Raphaël G. Git Repositories - youtubedl/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_urllib_request,
  12     compat_urlparse,
  13 )
  14 from ..utils import (
  15     encode_dict,
  16     ExtractorError,
  17     InAdvancePagedList,
  18     int_or_none,
  19     RegexNotFoundError,
  20     smuggle_url,
  21     std_headers,
  22     unified_strdate,
  23     unsmuggle_url,
  24     urlencode_postdata,
  25     unescapeHTML,
  26 )
  27
  28
  29 class VimeoBaseInfoExtractor(InfoExtractor):
  30     _NETRC_MACHINE = 'vimeo'
  31     _LOGIN_REQUIRED = False
  32     _LOGIN_URL = 'https://vimeo.com/log_in'
  33
  34     def _login(self):
  35         (username, password) = self._get_login_info()
  36         if username is None:
  37             if self._LOGIN_REQUIRED:
  38                 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
  39             return
  40         self.report_login()
  41         webpage = self._download_webpage(self._LOGIN_URL, None, False)
  42         token, vuid = self._extract_xsrft_and_vuid(webpage)
  43         data = urlencode_postdata(encode_dict({
  44             'action': 'login',
  45             'email': username,
  46             'password': password,
  47             'service': 'vimeo',
  48             'token': token,
  49         }))
  50         login_request = compat_urllib_request.Request(self._LOGIN_URL, data)
  51         login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  52         login_request.add_header('Cookie', 'vuid=%s' % vuid)
  53         login_request.add_header('Referer', self._LOGIN_URL)
  54         self._download_webpage(login_request, None, False, 'Wrong login info')
  55
  56     def _extract_xsrft_and_vuid(self, webpage):
  57         xsrft = self._search_regex(
  58             r'xsrft\s*[=:]\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
  59             webpage, 'login token', group='xsrft')
  60         vuid = self._search_regex(
  61             r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
  62             webpage, 'vuid', group='vuid')
  63         return xsrft, vuid
  64
  65
  66 class VimeoIE(VimeoBaseInfoExtractor):
  67     """Information extractor for vimeo.com."""
  68
  69     # _VALID_URL matches Vimeo URLs
  70     _VALID_URL = r'''(?x)
  71         https?://
  72         (?:(?:www|(?P<player>player))\.)?
  73         vimeo(?P<pro>pro)?\.com/
  74         (?!channels/[^/?#]+/?(?:$|[?#])|album/)
  75         (?:.*?/)?
  76         (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)?
  77         (?:videos?/)?
  78         (?P<id>[0-9]+)
  79         /?(?:[?&].*)?(?:[#].*)?$'''
  80     IE_NAME = 'vimeo'
  81     _TESTS = [
  82         {
  83             'url': 'http://vimeo.com/56015672#at=0',
  84             'md5': '8879b6cc097e987f02484baf890129e5',
  85             'info_dict': {
  86                 'id': '56015672',
  87                 'ext': 'mp4',
  88                 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
  89                 'description': 'md5:2d3305bad981a06ff79f027f19865021',
  90                 'upload_date': '20121220',
  91                 'uploader_id': 'user7108434',
  92                 'uploader': 'Filippo Valsorda',
  93                 'duration': 10,
  94             },
  95         },
  96         {
  97             'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
  98             'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
  99             'note': 'Vimeo Pro video (#1197)',
 100             'info_dict': {
 101                 'id': '68093876',
 102                 'ext': 'mp4',
 103                 'uploader_id': 'openstreetmapus',
 104                 'uploader': 'OpenStreetMap US',
 105                 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
 106                 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30',
 107                 'duration': 1595,
 108             },
 109         },
 110         {
 111             'url': 'http://player.vimeo.com/video/54469442',
 112             'md5': '619b811a4417aa4abe78dc653becf511',
 113             'note': 'Videos that embed the url in the player page',
 114             'info_dict': {
 115                 'id': '54469442',
 116                 'ext': 'mp4',
 117                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
 118                 'uploader': 'The BLN & Business of Software',
 119                 'uploader_id': 'theblnbusinessofsoftware',
 120                 'duration': 3610,
 121                 'description': None,
 122             },
 123         },
 124         {
 125             'url': 'http://vimeo.com/68375962',
 126             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 127             'note': 'Video protected with password',
 128             'info_dict': {
