_ 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 .subtitles import SubtitlesInfoExtractor
  10 from ..compat import (
  11     compat_HTTPError,
  12     compat_urllib_parse,
  13     compat_urllib_request,
  14     compat_urlparse,
  15 )
  16 from ..utils import (
  17     ExtractorError,
  18     InAdvancePagedList,
  19     int_or_none,
  20     RegexNotFoundError,
  21     smuggle_url,
  22     std_headers,
  23     unsmuggle_url,
  24     urlencode_postdata,
  25 )
  26
  27
  28 class VimeoBaseInfoExtractor(InfoExtractor):
  29     _NETRC_MACHINE = 'vimeo'
  30     _LOGIN_REQUIRED = False
  31
  32     def _login(self):
  33         (username, password) = self._get_login_info()
  34         if username is None:
  35             if self._LOGIN_REQUIRED:
  36                 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
  37             return
  38         self.report_login()
  39         login_url = 'https://vimeo.com/log_in'
  40         webpage = self._download_webpage(login_url, None, False)
  41         token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
  42         data = urlencode_postdata({
  43             'email': username,
  44             'password': password,
  45             'action': 'login',
  46             'service': 'vimeo',
  47             'token': token,
  48         })
  49         login_request = compat_urllib_request.Request(login_url, data)
  50         login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  51         login_request.add_header('Cookie', 'xsrft=%s' % token)
  52         self._download_webpage(login_request, None, False, 'Wrong login info')
  53
  54
  55 class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor):
  56     """Information extractor for vimeo.com."""
  57
  58     # _VALID_URL matches Vimeo URLs
  59     _VALID_URL = r'''(?x)
  60         https?://
  61         (?:(?:www|(?P<player>player))\.)?
  62         vimeo(?P<pro>pro)?\.com/
  63         (?!channels/[^/?#]+/?(?:$|[?#])|album/)
  64         (?:.*?/)?
  65         (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)?
  66         (?:videos?/)?
  67         (?P<id>[0-9]+)
  68         /?(?:[?&].*)?(?:[#].*)?$'''
  69     IE_NAME = 'vimeo'
  70     _TESTS = [
  71         {
  72             'url': 'http://vimeo.com/56015672#at=0',
  73             'md5': '8879b6cc097e987f02484baf890129e5',
  74             'info_dict': {
  75                 'id': '56015672',
  76                 'ext': 'mp4',
  77                 "upload_date": "20121220",
  78                 "description": "This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
  79                 "uploader_id": "user7108434",
  80                 "uploader": "Filippo Valsorda",
  81                 "title": "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
  82                 "duration": 10,
  83             },
  84         },
  85         {
  86             'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
  87             'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
  88             'note': 'Vimeo Pro video (#1197)',
  89             'info_dict': {
  90                 'id': '68093876',
  91                 'ext': 'mp4',
  92                 'uploader_id': 'openstreetmapus',
  93                 'uploader': 'OpenStreetMap US',
  94                 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
  95                 'description': 'md5:380943ec71b89736ff4bf27183233d09',
  96                 'duration': 1595,
  97             },
  98         },
  99         {
 100             'url': 'http://player.vimeo.com/video/54469442',
 101             'md5': '619b811a4417aa4abe78dc653becf511',
 102             'note': 'Videos that embed the url in the player page',
 103             'info_dict': {
 104                 'id': '54469442',
 105                 'ext': 'mp4',
 106                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
 107                 'uploader': 'The BLN & Business of Software',
 108                 'uploader_id': 'theblnbusinessofsoftware',
 109                 'duration': 3610,
 110                 'description': None,
 111             },
 112         },
 113         {
 114             'url': 'http://vimeo.com/68375962',
 115             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 116             'note': 'Video protected with password',
 117             'info_dict': {
 118                 'id': '68375962',
 119                 'ext': 'mp4',
 120                 'title': 'youtube-dl password protected test video',
 121                 'upload_date': '20130614',
 122                 'uploader_id': 'user18948128',
 123                 'uploader': 'Jaime Marquínez Ferrándiz',
 124                 'duration': 10,
 125                 'description': 'This is "youtube-dl password protected test video" by Jaime Marquínez Ferrándiz on Vimeo, the home for high quality videos and the people who love them.',
 126             },
 127             'params': {
 128                 'videopassword': 'youtube-dl',
 129             },
 130         },
 131         {
 132             'url': 'http://vimeo.com/channels/keypeele/75629013',
 133             'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
 134             'note': 'Video is freely available via original URL '
