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     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({
  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'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|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     def _vimeo_sort_formats(self, formats):
  70         # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
  71         # at the same time without actual units specified. This lead to wrong sorting.
  72         self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'format_id'))
  73
  74     def _parse_config(self, config, video_id):
  75         # Extract title
  76         video_title = config['video']['title']
  77
  78         # Extract uploader, uploader_url and uploader_id
  79         video_uploader = config['video'].get('owner', {}).get('name')
  80         video_uploader_url = config['video'].get('owner', {}).get('url')
  81         video_uploader_id = video_uploader_url.split('/')[-1] if video_uploader_url else None
  82
  83         # Extract video thumbnail
  84         video_thumbnail = config['video'].get('thumbnail')
  85         if video_thumbnail is None:
  86             video_thumbs = config['video'].get('thumbs')
  87             if video_thumbs and isinstance(video_thumbs, dict):
  88                 _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
  89
  90         # Extract video duration
  91         video_duration = int_or_none(config['video'].get('duration'))
  92
  93         formats = []
  94         config_files = config['video'].get('files') or config['request'].get('files', {})
  95         for f in config_files.get('progressive', []):
  96             video_url = f.get('url')
  97             if not video_url:
  98                 continue
  99             formats.append({
 100                 'url': video_url,
 101                 'format_id': 'http-%s' % f.get('quality'),
 102                 'width': int_or_none(f.get('width')),
 103                 'height': int_or_none(f.get('height')),
 104                 'fps': int_or_none(f.get('fps')),
 105                 'tbr': int_or_none(f.get('bitrate')),
 106             })
 107         m3u8_url = config_files.get('hls', {}).get('url')
 108         if m3u8_url:
 109             formats.extend(self._extract_m3u8_formats(
 110                 m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
 111
 112         subtitles = {}
 113         text_tracks = config['request'].get('text_tracks')
 114         if text_tracks:
 115             for tt in text_tracks:
 116                 subtitles[tt['lang']] = [{
 117                     'ext': 'vtt',
 118                     'url': 'https://vimeo.com' + tt['url'],
 119                 }]
 120
 121         return {
 122             'title': video_title,
 123             'uploader': video_uploader,
 124             'uploader_id': video_uploader_id,
 125             'uploader_url': video_uploader_url,
 126             'thumbnail': video_thumbnail,
 127             'duration': video_duration,
 128             'formats': formats,
 129             'subtitles': subtitles,
 130         }
 131
 132
 133 class VimeoIE(VimeoBaseInfoExtractor):
 134     """Information extractor for vimeo.com."""
 135
 136     # _VALID_URL matches Vimeo URLs
 137     _VALID_URL = r'''(?x)
 138                     https?://
 139                         (?:
 140                             (?:
 141                                 www|
 142                                 (?P<player>player)
 143                             )
 144                             \.
 145                         )?
 146                         vimeo(?P<pro>pro)?\.com/
 147                         (?!channels/[^/?#]+/?(?:$|[?#])|[^/]+/review/|(?:album|ondemand)/)
 148                         (?:.*?/)?
 149                         (?:
 150                             (?:
 151                                 play_redirect_hls|
 152                                 moogaloop\.swf)\?clip_id=
 153                             )?
 154                         (?:videos?/)?
 155                         (?P<id>[0-9]+)
 156                         (?:/[\da-f]+)?