 129                 'id': '68375962',
 130                 'ext': 'mp4',
 131                 'title': 'youtube-dl password protected test video',
 132                 'upload_date': '20130614',
 133                 'uploader_id': 'user18948128',
 134                 'uploader': 'Jaime Marquínez Ferrándiz',
 135                 'duration': 10,
 136                 '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',
 137             },
 138             'params': {
 139                 'videopassword': 'youtube-dl',
 140             },
 141         },
 142         {
 143             'url': 'http://vimeo.com/channels/keypeele/75629013',
 144             'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
 145             'note': 'Video is freely available via original URL '
 146                     'and protected with password when accessed via http://vimeo.com/75629013',
 147             'info_dict': {
 148                 'id': '75629013',
 149                 'ext': 'mp4',
 150                 'title': 'Key & Peele: Terrorist Interrogation',
 151                 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
 152                 'uploader_id': 'atencio',
 153                 'uploader': 'Peter Atencio',
 154                 'upload_date': '20130927',
 155                 'duration': 187,
 156             },
 157         },
 158         {
 159             'url': 'http://vimeo.com/76979871',
 160             'note': 'Video with subtitles',
 161             'info_dict': {
 162                 'id': '76979871',
 163                 'ext': 'mp4',
 164                 'title': 'The New Vimeo Player (You Know, For Videos)',
 165                 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
 166                 'upload_date': '20131015',
 167                 'uploader_id': 'staff',
 168                 'uploader': 'Vimeo Staff',
 169                 'duration': 62,
 170             }
 171         },
 172         {
 173             # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
 174             'url': 'https://player.vimeo.com/video/98044508',
 175             'note': 'The js code contains assignments to the same variable as the config',
 176             'info_dict': {
 177                 'id': '98044508',
 178                 'ext': 'mp4',
 179                 'title': 'Pier Solar OUYA Official Trailer',
 180                 'uploader': 'Tulio Gonçalves',
 181                 'uploader_id': 'user28849593',
 182             },
 183         },
 184         {
 185             'url': 'https://vimeo.com/109815029',
 186             'note': 'Video not completely processed, "failed" seed status',
 187             'only_matching': True,
 188         },
 189     ]
 190
 191     @staticmethod
 192     def _extract_vimeo_url(url, webpage):
 193         # Look for embedded (iframe) Vimeo player
 194         mobj = re.search(
 195             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
 196         if mobj:
 197             player_url = unescapeHTML(mobj.group('url'))
 198             surl = smuggle_url(player_url, {'Referer': url})
 199             return surl
 200         # Look for embedded (swf embed) Vimeo player
 201         mobj = re.search(
 202             r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
 203         if mobj:
 204             return mobj.group(1)
 205
 206     def _verify_video_password(self, url, video_id, webpage):
 207         password = self._downloader.params.get('videopassword', None)
 208         if password is None:
 209             raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
 210         token, vuid = self._extract_xsrft_and_vuid(webpage)
 211         data = urlencode_postdata(encode_dict({
 212             'password': password,
 213             'token': token,
 214         }))
 215         if url.startswith('http://'):
 216             # vimeo only supports https now, but the user can give an http url
 217             url = url.replace('http://', 'https://')
 218         password_request = compat_urllib_request.Request(url + '/password', data)
 219         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 220         password_request.add_header('Cookie', 'clip_test2=1; vuid=%s' % vuid)
 221         password_request.add_header('Referer', url)
 222         return self._download_webpage(
 223             password_request, video_id,
 224             'Verifying the password', 'Wrong password')
 225
 226     def _verify_player_video_password(self, url, video_id):
 227         password = self._downloader.params.get('videopassword', None)
 228         if password is None:
 229             raise ExtractorError('This video is protected by a password, use the --video-password option')
 230         data = urlencode_postdata(encode_dict({'password': password}))
 231         pass_url = url + '/check-password'
