_ 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_str,
  12     compat_urlparse,
  13 )
  14 from ..utils import (
  15     determine_ext,
  16     ExtractorError,
  17     InAdvancePagedList,
  18     int_or_none,
  19     RegexNotFoundError,
  20     sanitized_Request,
  21     smuggle_url,
  22     std_headers,
  23     unified_strdate,
  24     unsmuggle_url,
  25     urlencode_postdata,
  26     unescapeHTML,
  27     parse_filesize,
  28     try_get,
  29 )
  30
  31
  32 class VimeoBaseInfoExtractor(InfoExtractor):
  33     _NETRC_MACHINE = 'vimeo'
  34     _LOGIN_REQUIRED = False
  35     _LOGIN_URL = 'https://vimeo.com/log_in'
  36
  37     def _login(self):
  38         (username, password) = self._get_login_info()
  39         if username is None:
  40             if self._LOGIN_REQUIRED:
  41                 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
  42             return
  43         self.report_login()
  44         webpage = self._download_webpage(self._LOGIN_URL, None, False)
  45         token, vuid = self._extract_xsrft_and_vuid(webpage)
  46         data = urlencode_postdata({
  47             'action': 'login',
  48             'email': username,
  49             'password': password,
  50             'service': 'vimeo',
  51             'token': token,
  52         })
  53         login_request = sanitized_Request(self._LOGIN_URL, data)
  54         login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  55         login_request.add_header('Referer', self._LOGIN_URL)
  56         self._set_vimeo_cookie('vuid', vuid)
  57         self._download_webpage(login_request, None, False, 'Wrong login info')
  58
  59     def _extract_xsrft_and_vuid(self, webpage):
  60         xsrft = self._search_regex(
  61             r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
  62             webpage, 'login token', group='xsrft')
  63         vuid = self._search_regex(
  64             r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
  65             webpage, 'vuid', group='vuid')
  66         return xsrft, vuid
  67
  68     def _set_vimeo_cookie(self, name, value):
  69         self._set_cookie('vimeo.com', name, value)
  70
  71     def _vimeo_sort_formats(self, formats):
  72         # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
  73         # at the same time without actual units specified. This lead to wrong sorting.
  74         self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'format_id'))
  75
  76     def _parse_config(self, config, video_id):
  77         # Extract title
  78         video_title = config['video']['title']
  79
  80         # Extract uploader, uploader_url and uploader_id
  81         video_uploader = config['video'].get('owner', {}).get('name')
  82         video_uploader_url = config['video'].get('owner', {}).get('url')
  83         video_uploader_id = video_uploader_url.split('/')[-1] if video_uploader_url else None
  84
  85         # Extract video thumbnail
  86         video_thumbnail = config['video'].get('thumbnail')
  87         if video_thumbnail is None:
  88             video_thumbs = config['video'].get('thumbs')
  89             if video_thumbs and isinstance(video_thumbs, dict):
  90                 _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
  91
  92         # Extract video duration
  93         video_duration = int_or_none(config['video'].get('duration'))
  94
  95         formats = []
  96         config_files = config['video'].get('files') or config['request'].get('files', {})
  97         for f in config_files.get('progressive', []):
  98             video_url = f.get('url')
  99             if not video_url:
 100                 continue
 101             formats.append({
 102                 'url': video_url,
 103                 'format_id': 'http-%s' % f.get('quality'),
 104                 'width': int_or_none(f.get('width')),
 105                 'height': int_or_none(f.get('height')),
 106                 'fps': int_or_none(f.get('fps')),
 107                 'tbr': int_or_none(f.get('bitrate')),
 108             })
 109         m3u8_url = config_files.get('hls', {}).get('url')
 110         if m3u8_url:
 111             formats.extend(self._extract_m3u8_formats(
 112                 m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
 113
 114         subtitles = {}
 115         text_tracks = config['request'].get('text_tracks')
 116         if text_tracks:
 117             for tt in text_tracks:
 118                 subtitles[tt['lang']] = [{
 119                     'ext': 'vtt',
 120                     'url': 'https://vimeo.com' + tt['url'],
 121                 }]
 122
 123         return {
 124             'title': video_title,
 125             'uploader': video_uploader,
 126             'uploader_id': video_uploader_id,
 127             'uploader_url': video_uploader_url,
 128             'thumbnail': video_thumbnail,
 129             'duration': video_duration,
 130             'formats': formats,
 131             'subtitles': subtitles,
 132         }
 133
 134
 135 class VimeoIE(VimeoBaseInfoExtractor):
 136     """Information extractor for vimeo.com."""
