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