 232         password_request = compat_urllib_request.Request(pass_url, data)
 233         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 234         return self._download_json(
 235             password_request, video_id,
 236             'Verifying the password',
 237             'Wrong password')
 238
 239     def _real_initialize(self):
 240         self._login()
 241
 242     def _real_extract(self, url):
 243         url, data = unsmuggle_url(url)
 244         headers = std_headers
 245         if data is not None:
 246             headers = headers.copy()
 247             headers.update(data)
 248         if 'Referer' not in headers:
 249             headers['Referer'] = url
 250
 251         # Extract ID from URL
 252         mobj = re.match(self._VALID_URL, url)
 253         video_id = mobj.group('id')
 254         orig_url = url
 255         if mobj.group('pro') or mobj.group('player'):
 256             url = 'https://player.vimeo.com/video/' + video_id
 257         else:
 258             url = 'https://vimeo.com/' + video_id
 259
 260         # Retrieve video webpage to extract further information
 261         request = compat_urllib_request.Request(url, None, headers)
 262         try:
 263             webpage = self._download_webpage(request, video_id)
 264         except ExtractorError as ee:
 265             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
 266                 errmsg = ee.cause.read()
 267                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 268                     raise ExtractorError(
 269                         'Cannot download embed-only video without embedding '
 270                         'URL. Please call youtube-dl with the URL of the page '
 271                         'that embeds this video.',
 272                         expected=True)
 273             raise
 274
 275         # Now we begin extracting as much information as we can from what we
 276         # retrieved. First we extract the information common to all extractors,
 277         # and latter we extract those that are Vimeo specific.
 278         self.report_extraction(video_id)
 279
 280         vimeo_config = self._search_regex(
 281             r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage,
 282             'vimeo config', default=None)
 283         if vimeo_config:
 284             seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
 285             if seed_status.get('state') == 'failed':
 286                 raise ExtractorError(
 287                     '%s said: %s' % (self.IE_NAME, seed_status['title']),
 288                     expected=True)
 289
 290         # Extract the config JSON
 291         try:
 292             try:
 293                 config_url = self._html_search_regex(
 294                     r' data-config-url="(.+?)"', webpage,
 295                     'config URL', default=None)
 296                 if not config_url:
 297                     # Sometimes new react-based page is served instead of old one that require
 298                     # different config URL extraction approach (see
 299                     # https://github.com/rg3/youtube-dl/pull/7209)
 300                     vimeo_clip_page_config = self._search_regex(
 301                         r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
 302                         'vimeo clip page config')
 303                     config_url = self._parse_json(
 304                         vimeo_clip_page_config, video_id)['player']['config_url']
 305                 config_json = self._download_webpage(config_url, video_id)
 306                 config = json.loads(config_json)
 307             except RegexNotFoundError:
 308                 # For pro videos or player.vimeo.com urls
 309                 # We try to find out to which variable is assigned the config dic
 310                 m_variable_name = re.search('(\w)\.video\.id', webpage)
 311                 if m_variable_name is not None:
 312                     config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))
 313                 else:
 314                     config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
 315                 config = self._search_regex(config_re, webpage, 'info section',
 316                                             flags=re.DOTALL)
 317                 config = json.loads(config)
 318         except Exception as e:
 319             if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
 320                 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
 321
 322             if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
 323                 if data and '_video_password_verified' in data:
 324                     raise ExtractorError('video password verification failed!')