 157                         /?(?:[?&].*)?(?:[#].*)?$
 158                     '''
 159     IE_NAME = 'vimeo'
 160     _TESTS = [
 161         {
 162             'url': 'http://vimeo.com/56015672#at=0',
 163             'md5': '8879b6cc097e987f02484baf890129e5',
 164             'info_dict': {
 165                 'id': '56015672',
 166                 'ext': 'mp4',
 167                 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
 168                 'description': 'md5:2d3305bad981a06ff79f027f19865021',
 169                 'upload_date': '20121220',
 170                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user7108434',
 171                 'uploader_id': 'user7108434',
 172                 'uploader': 'Filippo Valsorda',
 173                 'duration': 10,
 174             },
 175         },
 176         {
 177             'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
 178             'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
 179             'note': 'Vimeo Pro video (#1197)',
 180             'info_dict': {
 181                 'id': '68093876',
 182                 'ext': 'mp4',
 183                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
 184                 'uploader_id': 'openstreetmapus',
 185                 'uploader': 'OpenStreetMap US',
 186                 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
 187                 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30',
 188                 'duration': 1595,
 189             },
 190         },
 191         {
 192             'url': 'http://player.vimeo.com/video/54469442',
 193             'md5': '619b811a4417aa4abe78dc653becf511',
 194             'note': 'Videos that embed the url in the player page',
 195             'info_dict': {
 196                 'id': '54469442',
 197                 'ext': 'mp4',
 198                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
 199                 'uploader': 'The BLN & Business of Software',
 200                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware',
 201                 'uploader_id': 'theblnbusinessofsoftware',
 202                 'duration': 3610,
 203                 'description': None,
 204             },
 205         },
 206         {
 207             'url': 'http://vimeo.com/68375962',
 208             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 209             'note': 'Video protected with password',
 210             'info_dict': {
 211                 'id': '68375962',
 212                 'ext': 'mp4',
 213                 'title': 'youtube-dl password protected test video',
 214                 'upload_date': '20130614',
 215                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user18948128',
 216                 'uploader_id': 'user18948128',
 217                 'uploader': 'Jaime Marquínez Ferrándiz',
 218                 'duration': 10,
 219                 'description': 'This is "youtube-dl password protected test video" by  on Vimeo, the home for high quality videos and the people who love them.',
 220             },
 221             'params': {
 222                 'videopassword': 'youtube-dl',
 223             },
 224         },
 225         {
 226             'url': 'http://vimeo.com/channels/keypeele/75629013',
 227             'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
 228             'note': 'Video is freely available via original URL '
 229                     'and protected with password when accessed via http://vimeo.com/75629013',
 230             'info_dict': {
 231                 'id': '75629013',
 232                 'ext': 'mp4',
 233                 'title': 'Key & Peele: Terrorist Interrogation',
 234                 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
 235                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/atencio',
 236                 'uploader_id': 'atencio',
 237                 'uploader': 'Peter Atencio',
 238                 'upload_date': '20130927',
 239                 'duration': 187,
 240             },
 241         },
 242         {
 243             'url': 'http://vimeo.com/76979871',
 244             'note': 'Video with subtitles',
 245             'info_dict': {
 246                 'id': '76979871',
 247                 'ext': 'mp4',
 248                 'title': 'The New Vimeo Player (You Know, For Videos)',
 249                 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
 250                 'upload_date': '20131015',
 251                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/staff',
 252                 'uploader_id': 'staff',
 253                 'uploader': 'Vimeo Staff',
 254                 'duration': 62,
 255             }
 256         },
 257         {
 258             # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
 259             'url': 'https://player.vimeo.com/video/98044508',
 260             'note': 'The js code contains assignments to the same variable as the config',
 261             'info_dict': {
 262                 'id': '98044508',
 263                 'ext': 'mp4',
 264                 'title': 'Pier Solar OUYA Official Trailer',
 265                 'uploader': 'Tulio Gonçalves',
 266                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user28849593',
 267                 'uploader_id': 'user28849593',
 268             },
 269         },
 270         {
 271             # contains original format