 137
 138     # _VALID_URL matches Vimeo URLs
 139     _VALID_URL = r'''(?x)
 140                     https?://
 141                         (?:
 142                             (?:
 143                                 www|
 144                                 (?P<player>player)
 145                             )
 146                             \.
 147                         )?
 148                         vimeo(?P<pro>pro)?\.com/
 149                         (?!channels/[^/?#]+/?(?:$|[?#])|[^/]+/review/|(?:album|ondemand)/)
 150                         (?:.*?/)?
 151                         (?:
 152                             (?:
 153                                 play_redirect_hls|
 154                                 moogaloop\.swf)\?clip_id=
 155                             )?
 156                         (?:videos?/)?
 157                         (?P<id>[0-9]+)
 158                         (?:/[\da-f]+)?
 159                         /?(?:[?&].*)?(?:[#].*)?$
 160                     '''
 161     IE_NAME = 'vimeo'
 162     _TESTS = [
 163         {
 164             'url': 'http://vimeo.com/56015672#at=0',
 165             'md5': '8879b6cc097e987f02484baf890129e5',
 166             'info_dict': {
 167                 'id': '56015672',
 168                 'ext': 'mp4',
 169                 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
 170                 'description': 'md5:2d3305bad981a06ff79f027f19865021',
 171                 'upload_date': '20121220',
 172                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user7108434',
 173                 'uploader_id': 'user7108434',
 174                 'uploader': 'Filippo Valsorda',
 175                 'duration': 10,
 176             },
 177         },
 178         {
 179             'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
 180             'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
 181             'note': 'Vimeo Pro video (#1197)',
 182             'info_dict': {
 183                 'id': '68093876',
 184                 'ext': 'mp4',
 185                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
 186                 'uploader_id': 'openstreetmapus',
 187                 'uploader': 'OpenStreetMap US',
 188                 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
 189                 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30',
 190                 'duration': 1595,
 191             },
 192         },
 193         {
 194             'url': 'http://player.vimeo.com/video/54469442',
 195             'md5': '619b811a4417aa4abe78dc653becf511',
 196             'note': 'Videos that embed the url in the player page',
 197             'info_dict': {
 198                 'id': '54469442',
 199                 'ext': 'mp4',
 200                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
 201                 'uploader': 'The BLN & Business of Software',
 202                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware',
 203                 'uploader_id': 'theblnbusinessofsoftware',
 204                 'duration': 3610,
 205                 'description': None,
 206             },
 207         },
 208         {
 209             'url': 'http://vimeo.com/68375962',
 210             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 211             'note': 'Video protected with password',
 212             'info_dict': {
 213                 'id': '68375962',
 214                 'ext': 'mp4',
 215                 'title': 'youtube-dl password protected test video',
 216                 'upload_date': '20130614',
 217                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user18948128',
 218                 'uploader_id': 'user18948128',
 219                 'uploader': 'Jaime Marquínez Ferrándiz',
 220                 'duration': 10,
 221                 'description': 'This is "youtube-dl password protected test video" by  on Vimeo, the home for high quality videos and the people who love them.',
 222             },
 223             'params': {
 224                 'videopassword': 'youtube-dl',
 225             },
 226         },
 227         {
 228             'url': 'http://vimeo.com/channels/keypeele/75629013',
 229             'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
 230             'note': 'Video is freely available via original URL '
 231                     'and protected with password when accessed via http://vimeo.com/75629013',
 232             'info_dict': {
 233                 'id': '75629013',
 234                 'ext': 'mp4',
 235                 'title': 'Key & Peele: Terrorist Interrogation',
 236                 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
 237                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/atencio',
 238                 'uploader_id': 'atencio',
 239                 'uploader': 'Peter Atencio',
 240                 'upload_date': '20130927',
 241                 'duration': 187,
 242             },
 243         },
 244         {
 245             'url': 'http://vimeo.com/76979871',
 246             'note': 'Video with subtitles',
 247             'info_dict': {
 248                 'id': '76979871',
 249                 'ext': 'mp4',
 250                 'title': 'The New Vimeo Player (You Know, For Videos)',
 251                 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
 252                 'upload_date': '20131015',
 253                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/staff',
 254                 'uploader_id': 'staff',
 255                 'uploader': 'Vimeo Staff',
 256                 'duration': 62,
 257             }
 258         },
 259         {
 260             # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
 261             'url': 'https://player.vimeo.com/video/98044508',
 262             'note': 'The js code contains assignments to the same variable as the config',