 135                     'and protected with password when accessed via http://vimeo.com/75629013',
 136             'info_dict': {
 137                 'id': '75629013',
 138                 'ext': 'mp4',
 139                 'title': 'Key & Peele: Terrorist Interrogation',
 140                 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
 141                 'uploader_id': 'atencio',
 142                 'uploader': 'Peter Atencio',
 143                 'duration': 187,
 144             },
 145         },
 146         {
 147             'url': 'http://vimeo.com/76979871',
 148             'md5': '3363dd6ffebe3784d56f4132317fd446',
 149             'note': 'Video with subtitles',
 150             'info_dict': {
 151                 'id': '76979871',
 152                 'ext': 'mp4',
 153                 'title': 'The New Vimeo Player (You Know, For Videos)',
 154                 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
 155                 'upload_date': '20131015',
 156                 'uploader_id': 'staff',
 157                 'uploader': 'Vimeo Staff',
 158                 'duration': 62,
 159             }
 160         },
 161         {
 162             # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
 163             'url': 'https://player.vimeo.com/video/98044508',
 164             'note': 'The js code contains assignments to the same variable as the config',
 165             'info_dict': {
 166                 'id': '98044508',
 167                 'ext': 'mp4',
 168                 'title': 'Pier Solar OUYA Official Trailer',
 169                 'uploader': 'Tulio Gonçalves',
 170                 'uploader_id': 'user28849593',
 171             },
 172         },
 173     ]
 174
 175     def _verify_video_password(self, url, video_id, webpage):
 176         password = self._downloader.params.get('videopassword', None)
 177         if password is None:
 178             raise ExtractorError('This video is protected by a password, use the --video-password option')
 179         token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
 180         data = compat_urllib_parse.urlencode({
 181             'password': password,
 182             'token': token,
 183         })
 184         # I didn't manage to use the password with https
 185         if url.startswith('https'):
 186             pass_url = url.replace('https', 'http')
 187         else:
 188             pass_url = url
 189         password_request = compat_urllib_request.Request(pass_url + '/password', data)
 190         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 191         password_request.add_header('Cookie', 'xsrft=%s' % token)
 192         return self._download_webpage(
 193             password_request, video_id,
 194             'Verifying the password', 'Wrong password')
 195
 196     def _verify_player_video_password(self, url, video_id):
 197         password = self._downloader.params.get('videopassword', None)
 198         if password is None:
 199             raise ExtractorError('This video is protected by a password, use the --video-password option')
 200         data = compat_urllib_parse.urlencode({'password': password})
 201         pass_url = url + '/check-password'
 202         password_request = compat_urllib_request.Request(pass_url, data)
 203         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 204         return self._download_json(
 205             password_request, video_id,
 206             'Verifying the password',
 207             'Wrong password')
 208
 209     def _real_initialize(self):
 210         self._login()
 211
 212     def _real_extract(self, url):
 213         url, data = unsmuggle_url(url)
 214         headers = std_headers
 215         if data is not None:
 216             headers = headers.copy()
 217             headers.update(data)
 218         if 'Referer' not in headers:
 219             headers['Referer'] = url
 220
 221         # Extract ID from URL
 222         mobj = re.match(self._VALID_URL, url)
 223         video_id = mobj.group('id')
 224         orig_url = url
 225         if mobj.group('pro') or mobj.group('player'):
 226             url = 'http://player.vimeo.com/video/' + video_id
 227
 228         # Retrieve video webpage to extract further information
 229         request = compat_urllib_request.Request(url, None, headers)
 230         try:
 231             webpage = self._download_webpage(request, video_id)
 232         except ExtractorError as ee:
 233             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
 234                 errmsg = ee.cause.read()
 235                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 236                     raise ExtractorError(
 237                         'Cannot download embed-only video without embedding '
 238                         'URL. Please call youtube-dl with the URL of the page '
 239                         'that embeds this video.',
 240                         expected=True)
 241             raise
 242
 243         # Now we begin extracting as much information as we can from what we
 244         # retrieved. First we extract the information common to all extractors,
 245         # and latter we extract those that are Vimeo specific.