 272             'url': 'https://vimeo.com/33951933',
 273             'md5': '53c688fa95a55bf4b7293d37a89c5c53',
 274             'info_dict': {
 275                 'id': '33951933',
 276                 'ext': 'mp4',
 277                 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
 278                 'uploader': 'The DMCI',
 279                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/dmci',
 280                 'uploader_id': 'dmci',
 281                 'upload_date': '20111220',
 282                 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
 283             },
 284         },
 285         {
 286             'url': 'https://vimeo.com/109815029',
 287             'note': 'Video not completely processed, "failed" seed status',
 288             'only_matching': True,
 289         },
 290         {
 291             'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
 292             'only_matching': True,
 293         },
 294         {
 295             # source file returns 403: Forbidden
 296             'url': 'https://vimeo.com/7809605',
 297             'only_matching': True,
 298         },
 299         {
 300             'url': 'https://vimeo.com/160743502/abd0e13fb4',
 301             'only_matching': True,
 302         }
 303     ]
 304
 305     @staticmethod
 306     def _extract_vimeo_url(url, webpage):
 307         # Look for embedded (iframe) Vimeo player
 308         mobj = re.search(
 309             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
 310         if mobj:
 311             player_url = unescapeHTML(mobj.group('url'))
 312             surl = smuggle_url(player_url, {'http_headers': {'Referer': url}})
 313             return surl
 314         # Look for embedded (swf embed) Vimeo player
 315         mobj = re.search(
 316             r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
 317         if mobj:
 318             return mobj.group(1)
 319
 320     def _verify_video_password(self, url, video_id, webpage):
 321         password = self._downloader.params.get('videopassword')
 322         if password is None:
 323             raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
 324         token, vuid = self._extract_xsrft_and_vuid(webpage)
 325         data = urlencode_postdata({
 326             'password': password,
 327             'token': token,
 328         })
 329         if url.startswith('http://'):
 330             # vimeo only supports https now, but the user can give an http url
 331             url = url.replace('http://', 'https://')
 332         password_request = sanitized_Request(url + '/password', data)
 333         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 334         password_request.add_header('Referer', url)
 335         self._set_vimeo_cookie('vuid', vuid)
 336         return self._download_webpage(
 337             password_request, video_id,
 338             'Verifying the password', 'Wrong password')
 339
 340     def _verify_player_video_password(self, url, video_id):
 341         password = self._downloader.params.get('videopassword')
 342         if password is None:
 343             raise ExtractorError('This video is protected by a password, use the --video-password option')
 344         data = urlencode_postdata({'password': password})
 345         pass_url = url + '/check-password'
 346         password_request = sanitized_Request(pass_url, data)
 347         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 348         password_request.add_header('Referer', url)
 349         return self._download_json(
 350             password_request, video_id,
 351             'Verifying the password', 'Wrong password')
 352
 353     def _real_initialize(self):
 354         self._login()
 355
 356     def _real_extract(self, url):
 357         url, data = unsmuggle_url(url, {})
 358         headers = std_headers.copy()
 359         if 'http_headers' in data:
 360             headers.update(data['http_headers'])
 361         if 'Referer' not in headers:
 362             headers['Referer'] = url
 363
 364         # Extract ID from URL
 365         mobj = re.match(self._VALID_URL, url)
 366         video_id = mobj.group('id')
 367         orig_url = url
 368         if mobj.group('pro') or mobj.group('player'):
 369             url = 'https://player.vimeo.com/video/' + video_id
 370         else:
 371             url = 'https://vimeo.com/' + video_id
 372
 373         # Retrieve video webpage to extract further information
 374         request = sanitized_Request(url, headers=headers)
 375         try:
 376             webpage = self._download_webpage(request, video_id)
 377         except ExtractorError as ee:
 378             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
 379                 errmsg = ee.cause.read()
 380                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 381                     raise ExtractorError(
 382                         'Cannot download embed-only video without embedding '
 383                         'URL. Please call youtube-dl with the URL of the page '
 384                         'that embeds this video.',
 385                         expected=True)
 386             raise
 387
 388         # Now we begin extracting as much information as we can from what we
 389         # retrieved. First we extract the information common to all extractors,
 390         # and latter we extract those that are Vimeo specific.