 263             'info_dict': {
 264                 'id': '98044508',
 265                 'ext': 'mp4',
 266                 'title': 'Pier Solar OUYA Official Trailer',
 267                 'uploader': 'Tulio Gonçalves',
 268                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/user28849593',
 269                 'uploader_id': 'user28849593',
 270             },
 271         },
 272         {
 273             # contains original format
 274             'url': 'https://vimeo.com/33951933',
 275             'md5': '53c688fa95a55bf4b7293d37a89c5c53',
 276             'info_dict': {
 277                 'id': '33951933',
 278                 'ext': 'mp4',
 279                 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
 280                 'uploader': 'The DMCI',
 281                 'uploader_url': 're:https?://(?:www\.)?vimeo\.com/dmci',
 282                 'uploader_id': 'dmci',
 283                 'upload_date': '20111220',
 284                 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
 285             },
 286         },
 287         {
 288             'url': 'https://vimeo.com/109815029',
 289             'note': 'Video not completely processed, "failed" seed status',
 290             'only_matching': True,
 291         },
 292         {
 293             'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
 294             'only_matching': True,
 295         },
 296         {
 297             # source file returns 403: Forbidden
 298             'url': 'https://vimeo.com/7809605',
 299             'only_matching': True,
 300         },
 301         {
 302             'url': 'https://vimeo.com/160743502/abd0e13fb4',
 303             'only_matching': True,
 304         }
 305     ]
 306
 307     @staticmethod
 308     def _extract_vimeo_url(url, webpage):
 309         # Look for embedded (iframe) Vimeo player
 310         mobj = re.search(
 311             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
 312         if mobj:
 313             player_url = unescapeHTML(mobj.group('url'))
 314             surl = smuggle_url(player_url, {'http_headers': {'Referer': url}})
 315             return surl
 316         # Look for embedded (swf embed) Vimeo player
 317         mobj = re.search(
 318             r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
 319         if mobj:
 320             return mobj.group(1)
 321
 322     def _verify_video_password(self, url, video_id, webpage):
 323         password = self._downloader.params.get('videopassword')
 324         if password is None:
 325             raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
 326         token, vuid = self._extract_xsrft_and_vuid(webpage)
 327         data = urlencode_postdata({
 328             'password': password,
 329             'token': token,
 330         })
 331         if url.startswith('http://'):
 332             # vimeo only supports https now, but the user can give an http url
 333             url = url.replace('http://', 'https://')
 334         password_request = sanitized_Request(url + '/password', data)
 335         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 336         password_request.add_header('Referer', url)
 337         self._set_vimeo_cookie('vuid', vuid)
 338         return self._download_webpage(
 339             password_request, video_id,
 340             'Verifying the password', 'Wrong password')
 341
 342     def _verify_player_video_password(self, url, video_id):
 343         password = self._downloader.params.get('videopassword')
 344         if password is None:
 345             raise ExtractorError('This video is protected by a password, use the --video-password option')
 346         data = urlencode_postdata({'password': password})
 347         pass_url = url + '/check-password'
 348         password_request = sanitized_Request(pass_url, data)
 349         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 350         password_request.add_header('Referer', url)
 351         return self._download_json(
 352             password_request, video_id,
 353             'Verifying the password', 'Wrong password')
 354
 355     def _real_initialize(self):
 356         self._login()
 357
 358     def _real_extract(self, url):
 359         url, data = unsmuggle_url(url, {})
 360         headers = std_headers.copy()
 361         if 'http_headers' in data:
 362             headers.update(data['http_headers'])
 363         if 'Referer' not in headers:
 364             headers['Referer'] = url
 365
 366         # Extract ID from URL
 367         mobj = re.match(self._VALID_URL, url)
 368         video_id = mobj.group('id')
 369         orig_url = url
 370         if mobj.group('pro') or mobj.group('player'):
 371             url = 'https://player.vimeo.com/video/' + video_id
 372         else:
 373             url = 'https://vimeo.com/' + video_id
 374
 375         # Retrieve video webpage to extract further information
 376         request = sanitized_Request(url, headers=headers)
 377         try:
 378             webpage = self._download_webpage(request, video_id)
 379         except ExtractorError as ee:
 380             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
 381                 errmsg = ee.cause.read()
 382                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 383                     raise ExtractorError(
 384                         'Cannot download embed-only video without embedding '
 385                         'URL. Please call youtube-dl with the URL of the page '
 386                         'that embeds this video.',
 387                         expected=True)
 388             raise
 389
 390         # Now we begin extracting as much information as we can from what we
 391         # retrieved. First we extract the information common to all extractors,
 392         # and latter we extract those that are Vimeo specific.