 246         self.report_extraction(video_id)
 247
 248         # Extract the config JSON
 249         try:
 250             try:
 251                 config_url = self._html_search_regex(
 252                     r' data-config-url="(.+?)"', webpage, 'config URL')
 253                 config_json = self._download_webpage(config_url, video_id)
 254                 config = json.loads(config_json)
 255             except RegexNotFoundError:
 256                 # For pro videos or player.vimeo.com urls
 257                 # We try to find out to which variable is assigned the config dic
 258                 m_variable_name = re.search('(\w)\.video\.id', webpage)
 259                 if m_variable_name is not None:
 260                     config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))
 261                 else:
 262                     config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
 263                 config = self._search_regex(config_re, webpage, 'info section',
 264                                             flags=re.DOTALL)
 265                 config = json.loads(config)
 266         except Exception as e:
 267             if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
 268                 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
 269
 270             if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
 271                 if data and '_video_password_verified' in data:
 272                     raise ExtractorError('video password verification failed!')
 273                 self._verify_video_password(url, video_id, webpage)
 274                 return self._real_extract(
 275                     smuggle_url(url, {'_video_password_verified': 'verified'}))
 276             else:
 277                 raise ExtractorError('Unable to extract info section',
 278                                      cause=e)
 279         else:
 280             if config.get('view') == 4:
 281                 config = self._verify_player_video_password(url, video_id)
 282
 283         # Extract title
 284         video_title = config["video"]["title"]
 285
 286         # Extract uploader and uploader_id
 287         video_uploader = config["video"]["owner"]["name"]
 288         video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None
 289
 290         # Extract video thumbnail
 291         video_thumbnail = config["video"].get("thumbnail")
 292         if video_thumbnail is None:
 293             video_thumbs = config["video"].get("thumbs")
 294             if video_thumbs and isinstance(video_thumbs, dict):
 295                 _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
 296
 297         # Extract video description
 298
 299         video_description = self._html_search_regex(
 300             r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 301             webpage, 'description', default=None)
 302         if not video_description:
 303             video_description = self._html_search_meta(
 304                 'description', webpage, default=None)
 305         if not video_description and mobj.group('pro'):
 306             orig_webpage = self._download_webpage(
 307                 orig_url, video_id,
 308                 note='Downloading webpage for description',
 309                 fatal=False)
 310             if orig_webpage:
 311                 video_description = self._html_search_meta(
 312                     'description', orig_webpage, default=None)
 313         if not video_description and not mobj.group('player'):
 314             self._downloader.report_warning('Cannot find video description')
 315
 316         # Extract video duration
 317         video_duration = int_or_none(config["video"].get("duration"))
 318
 319         # Extract upload date
 320         video_upload_date = None
 321         mobj = re.search(r'<meta itemprop="dateCreated" content="(\d{4})-(\d{2})-(\d{2})T', webpage)
 322         if mobj is not None:
 323             video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3)
 324
 325         try:
 326             view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
 327             like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
 328             comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
 329         except RegexNotFoundError:
 330             # This info is only available in vimeo.com/{id} urls
 331             view_count = None
 332             like_count = None
 333             comment_count = None
 334
 335         # Vimeo specific: extract request signature and timestamp
 336         sig = config['request']['signature']
 337         timestamp = config['request']['timestamp']
 338
 339         # Vimeo specific: extract video codec and quality information
 340         # First consider quality, then codecs, then take everything
 341         codecs = [('vp6', 'flv'), ('vp8', 'flv'), ('h264', 'mp4')]
 342         files = {'hd': [], 'sd': [], 'other': []}
 343         config_files = config["video"].get("files") or config["request"].get("files")
 344         for codec_name, codec_extension in codecs:
 345             for quality in config_files.get(codec_name, []):
 346                 format_id = '-'.join((codec_name, quality)).lower()
 347                 key = quality if quality in files else 'other'
 348                 video_url = None
 349                 if isinstance(config_files[codec_name], dict):
 350                     file_info = config_files[codec_name][quality]
 351                     video_url = file_info.get('url')
 352                 else:
 353                     file_info = {}
 354                 if video_url is None:
 355                     video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
 356                         % (video_id, sig, timestamp, quality, codec_name.upper())
 357
 358                 files[key].append({
 359                     'ext': codec_extension,
 360                     'url': video_url,