 325                 self._verify_video_password(url, video_id, webpage)
 326                 return self._real_extract(
 327                     smuggle_url(url, {'_video_password_verified': 'verified'}))
 328             else:
 329                 raise ExtractorError('Unable to extract info section',
 330                                      cause=e)
 331         else:
 332             if config.get('view') == 4:
 333                 config = self._verify_player_video_password(url, video_id)
 334
 335         # Extract title
 336         video_title = config["video"]["title"]
 337
 338         # Extract uploader and uploader_id
 339         video_uploader = config["video"]["owner"]["name"]
 340         video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None
 341
 342         # Extract video thumbnail
 343         video_thumbnail = config["video"].get("thumbnail")
 344         if video_thumbnail is None:
 345             video_thumbs = config["video"].get("thumbs")
 346             if video_thumbs and isinstance(video_thumbs, dict):
 347                 _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
 348
 349         # Extract video description
 350
 351         video_description = self._html_search_regex(
 352             r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 353             webpage, 'description', default=None)
 354         if not video_description:
 355             video_description = self._html_search_meta(
 356                 'description', webpage, default=None)
 357         if not video_description and mobj.group('pro'):
 358             orig_webpage = self._download_webpage(
 359                 orig_url, video_id,
 360                 note='Downloading webpage for description',
 361                 fatal=False)
 362             if orig_webpage:
 363                 video_description = self._html_search_meta(
 364                     'description', orig_webpage, default=None)
 365         if not video_description and not mobj.group('player'):
 366             self._downloader.report_warning('Cannot find video description')
 367
 368         # Extract video duration
 369         video_duration = int_or_none(config["video"].get("duration"))
 370
 371         # Extract upload date
 372         video_upload_date = None
 373         mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage)
 374         if mobj is not None:
 375             video_upload_date = unified_strdate(mobj.group(1))
 376
 377         try:
 378             view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
 379             like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
 380             comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
 381         except RegexNotFoundError:
 382             # This info is only available in vimeo.com/{id} urls
 383             view_count = None
 384             like_count = None
 385             comment_count = None
 386
 387         # Vimeo specific: extract request signature and timestamp
 388         sig = config['request']['signature']
 389         timestamp = config['request']['timestamp']
 390
 391         # Vimeo specific: extract video codec and quality information
 392         # First consider quality, then codecs, then take everything
 393         codecs = [('vp6', 'flv'), ('vp8', 'flv'), ('h264', 'mp4')]
 394         files = {'hd': [], 'sd': [], 'other': []}
 395         config_files = config["video"].get("files") or config["request"].get("files")
 396         for codec_name, codec_extension in codecs:
 397             for quality in config_files.get(codec_name, []):
 398                 format_id = '-'.join((codec_name, quality)).lower()
 399                 key = quality if quality in files else 'other'
 400                 video_url = None
 401                 if isinstance(config_files[codec_name], dict):
 402                     file_info = config_files[codec_name][quality]
 403                     video_url = file_info.get('url')
 404                 else:
 405                     file_info = {}
 406                 if video_url is None:
 407                     video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
 408                         % (video_id, sig, timestamp, quality, codec_name.upper())
 409
 410                 files[key].append({
 411                     'ext': codec_extension,
 412                     'url': video_url,
 413                     'format_id': format_id,
 414                     'width': int_or_none(file_info.get('width')),
 415                     'height': int_or_none(file_info.get('height')),
 416                     'tbr': int_or_none(file_info.get('bitrate')),
 417                 })
 418         formats = []
 419         m3u8_url = config_files.get('hls', {}).get('all')
 420         if m3u8_url:
 421             m3u8_formats = self._extract_m3u8_formats(
 422                 m3u8_url, video_id, 'mp4', 'm3u8_native', 0, 'hls', fatal=False)
 423             if m3u8_formats:
 424                 formats.extend(m3u8_formats)
 425         for key in ('other', 'sd', 'hd'):
 426             formats += files[key]
 427         self._sort_formats(formats)
 428
 429         subtitles = {}
 430         text_tracks = config['request'].get('text_tracks')
 431         if text_tracks:
 432             for tt in text_tracks:
 433                 subtitles[tt['lang']] = [{
 434                     'ext': 'vtt',
 435                     'url': 'https://vimeo.com' + tt['url'],
 436                 }]
 437
 438         return {
 439             'id': video_id,