 391         self.report_extraction(video_id)
 392
 393         vimeo_config = self._search_regex(
 394             r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage,
 395             'vimeo config', default=None)
 396         if vimeo_config:
 397             seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
 398             if seed_status.get('state') == 'failed':
 399                 raise ExtractorError(
 400                     '%s said: %s' % (self.IE_NAME, seed_status['title']),
 401                     expected=True)
 402
 403         # Extract the config JSON
 404         try:
 405             try:
 406                 config_url = self._html_search_regex(
 407                     r' data-config-url="(.+?)"', webpage,
 408                     'config URL', default=None)
 409                 if not config_url:
 410                     # Sometimes new react-based page is served instead of old one that require
 411                     # different config URL extraction approach (see
 412                     # https://github.com/rg3/youtube-dl/pull/7209)
 413                     vimeo_clip_page_config = self._search_regex(
 414                         r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
 415                         'vimeo clip page config')
 416                     config_url = self._parse_json(
 417                         vimeo_clip_page_config, video_id)['player']['config_url']
 418                 config_json = self._download_webpage(config_url, video_id)
 419                 config = json.loads(config_json)
 420             except RegexNotFoundError:
 421                 # For pro videos or player.vimeo.com urls
 422                 # We try to find out to which variable is assigned the config dic
 423                 m_variable_name = re.search('(\w)\.video\.id', webpage)
 424                 if m_variable_name is not None:
 425                     config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))
 426                 else:
 427                     config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
 428                 config = self._search_regex(config_re, webpage, 'info section',
 429                                             flags=re.DOTALL)
 430                 config = json.loads(config)
 431         except Exception as e:
 432             if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
 433                 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
 434
 435             if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
 436                 if '_video_password_verified' in data:
 437                     raise ExtractorError('video password verification failed!')
 438                 self._verify_video_password(url, video_id, webpage)
 439                 return self._real_extract(
 440                     smuggle_url(url, {'_video_password_verified': 'verified'}))
 441             else:
 442                 raise ExtractorError('Unable to extract info section',
 443                                      cause=e)
 444         else:
 445             if config.get('view') == 4:
 446                 config = self._verify_player_video_password(url, video_id)
 447
 448         if '>You rented this title.<' in webpage:
 449             feature_id = config.get('video', {}).get('vod', {}).get('feature_id')
 450             if feature_id and not data.get('force_feature_id', False):
 451                 return self.url_result(smuggle_url(
 452                     'https://player.vimeo.com/player/%s' % feature_id,
 453                     {'force_feature_id': True}), 'Vimeo')
 454
 455         # Extract video description
 456
 457         video_description = self._html_search_regex(
 458             r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 459             webpage, 'description', default=None)
 460         if not video_description:
 461             video_description = self._html_search_meta(
 462                 'description', webpage, default=None)
 463         if not video_description and mobj.group('pro'):
 464             orig_webpage = self._download_webpage(
 465                 orig_url, video_id,
 466                 note='Downloading webpage for description',
 467                 fatal=False)
 468             if orig_webpage:
 469                 video_description = self._html_search_meta(
 470                     'description', orig_webpage, default=None)
 471         if not video_description and not mobj.group('player'):
 472             self._downloader.report_warning('Cannot find video description')
 473
 474         # Extract upload date
 475         video_upload_date = None
 476         mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage)
 477         if mobj is not None:
 478             video_upload_date = unified_strdate(mobj.group(1))