 393         self.report_extraction(video_id)
 394
 395         vimeo_config = self._search_regex(
 396             r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage,
 397             'vimeo config', default=None)
 398         if vimeo_config:
 399             seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
 400             if seed_status.get('state') == 'failed':
 401                 raise ExtractorError(
 402                     '%s said: %s' % (self.IE_NAME, seed_status['title']),
 403                     expected=True)
 404
 405         # Extract the config JSON
 406         try:
 407             try:
 408                 config_url = self._html_search_regex(
 409                     r' data-config-url="(.+?)"', webpage,
 410                     'config URL', default=None)
 411                 if not config_url:
 412                     # Sometimes new react-based page is served instead of old one that require
 413                     # different config URL extraction approach (see
 414                     # https://github.com/rg3/youtube-dl/pull/7209)
 415                     vimeo_clip_page_config = self._search_regex(
 416                         r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
 417                         'vimeo clip page config')
 418                     config_url = self._parse_json(
 419                         vimeo_clip_page_config, video_id)['player']['config_url']
 420                 config_json = self._download_webpage(config_url, video_id)
 421                 config = json.loads(config_json)
 422             except RegexNotFoundError:
 423                 # For pro videos or player.vimeo.com urls
 424                 # We try to find out to which variable is assigned the config dic
 425                 m_variable_name = re.search('(\w)\.video\.id', webpage)
 426                 if m_variable_name is not None:
 427                     config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))
 428                 else:
 429                     config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
 430                 config = self._search_regex(config_re, webpage, 'info section',
 431                                             flags=re.DOTALL)
 432                 config = json.loads(config)
 433         except Exception as e:
 434             if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
 435                 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
 436
 437             if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
 438                 if '_video_password_verified' in data:
 439                     raise ExtractorError('video password verification failed!')
 440                 self._verify_video_password(url, video_id, webpage)
 441                 return self._real_extract(
 442                     smuggle_url(url, {'_video_password_verified': 'verified'}))
 443             else:
 444                 raise ExtractorError('Unable to extract info section',
 445                                      cause=e)
 446         else:
 447             if config.get('view') == 4:
 448                 config = self._verify_player_video_password(url, video_id)
 449
 450         def is_rented():
 451             if '>You rented this title.<' in webpage:
 452                 return True
 453             if config.get('user', {}).get('purchased'):
 454                 return True
 455             label = try_get(
 456                 config, lambda x: x['video']['vod']['purchase_options'][0]['label_string'], compat_str)
 457             if label and label.startswith('You rented this'):
 458                 return True
 459             return False
 460
 461         if is_rented():
 462             feature_id = config.get('video', {}).get('vod', {}).get('feature_id')
 463             if feature_id and not data.get('force_feature_id', False):
 464                 return self.url_result(smuggle_url(
 465                     'https://player.vimeo.com/player/%s' % feature_id,
 466                     {'force_feature_id': True}), 'Vimeo')
 467
 468         # Extract video description
 469
 470         video_description = self._html_search_regex(
 471             r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 472             webpage, 'description', default=None)
 473         if not video_description:
 474             video_description = self._html_search_meta(
 475                 'description', webpage, default=None)
 476         if not video_description and mobj.group('pro'):
 477             orig_webpage = self._download_webpage(
 478                 orig_url, video_id,
 479                 note='Downloading webpage for description',
 480                 fatal=False)
 481             if orig_webpage:
 482                 video_description = self._html_search_meta(
 483                     'description', orig_webpage, default=None)
 484         if not video_description and not mobj.group('player'):