 440             'uploader': video_uploader,
 441             'uploader_id': video_uploader_id,
 442             'upload_date': video_upload_date,
 443             'title': video_title,
 444             'thumbnail': video_thumbnail,
 445             'description': video_description,
 446             'duration': video_duration,
 447             'formats': formats,
 448             'webpage_url': url,
 449             'view_count': view_count,
 450             'like_count': like_count,
 451             'comment_count': comment_count,
 452             'subtitles': subtitles,
 453         }
 454
 455
 456 class VimeoChannelIE(VimeoBaseInfoExtractor):
 457     IE_NAME = 'vimeo:channel'
 458     _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
 459     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
 460     _TITLE = None
 461     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
 462     _TESTS = [{
 463         'url': 'https://vimeo.com/channels/tributes',
 464         'info_dict': {
 465             'id': 'tributes',
 466             'title': 'Vimeo Tributes',
 467         },
 468         'playlist_mincount': 25,
 469     }]
 470
 471     def _page_url(self, base_url, pagenum):
 472         return '%s/videos/page:%d/' % (base_url, pagenum)
 473
 474     def _extract_list_title(self, webpage):
 475         return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title')
 476
 477     def _login_list_password(self, page_url, list_id, webpage):
 478         login_form = self._search_regex(
 479             r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
 480             webpage, 'login form', default=None)
 481         if not login_form:
 482             return webpage
 483
 484         password = self._downloader.params.get('videopassword', None)
 485         if password is None:
 486             raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
 487         fields = self._hidden_inputs(login_form)
 488         token, vuid = self._extract_xsrft_and_vuid(webpage)
 489         fields['token'] = token
 490         fields['password'] = password
 491         post = urlencode_postdata(encode_dict(fields))
 492         password_path = self._search_regex(
 493             r'action="([^"]+)"', login_form, 'password URL')
 494         password_url = compat_urlparse.urljoin(page_url, password_path)
 495         password_request = compat_urllib_request.Request(password_url, post)
 496         password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
 497         password_request.add_header('Cookie', 'vuid=%s' % vuid)
 498         self._set_cookie('vimeo.com', 'xsrft', token)
 499
 500         return self._download_webpage(
 501             password_request, list_id,
 502             'Verifying the password', 'Wrong password')
 503
 504     def _extract_videos(self, list_id, base_url):
 505         video_ids = []
 506         for pagenum in itertools.count(1):
 507             page_url = self._page_url(base_url, pagenum)
 508             webpage = self._download_webpage(
 509                 page_url, list_id,
 510                 'Downloading page %s' % pagenum)
 511
 512             if pagenum == 1:
 513                 webpage = self._login_list_password(page_url, list_id, webpage)
 514
 515             video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage))
 516             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
 517                 break
 518
 519         entries = [self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo')
 520                    for video_id in video_ids]
 521         return {'_type': 'playlist',
 522                 'id': list_id,
 523                 'title': self._extract_list_title(webpage),
 524                 'entries': entries,
 525                 }
 526
 527     def _real_extract(self, url):
 528         mobj = re.match(self._VALID_URL, url)
 529         channel_id = mobj.group('id')
 530         return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
 531
 532
 533 class VimeoUserIE(VimeoChannelIE):
 534     IE_NAME = 'vimeo:user'
 535     _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
 536     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
 537     _TESTS = [{
 538         'url': 'https://vimeo.com/nkistudio/videos',
 539         'info_dict': {
 540             'title': 'Nki',
 541             'id': 'nkistudio',
 542         },
 543         'playlist_mincount': 66,
 544     }]
 545
 546     def _real_extract(self, url):
 547         mobj = re.match(self._VALID_URL, url)
 548         name = mobj.group('name')
 549         return self._extract_videos(name, 'https://vimeo.com/%s' % name)
 550
 551
 552 class VimeoAlbumIE(VimeoChannelIE):
 553     IE_NAME = 'vimeo:album'
 554     _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)'
 555     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
 556     _TESTS = [{
 557         'url': 'https://vimeo.com/album/2632481',
 558         'info_dict': {
 559             'id': '2632481',
 560             'title': 'Staff Favorites: November 2013',
 561         },
 562         'playlist_mincount': 13,
 563     }, {
 564         'note': 'Password-protected album',
 565         'url': 'https://vimeo.com/album/3253534',
 566         'info_dict': {
 567             'title': 'test',
 568             'id': '3253534',
 569         },
 570         'playlist_count': 1,
 571         'params': {
 572             'videopassword': 'youtube-dl',
 573         }
 574     }]
 575
 576     def _page_url(self, base_url, pagenum):