 479
 480         try:
 481             view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
 482             like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
 483             comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
 484         except RegexNotFoundError:
 485             # This info is only available in vimeo.com/{id} urls
 486             view_count = None
 487             like_count = None
 488             comment_count = None
 489
 490         formats = []
 491         download_request = sanitized_Request('https://vimeo.com/%s?action=load_download_config' % video_id, headers={
 492             'X-Requested-With': 'XMLHttpRequest'})
 493         download_data = self._download_json(download_request, video_id, fatal=False)
 494         if download_data:
 495             source_file = download_data.get('source_file')
 496             if isinstance(source_file, dict):
 497                 download_url = source_file.get('download_url')
 498                 if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
 499                     source_name = source_file.get('public_name', 'Original')
 500                     if self._is_valid_url(download_url, video_id, '%s video' % source_name):
 501                         ext = source_file.get('extension', determine_ext(download_url)).lower()
 502                         formats.append({
 503                             'url': download_url,
 504                             'ext': ext,
 505                             'width': int_or_none(source_file.get('width')),
 506                             'height': int_or_none(source_file.get('height')),
 507                             'filesize': parse_filesize(source_file.get('size')),
 508                             'format_id': source_name,
 509                             'preference': 1,
 510                         })
 511
 512         info_dict = self._parse_config(config, video_id)
 513         formats.extend(info_dict['formats'])
 514         self._vimeo_sort_formats(formats)
 515         info_dict.update({
 516             'id': video_id,
 517             'formats': formats,
 518             'upload_date': video_upload_date,
 519             'description': video_description,
 520             'webpage_url': url,
 521             'view_count': view_count,
 522             'like_count': like_count,
 523             'comment_count': comment_count,
 524         })
 525
 526         return info_dict
 527
 528
 529 class VimeoOndemandIE(VimeoBaseInfoExtractor):
 530     IE_NAME = 'vimeo:ondemand'
 531     _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?P<id>[^/?#&]+)'
 532     _TESTS = [{
 533         # ondemand video not available via https://vimeo.com/id
 534         'url': 'https://vimeo.com/ondemand/20704',
 535         'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
 536         'info_dict': {
 537             'id': '105442900',
 538             'ext': 'mp4',
 539             'title': 'המעבדה - במאי יותם פלדמן',
 540             'uploader': 'גם סרטים',
 541             'uploader_url': 're:https?://(?:www\.)?vimeo\.com/gumfilms',
 542             'uploader_id': 'gumfilms',
 543         },
 544     }, {
 545         'url': 'https://vimeo.com/ondemand/nazmaalik',
 546         'only_matching': True,
 547     }, {
 548         'url': 'https://vimeo.com/ondemand/141692381',
 549         'only_matching': True,
 550     }, {
 551         'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
 552         'only_matching': True,
 553     }]
 554
 555     def _real_extract(self, url):
 556         video_id = self._match_id(url)
 557         webpage = self._download_webpage(url, video_id)
 558         return self.url_result(self._og_search_video_url(webpage), VimeoIE.ie_key())
 559
 560
 561 class VimeoChannelIE(VimeoBaseInfoExtractor):
 562     IE_NAME = 'vimeo:channel'
 563     _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
 564     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
 565     _TITLE = None
 566     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
 567     _TESTS = [{
 568         'url': 'https://vimeo.com/channels/tributes',
 569         'info_dict': {
 570             'id': 'tributes',
 571             'title': 'Vimeo Tributes',
 572         },
 573         'playlist_mincount': 25,
 574     }]
 575
 576     def _page_url(self, base_url, pagenum):
 577         return '%s/videos/page:%d/' % (base_url, pagenum)
 578
 579     def _extract_list_title(self, webpage):
 580         return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title')
 581
 582     def _login_list_password(self, page_url, list_id, webpage):
 583         login_form = self._search_regex(
 584             r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
 585             webpage, 'login form', default=None)
