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