 577         return '%s/page:%d/' % (base_url, pagenum)
 578
 579     def _real_extract(self, url):
 580         album_id = self._match_id(url)
 581         return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id)
 582
 583
 584 class VimeoGroupsIE(VimeoAlbumIE):
 585     IE_NAME = 'vimeo:group'
 586     _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)'
 587     _TESTS = [{
 588         'url': 'https://vimeo.com/groups/rolexawards',
 589         'info_dict': {
 590             'id': 'rolexawards',
 591             'title': 'Rolex Awards for Enterprise',
 592         },
 593         'playlist_mincount': 73,
 594     }]
 595
 596     def _extract_list_title(self, webpage):
 597         return self._og_search_title(webpage)
 598
 599     def _real_extract(self, url):
 600         mobj = re.match(self._VALID_URL, url)
 601         name = mobj.group('name')
 602         return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
 603
 604
 605 class VimeoReviewIE(InfoExtractor):
 606     IE_NAME = 'vimeo:review'
 607     IE_DESC = 'Review pages on vimeo'
 608     _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
 609     _TESTS = [{
 610         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
 611         'md5': 'c507a72f780cacc12b2248bb4006d253',
 612         'info_dict': {
 613             'id': '75524534',
 614             'ext': 'mp4',
 615             'title': "DICK HARDWICK 'Comedian'",
 616             'uploader': 'Richard Hardwick',
 617         }
 618     }, {
 619         'note': 'video player needs Referer',
 620         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
 621         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
 622         'info_dict': {
 623             'id': '91613211',
 624             'ext': 'mp4',
 625             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
 626             'uploader': 'DevWeek Events',
 627             'duration': 2773,
 628             'thumbnail': 're:^https?://.*\.jpg$',
 629         }
 630     }]
 631
 632     def _real_extract(self, url):
 633         mobj = re.match(self._VALID_URL, url)
 634         video_id = mobj.group('id')
 635         player_url = 'https://player.vimeo.com/player/' + video_id
 636         return self.url_result(player_url, 'Vimeo', video_id)
 637
 638
 639 class VimeoWatchLaterIE(VimeoChannelIE):
 640     IE_NAME = 'vimeo:watchlater'
 641     IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
 642     _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
 643     _TITLE = 'Watch Later'
 644     _LOGIN_REQUIRED = True
 645     _TESTS = [{
 646         'url': 'https://vimeo.com/watchlater',
 647         'only_matching': True,
 648     }]
 649
 650     def _real_initialize(self):
 651         self._login()
 652
 653     def _page_url(self, base_url, pagenum):
 654         url = '%s/page:%d/' % (base_url, pagenum)
 655         request = compat_urllib_request.Request(url)
 656         # Set the header to get a partial html page with the ids,
 657         # the normal page doesn't contain them.
 658         request.add_header('X-Requested-With', 'XMLHttpRequest')
 659         return request
 660
 661     def _real_extract(self, url):
 662         return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
 663
 664
 665 class VimeoLikesIE(InfoExtractor):
 666     _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
 667     IE_NAME = 'vimeo:likes'
 668     IE_DESC = 'Vimeo user likes'
 669     _TEST = {
 670         'url': 'https://vimeo.com/user755559/likes/',
 671         'playlist_mincount': 293,
 672         "info_dict": {
 673             'id': 'user755559_likes',
 674             "description": "See all the videos urza likes",
 675             "title": 'Videos urza likes',
 676         },
 677     }
 678
 679     def _real_extract(self, url):
 680         user_id = self._match_id(url)
 681         webpage = self._download_webpage(url, user_id)
 682         page_count = self._int(
 683             self._search_regex(
 684                 r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
 685                     .*?</a></li>\s*<li\s+class="pagination_next">
 686                 ''', webpage, 'page count'),
 687             'page count', fatal=True)
 688         PAGE_SIZE = 12
 689         title = self._html_search_regex(
 690             r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
 691         description = self._html_search_meta('description', webpage)
 692
 693         def _get_page(idx):
 694             page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
 695                 user_id, idx + 1)
 696             webpage = self._download_webpage(
 697                 page_url, user_id,
 698                 note='Downloading page %d/%d' % (idx + 1, page_count))
 699             video_list = self._search_regex(
 700                 r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
 701                 webpage, 'video content')
 702             paths = re.findall(
 703                 r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
 704             for path in paths:
 705                 yield {
 706                     '_type': 'url',
 707                     'url': compat_urlparse.urljoin(page_url, path),
 708                 }
 709
 710         pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
 711
 712         return {
 713             '_type': 'playlist',
 714             'id': 'user%s_likes' % user_id,
 715             'title': title,
 716             'description': description,
 717             'entries': pl,
 718         }