 485             self._downloader.report_warning('Cannot find video description')
 486
 487         # Extract upload date
 488         video_upload_date = None
 489         mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage)
 490         if mobj is not None:
 491             video_upload_date = unified_strdate(mobj.group(1))
 492
 493         try:
 494             view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
 495             like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
 496             comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
 497         except RegexNotFoundError:
 498             # This info is only available in vimeo.com/{id} urls
 499             view_count = None
 500             like_count = None
 501             comment_count = None
 502
 503         formats = []
 504         download_request = sanitized_Request('https://vimeo.com/%s?action=load_download_config' % video_id, headers={
 505             'X-Requested-With': 'XMLHttpRequest'})
 506         download_data = self._download_json(download_request, video_id, fatal=False)
 507         if download_data:
 508             source_file = download_data.get('source_file')
 509             if isinstance(source_file, dict):
 510                 download_url = source_file.get('download_url')
 511                 if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
 512                     source_name = source_file.get('public_name', 'Original')
 513                     if self._is_valid_url(download_url, video_id, '%s video' % source_name):
 514                         ext = source_file.get('extension', determine_ext(download_url)).lower()
 515                         formats.append({
 516                             'url': download_url,
 517                             'ext': ext,
 518                             'width': int_or_none(source_file.get('width')),
 519                             'height': int_or_none(source_file.get('height')),
 520                             'filesize': parse_filesize(source_file.get('size')),
 521                             'format_id': source_name,
 522                             'preference': 1,
 523                         })
 524
 525         info_dict = self._parse_config(config, video_id)
 526         formats.extend(info_dict['formats'])
 527         self._vimeo_sort_formats(formats)
 528         info_dict.update({
 529             'id': video_id,
 530             'formats': formats,
 531             'upload_date': video_upload_date,
 532             'description': video_description,
 533             'webpage_url': url,
 534             'view_count': view_count,
 535             'like_count': like_count,
 536             'comment_count': comment_count,
 537         })
 538
 539         return info_dict
 540
 541
 542 class VimeoOndemandIE(VimeoBaseInfoExtractor):
 543     IE_NAME = 'vimeo:ondemand'
 544     _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?P<id>[^/?#&]+)'
 545     _TESTS = [{
 546         # ondemand video not available via https://vimeo.com/id
 547         'url': 'https://vimeo.com/ondemand/20704',
 548         'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
 549         'info_dict': {
 550             'id': '105442900',
 551             'ext': 'mp4',
 552             'title': 'המעבדה - במאי יותם פלדמן',
 553             'uploader': 'גם סרטים',
 554             'uploader_url': 're:https?://(?:www\.)?vimeo\.com/gumfilms',
 555             'uploader_id': 'gumfilms',
 556         },
 557     }, {
 558         'url': 'https://vimeo.com/ondemand/nazmaalik',
 559         'only_matching': True,
 560     }, {
 561         'url': 'https://vimeo.com/ondemand/141692381',
 562         'only_matching': True,
 563     }, {
 564         'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
 565         'only_matching': True,
 566     }]
 567
 568     def _real_extract(self, url):
 569         video_id = self._match_id(url)
 570         webpage = self._download_webpage(url, video_id)
 571         return self.url_result(self._og_search_video_url(webpage), VimeoIE.ie_key())
 572
 573
 574 class VimeoChannelIE(VimeoBaseInfoExtractor):
 575     IE_NAME = 'vimeo:channel'
 576     _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
 577     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
 578     _TITLE = None
 579     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
 580     _TESTS = [{
 581         'url': 'https://vimeo.com/channels/tributes',
 582         'info_dict': {
 583             'id': 'tributes',
 584             'title': 'Vimeo Tributes',
 585         },
 586         'playlist_mincount': 25,
 587     }]
 588
 589     def _page_url(self, base_url, pagenum):
 590         return '%s/videos/page:%d/' % (base_url, pagenum)
 591
 592     def _extract_list_title(self, webpage):
 593         return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title')
 594
