 537 class VimeoUserIE(VimeoChannelIE):
 538     IE_NAME = 'vimeo:user'
 539     _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
 540     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
 541     _TESTS = [{
 542         'url': 'https://vimeo.com/nkistudio/videos',
 543         'info_dict': {
 544             'title': 'Nki',
 545             'id': 'nkistudio',
 546         },
 547         'playlist_mincount': 66,
 548     }]
 549
 550     def _real_extract(self, url):
 551         mobj = re.match(self._VALID_URL, url)
 552         name = mobj.group('name')
 553         return self._extract_videos(name, 'https://vimeo.com/%s' % name)
 554
 555
 556 class VimeoAlbumIE(VimeoChannelIE):
 557     IE_NAME = 'vimeo:album'
 558     _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)'
 559     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
 560     _TESTS = [{
 561         'url': 'https://vimeo.com/album/2632481',
 562         'info_dict': {
 563             'id': '2632481',
 564             'title': 'Staff Favorites: November 2013',
 565         },
 566         'playlist_mincount': 13,
 567     }, {
 568         'note': 'Password-protected album',
 569         'url': 'https://vimeo.com/album/3253534',
 570         'info_dict': {
 571             'title': 'test',
 572             'id': '3253534',
 573         },
 574         'playlist_count': 1,
 575         'params': {
 576             'videopassword': 'youtube-dl',
 577         }
 578     }]
 579
 580     def _page_url(self, base_url, pagenum):
 581         return '%s/page:%d/' % (base_url, pagenum)
 582
 583     def _real_extract(self, url):
 584         album_id = self._match_id(url)
 585         return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id)
 586
 587
 588 class VimeoGroupsIE(VimeoAlbumIE):
 589     IE_NAME = 'vimeo:group'
 590     _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)'
 591     _TESTS = [{
 592         'url': 'https://vimeo.com/groups/rolexawards',
 593         'info_dict': {
 594             'id': 'rolexawards',
 595             'title': 'Rolex Awards for Enterprise',
 596         },
 597         'playlist_mincount': 73,
 598     }]
 599
 600     def _extract_list_title(self, webpage):
 601         return self._og_search_title(webpage)
 602
 603     def _real_extract(self, url):
 604         mobj = re.match(self._VALID_URL, url)
 605         name = mobj.group('name')
 606         return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
 607
 608
 609 class VimeoReviewIE(InfoExtractor):
 610     IE_NAME = 'vimeo:review'
 611     IE_DESC = 'Review pages on vimeo'
 612     _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
 613     _TESTS = [{
 614         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
 615         'md5': 'c507a72f780cacc12b2248bb4006d253',
 616         'info_dict': {
 617             'id': '75524534',
 618             'ext': 'mp4',
 619             'title': "DICK HARDWICK 'Comedian'",
 620             'uploader': 'Richard Hardwick',
 621         }
 622     }, {
 623         'note': 'video player needs Referer',
 624         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
 625         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
 626         'info_dict': {
 627             'id': '91613211',
 628             'ext': 'mp4',
 629             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
 630             'uploader': 'DevWeek Events',
 631             'duration': 2773,
 632             'thumbnail': 're:^https?://.*\.jpg$',
 633         }
 634     }]
 635
 636     def _real_extract(self, url):
 637         mobj = re.match(self._VALID_URL, url)
 638         video_id = mobj.group('id')
 639         player_url = 'https://player.vimeo.com/player/' + video_id
 640         return self.url_result(player_url, 'Vimeo', video_id)
 641
 642
 643 class VimeoWatchLaterIE(VimeoChannelIE):
 644     IE_NAME = 'vimeo:watchlater'
 645     IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
 646     _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
 647     _TITLE = 'Watch Later'
 648     _LOGIN_REQUIRED = True
 649     _TESTS = [{
 650         'url': 'https://vimeo.com/watchlater',
 651         'only_matching': True,
 652     }]
 653
 654     def _real_initialize(self):
 655         self._login()
 656
 657     def _page_url(self, base_url, pagenum):
 658         url = '%s/page:%d/' % (base_url, pagenum)
 659         request = sanitized_Request(url)
 660         # Set the header to get a partial html page with the ids,
 661         # the normal page doesn't contain them.
 662         request.add_header('X-Requested-With', 'XMLHttpRequest')
 663         return request
 664
 665     def _real_extract(self, url):
 666         return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
 667
 668
 669 class VimeoLikesIE(InfoExtractor):
 670     _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
 671     IE_NAME = 'vimeo:likes'
 672     IE_DESC = 'Vimeo user likes'
 673     _TEST = {
 674         'url': 'https://vimeo.com/user755559/likes/',
 675         'playlist_mincount': 293,
 676         "info_dict": {
 677             'id': 'user755559_likes',
 678             "description": "See all the videos urza likes",
 679             "title": 'Videos urza likes',
 680         },
 681     }
 682
 683     def _real_extract(self, url):
 684         user_id = self._match_id(url)
 685         webpage = self._download_webpage(url, user_id)
 686         page_count = self._int(
 687             self._search_regex(
 688                 r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
 689                     .*?</a></li>\s*<li\s+class="pagination_next">
 690                 ''', webpage, 'page count'),
 691             'page count', fatal=True)
 692         PAGE_SIZE = 12
 693         title = self._html_search_regex(
 694             r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
 695         description = self._html_search_meta('description', webpage)
 696
 697         def _get_page(idx):
 698             page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
 699                 user_id, idx + 1)
 700             webpage = self._download_webpage(
 701                 page_url, user_id,
 702                 note='Downloading page %d/%d' % (idx + 1, page_count))
 703             video_list = self._search_regex(
 704                 r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
 705                 webpage, 'video content')
 706             paths = re.findall(
 707                 r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
 708             for path in paths:
 709                 yield {
 710                     '_type': 'url',
 711                     'url': compat_urlparse.urljoin(page_url, path),
 712                 }
 713
 714         pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
 715
 716         return {
 717             '_type': 'playlist',
 718             'id': 'user%s_likes' % user_id,
 719             'title': title,
 720             'description': description,
 721             'entries': pl,
 722         }