 586         if not login_form:
 587             return webpage
 588
 589         password = self._downloader.params.get('videopassword')
 590         if password is None:
 591             raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
 592         fields = self._hidden_inputs(login_form)
 593         token, vuid = self._extract_xsrft_and_vuid(webpage)
 594         fields['token'] = token
 595         fields['password'] = password
 596         post = urlencode_postdata(fields)
 597         password_path = self._search_regex(
 598             r'action="([^"]+)"', login_form, 'password URL')
 599         password_url = compat_urlparse.urljoin(page_url, password_path)
 600         password_request = sanitized_Request(password_url, post)
 601         password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
 602         self._set_vimeo_cookie('vuid', vuid)
 603         self._set_vimeo_cookie('xsrft', token)
 604
 605         return self._download_webpage(
 606             password_request, list_id,
 607             'Verifying the password', 'Wrong password')
 608
 609     def _title_and_entries(self, list_id, base_url):
 610         for pagenum in itertools.count(1):
 611             page_url = self._page_url(base_url, pagenum)
 612             webpage = self._download_webpage(
 613                 page_url, list_id,
 614                 'Downloading page %s' % pagenum)
 615
 616             if pagenum == 1:
 617                 webpage = self._login_list_password(page_url, list_id, webpage)
 618                 yield self._extract_list_title(webpage)
 619
 620             for video_id in re.findall(r'id="clip_(\d+?)"', webpage):
 621                 yield self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo')
 622
 623             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
 624                 break
 625
 626     def _extract_videos(self, list_id, base_url):
 627         title_and_entries = self._title_and_entries(list_id, base_url)
 628         list_title = next(title_and_entries)
 629         return self.playlist_result(title_and_entries, list_id, list_title)
 630
 631     def _real_extract(self, url):
 632         mobj = re.match(self._VALID_URL, url)
 633         channel_id = mobj.group('id')
 634         return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
 635
 636
 637 class VimeoUserIE(VimeoChannelIE):
 638     IE_NAME = 'vimeo:user'
 639     _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
 640     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
 641     _TESTS = [{
 642         'url': 'https://vimeo.com/nkistudio/videos',
 643         'info_dict': {
 644             'title': 'Nki',
 645             'id': 'nkistudio',
 646         },
 647         'playlist_mincount': 66,
 648     }]
 649
 650     def _real_extract(self, url):
 651         mobj = re.match(self._VALID_URL, url)
 652         name = mobj.group('name')
 653         return self._extract_videos(name, 'https://vimeo.com/%s' % name)
 654
 655
 656 class VimeoAlbumIE(VimeoChannelIE):
 657     IE_NAME = 'vimeo:album'
 658     _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)'
 659     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
 660     _TESTS = [{
 661         'url': 'https://vimeo.com/album/2632481',
 662         'info_dict': {
 663             'id': '2632481',
 664             'title': 'Staff Favorites: November 2013',
 665         },
 666         'playlist_mincount': 13,
 667     }, {
 668         'note': 'Password-protected album',
 669         'url': 'https://vimeo.com/album/3253534',
 670         'info_dict': {
 671             'title': 'test',
 672             'id': '3253534',
 673         },
 674         'playlist_count': 1,
 675         'params': {
 676             'videopassword': 'youtube-dl',
 677         }
 678     }]
 679
 680     def _page_url(self, base_url, pagenum):
 681         return '%s/page:%d/' % (base_url, pagenum)
 682
 683     def _real_extract(self, url):
 684         album_id = self._match_id(url)
 685         return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id)
 686
 687
 688 class VimeoGroupsIE(VimeoAlbumIE):
 689     IE_NAME = 'vimeo:group'
 690     _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)'
 691     _TESTS = [{
 692         'url': 'https://vimeo.com/groups/rolexawards',
 693         'info_dict': {
 694             'id': 'rolexawards',
 695             'title': 'Rolex Awards for Enterprise',
 696         },
 697         'playlist_mincount': 73,
 698     }]
 699
 700     def _extract_list_title(self, webpage):
 701         return self._og_search_title(webpage)
 702
 703     def _real_extract(self, url):
 704         mobj = re.match(self._VALID_URL, url)
 705         name = mobj.group('name')
 706         return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
 707
 708