 595     def _login_list_password(self, page_url, list_id, webpage):
 596         login_form = self._search_regex(
 597             r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
 598             webpage, 'login form', default=None)
 599         if not login_form:
 600             return webpage
 601
 602         password = self._downloader.params.get('videopassword')
 603         if password is None:
 604             raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
 605         fields = self._hidden_inputs(login_form)
 606         token, vuid = self._extract_xsrft_and_vuid(webpage)
 607         fields['token'] = token
 608         fields['password'] = password
 609         post = urlencode_postdata(fields)
 610         password_path = self._search_regex(
 611             r'action="([^"]+)"', login_form, 'password URL')
 612         password_url = compat_urlparse.urljoin(page_url, password_path)
 613         password_request = sanitized_Request(password_url, post)
 614         password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
 615         self._set_vimeo_cookie('vuid', vuid)
 616         self._set_vimeo_cookie('xsrft', token)
 617
 618         return self._download_webpage(
 619             password_request, list_id,
 620             'Verifying the password', 'Wrong password')
 621
 622     def _title_and_entries(self, list_id, base_url):
 623         for pagenum in itertools.count(1):
 624             page_url = self._page_url(base_url, pagenum)
 625             webpage = self._download_webpage(
 626                 page_url, list_id,
 627                 'Downloading page %s' % pagenum)
 628
 629             if pagenum == 1:
 630                 webpage = self._login_list_password(page_url, list_id, webpage)
 631                 yield self._extract_list_title(webpage)
 632
 633             for video_id in re.findall(r'id="clip_(\d+?)"', webpage):
 634                 yield self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo')
 635
 636             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
 637                 break
 638
 639     def _extract_videos(self, list_id, base_url):
 640         title_and_entries = self._title_and_entries(list_id, base_url)
 641         list_title = next(title_and_entries)
 642         return self.playlist_result(title_and_entries, list_id, list_title)
 643
 644     def _real_extract(self, url):
 645         mobj = re.match(self._VALID_URL, url)
 646         channel_id = mobj.group('id')
 647         return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
 648
 649
 650 class VimeoUserIE(VimeoChannelIE):
 651     IE_NAME = 'vimeo:user'
 652     _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
 653     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
 654     _TESTS = [{
 655         'url': 'https://vimeo.com/nkistudio/videos',
 656         'info_dict': {
 657             'title': 'Nki',
 658             'id': 'nkistudio',
 659         },
 660         'playlist_mincount': 66,
 661     }]
 662
 663     def _real_extract(self, url):
 664         mobj = re.match(self._VALID_URL, url)
 665         name = mobj.group('name')
 666         return self._extract_videos(name, 'https://vimeo.com/%s' % name)
 667
 668
 669 class VimeoAlbumIE(VimeoChannelIE):
 670     IE_NAME = 'vimeo:album'
 671     _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)'
 672     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
 673     _TESTS = [{
 674         'url': 'https://vimeo.com/album/2632481',
 675         'info_dict': {
 676             'id': '2632481',
 677             'title': 'Staff Favorites: November 2013',
 678         },
 679         'playlist_mincount': 13,
 680     }, {
 681         'note': 'Password-protected album',
 682         'url': 'https://vimeo.com/album/3253534',
 683         'info_dict': {
 684             'title': 'test',
 685             'id': '3253534',
 686         },
 687         'playlist_count': 1,
 688         'params': {
 689             'videopassword': 'youtube-dl',
 690         }
 691     }]
 692
 693     def _page_url(self, base_url, pagenum):
 694         return '%s/page:%d/' % (base_url, pagenum)
 695
 696     def _real_extract(self, url):
 697         album_id = self._match_id(url)
 698         return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id)
 699
 700
 701 class VimeoGroupsIE(VimeoAlbumIE):
 702     IE_NAME = 'vimeo:group'
 703     _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)'
 704     _TESTS = [{
 705         'url': 'https://vimeo.com/groups/rolexawards',
 706         'info_dict': {
 707             'id': 'rolexawards',
 708             'title': 'Rolex Awards for Enterprise',
 709         },
 710         'playlist_mincount': 73,
 711     }]
 712
 713     def _extract_list_title(self, webpage):
 714         return self._og_search_title(webpage)
 715
 716     def _real_extract(self, url):
 717         mobj = re.match(self._VALID_URL, url)