 709 class VimeoReviewIE(VimeoBaseInfoExtractor):
 710     IE_NAME = 'vimeo:review'
 711     IE_DESC = 'Review pages on vimeo'
 712     _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
 713     _TESTS = [{
 714         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
 715         'md5': 'c507a72f780cacc12b2248bb4006d253',
 716         'info_dict': {
 717             'id': '75524534',
 718             'ext': 'mp4',
 719             'title': "DICK HARDWICK 'Comedian'",
 720             'uploader': 'Richard Hardwick',
 721             'uploader_id': 'user21297594',
 722         }
 723     }, {
 724         'note': 'video player needs Referer',
 725         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
 726         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
 727         'info_dict': {
 728             'id': '91613211',
 729             'ext': 'mp4',
 730             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
 731             'uploader': 'DevWeek Events',
 732             'duration': 2773,
 733             'thumbnail': 're:^https?://.*\.jpg$',
 734             'uploader_id': 'user22258446',
 735         }
 736     }]
 737
 738     def _real_extract(self, url):
 739         video_id = self._match_id(url)
 740         config = self._download_json(
 741             'https://player.vimeo.com/video/%s/config' % video_id, video_id)
 742         info_dict = self._parse_config(config, video_id)
 743         self._vimeo_sort_formats(info_dict['formats'])
 744         info_dict['id'] = video_id
 745         return info_dict
 746
 747
 748 class VimeoWatchLaterIE(VimeoChannelIE):
 749     IE_NAME = 'vimeo:watchlater'
 750     IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
 751     _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
 752     _TITLE = 'Watch Later'
 753     _LOGIN_REQUIRED = True
 754     _TESTS = [{
 755         'url': 'https://vimeo.com/watchlater',
 756         'only_matching': True,
 757     }]
 758
 759     def _real_initialize(self):
 760         self._login()
 761
 762     def _page_url(self, base_url, pagenum):
 763         url = '%s/page:%d/' % (base_url, pagenum)
 764         request = sanitized_Request(url)
 765         # Set the header to get a partial html page with the ids,
 766         # the normal page doesn't contain them.
 767         request.add_header('X-Requested-With', 'XMLHttpRequest')
 768         return request
 769
 770     def _real_extract(self, url):
 771         return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
 772
 773
 774 class VimeoLikesIE(InfoExtractor):
 775     _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
 776     IE_NAME = 'vimeo:likes'
 777     IE_DESC = 'Vimeo user likes'
 778     _TEST = {
 779         'url': 'https://vimeo.com/user755559/likes/',
 780         'playlist_mincount': 293,
 781         'info_dict': {
 782             'id': 'user755559_likes',
 783             'description': 'See all the videos urza likes',
 784             'title': 'Videos urza likes',
 785         },
 786     }
 787
 788     def _real_extract(self, url):
 789         user_id = self._match_id(url)
 790         webpage = self._download_webpage(url, user_id)
 791         page_count = self._int(
 792             self._search_regex(
 793                 r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
 794                     .*?</a></li>\s*<li\s+class="pagination_next">
 795                 ''', webpage, 'page count'),
 796             'page count', fatal=True)
 797         PAGE_SIZE = 12
 798         title = self._html_search_regex(
 799             r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
 800         description = self._html_search_meta('description', webpage)
 801
 802         def _get_page(idx):
 803             page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
 804                 user_id, idx + 1)
 805             webpage = self._download_webpage(
 806                 page_url, user_id,
 807                 note='Downloading page %d/%d' % (idx + 1, page_count))
 808             video_list = self._search_regex(
 809                 r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
 810                 webpage, 'video content')
 811             paths = re.findall(
 812                 r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
 813             for path in paths:
 814                 yield {
 815                     '_type': 'url',
 816                     'url': compat_urlparse.urljoin(page_url, path),
 817                 }
 818
 819         pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
 820
 821         return {
 822             '_type': 'playlist',
 823             'id': 'user%s_likes' % user_id,
 824             'title': title,
 825             'description': description,
 826             'entries': pl,
 827         }