 718         name = mobj.group('name')
 719         return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
 720
 721
 722 class VimeoReviewIE(VimeoBaseInfoExtractor):
 723     IE_NAME = 'vimeo:review'
 724     IE_DESC = 'Review pages on vimeo'
 725     _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
 726     _TESTS = [{
 727         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
 728         'md5': 'c507a72f780cacc12b2248bb4006d253',
 729         'info_dict': {
 730             'id': '75524534',
 731             'ext': 'mp4',
 732             'title': "DICK HARDWICK 'Comedian'",
 733             'uploader': 'Richard Hardwick',
 734             'uploader_id': 'user21297594',
 735         }
 736     }, {
 737         'note': 'video player needs Referer',
 738         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
 739         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
 740         'info_dict': {
 741             'id': '91613211',
 742             'ext': 'mp4',
 743             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
 744             'uploader': 'DevWeek Events',
 745             'duration': 2773,
 746             'thumbnail': 're:^https?://.*\.jpg$',
 747             'uploader_id': 'user22258446',
 748         }
 749     }]
 750
 751     def _real_extract(self, url):
 752         video_id = self._match_id(url)
 753         config = self._download_json(
 754             'https://player.vimeo.com/video/%s/config' % video_id, video_id)
 755         info_dict = self._parse_config(config, video_id)
 756         self._vimeo_sort_formats(info_dict['formats'])
 757         info_dict['id'] = video_id
 758         return info_dict
 759
 760
 761 class VimeoWatchLaterIE(VimeoChannelIE):
 762     IE_NAME = 'vimeo:watchlater'
 763     IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
 764     _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
 765     _TITLE = 'Watch Later'
 766     _LOGIN_REQUIRED = True
 767     _TESTS = [{
 768         'url': 'https://vimeo.com/watchlater',
 769         'only_matching': True,
 770     }]
 771
 772     def _real_initialize(self):
 773         self._login()
 774
 775     def _page_url(self, base_url, pagenum):
 776         url = '%s/page:%d/' % (base_url, pagenum)
 777         request = sanitized_Request(url)
 778         # Set the header to get a partial html page with the ids,
 779         # the normal page doesn't contain them.
 780         request.add_header('X-Requested-With', 'XMLHttpRequest')
 781         return request
 782
 783     def _real_extract(self, url):
 784         return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
 785
 786
 787 class VimeoLikesIE(InfoExtractor):
 788     _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
 789     IE_NAME = 'vimeo:likes'
 790     IE_DESC = 'Vimeo user likes'
 791     _TEST = {
 792         'url': 'https://vimeo.com/user755559/likes/',
 793         'playlist_mincount': 293,
 794         'info_dict': {
 795             'id': 'user755559_likes',
 796             'description': 'See all the videos urza likes',
 797             'title': 'Videos urza likes',
 798         },
 799     }
 800
 801     def _real_extract(self, url):
 802         user_id = self._match_id(url)
 803         webpage = self._download_webpage(url, user_id)
 804         page_count = self._int(
 805             self._search_regex(
 806                 r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
 807                     .*?</a></li>\s*<li\s+class="pagination_next">
 808                 ''', webpage, 'page count'),
 809             'page count', fatal=True)
 810         PAGE_SIZE = 12
 811         title = self._html_search_regex(
 812             r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
 813         description = self._html_search_meta('description', webpage)
 814
 815         def _get_page(idx):
 816             page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
 817                 user_id, idx + 1)
 818             webpage = self._download_webpage(
 819                 page_url, user_id,
 820                 note='Downloading page %d/%d' % (idx + 1, page_count))
 821             video_list = self._search_regex(
 822                 r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
 823                 webpage, 'video content')
 824             paths = re.findall(
 825                 r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
 826             for path in paths:
 827                 yield {
 828                     '_type': 'url',
 829                     'url': compat_urlparse.urljoin(page_url, path),
 830                 }
 831
 832         pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
 833
 834         return {
 835             '_type': 'playlist',
 836             'id': 'user%s_likes' % user_id,
 837             'title': title,
 838             'description': description,
 839             'entries': pl,
 840         }