 361                     'format_id': format_id,
 362                     'width': file_info.get('width'),
 363                     'height': file_info.get('height'),
 364                 })
 365         formats = []
 366         for key in ('other', 'sd', 'hd'):
 367             formats += files[key]
 368         if len(formats) == 0:
 369             raise ExtractorError('No known codec found')
 370
 371         subtitles = {}
 372         text_tracks = config['request'].get('text_tracks')
 373         if text_tracks:
 374             for tt in text_tracks:
 375                 subtitles[tt['lang']] = 'http://vimeo.com' + tt['url']
 376
 377         video_subtitles = self.extract_subtitles(video_id, subtitles)
 378         if self._downloader.params.get('listsubtitles', False):
 379             self._list_available_subtitles(video_id, subtitles)
 380             return
 381
 382         return {
 383             'id': video_id,
 384             'uploader': video_uploader,
 385             'uploader_id': video_uploader_id,
 386             'upload_date': video_upload_date,
 387             'title': video_title,
 388             'thumbnail': video_thumbnail,
 389             'description': video_description,
 390             'duration': video_duration,
 391             'formats': formats,
 392             'webpage_url': url,
 393             'view_count': view_count,
 394             'like_count': like_count,
 395             'comment_count': comment_count,
 396             'subtitles': video_subtitles,
 397         }
 398
 399
 400 class VimeoChannelIE(InfoExtractor):
 401     IE_NAME = 'vimeo:channel'
 402     _VALID_URL = r'https?://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
 403     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
 404     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
 405     _TESTS = [{
 406         'url': 'http://vimeo.com/channels/tributes',
 407         'info_dict': {
 408             'title': 'Vimeo Tributes',
 409         },
 410         'playlist_mincount': 25,
 411     }]
 412
 413     def _page_url(self, base_url, pagenum):
 414         return '%s/videos/page:%d/' % (base_url, pagenum)
 415
 416     def _extract_list_title(self, webpage):
 417         return self._html_search_regex(self._TITLE_RE, webpage, 'list title')
 418
 419     def _login_list_password(self, page_url, list_id, webpage):
 420         login_form = self._search_regex(
 421             r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
 422             webpage, 'login form', default=None)
 423         if not login_form:
 424             return webpage
 425
 426         password = self._downloader.params.get('videopassword', None)
 427         if password is None:
 428             raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
 429         fields = dict(re.findall(r'''(?x)<input\s+
 430             type="hidden"\s+
 431             name="([^"]+)"\s+
 432             value="([^"]*)"
 433             ''', login_form))
 434         token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
 435         fields['token'] = token
 436         fields['password'] = password
 437         post = compat_urllib_parse.urlencode(fields)
 438         password_path = self._search_regex(
 439             r'action="([^"]+)"', login_form, 'password URL')
 440         password_url = compat_urlparse.urljoin(page_url, password_path)
 441         password_request = compat_urllib_request.Request(password_url, post)
 442         password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
 443         self._set_cookie('vimeo.com', 'xsrft', token)
 444
 445         return self._download_webpage(
 446             password_request, list_id,
 447             'Verifying the password', 'Wrong password')
 448
 449     def _extract_videos(self, list_id, base_url):
 450         video_ids = []
 451         for pagenum in itertools.count(1):
 452             page_url = self._page_url(base_url, pagenum)
 453             webpage = self._download_webpage(
 454                 page_url, list_id,
 455                 'Downloading page %s' % pagenum)
 456
 457             if pagenum == 1:
 458                 webpage = self._login_list_password(page_url, list_id, webpage)
 459
 460             video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage))
 461             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
 462                 break
 463
 464         entries = [self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo')
 465                    for video_id in video_ids]
 466         return {'_type': 'playlist',
 467                 'id': list_id,
 468                 'title': self._extract_list_title(webpage),
 469                 'entries': entries,
 470                 }
 471
 472     def _real_extract(self, url):
 473         mobj = re.match(self._VALID_URL, url)
 474         channel_id = mobj.group('id')
 475         return self._extract_videos(channel_id, 'http://vimeo.com/channels/%s' % channel_id)
 476
 477
 478 class VimeoUserIE(VimeoChannelIE):
 479     IE_NAME = 'vimeo:user'
 480     _VALID_URL = r'https?://vimeo\.com/(?![0-9]+(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
 481     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
 482     _TESTS = [{
 483         'url': 'http://vimeo.com/nkistudio/videos',
 484         'info_dict': {
 485             'title': 'Nki',
 486         },
 487         'playlist_mincount': 66,
 488     }]
 489
 490     def _real_extract(self, url):
 491         mobj = re.match(self._VALID_URL, url)
 492         name = mobj.group('name')
 493         return self._extract_videos(name, 'http://vimeo.com/%s' % name)
 494
 495
 496 class VimeoAlbumIE(VimeoChannelIE):
 497     IE_NAME = 'vimeo:album'
 498     _VALID_URL = r'https?://vimeo\.com/album/(?P<id>\d+)'
 499     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
 500     _TESTS = [{
 501         'url': 'http://vimeo.com/album/2632481',
 502         'info_dict': {
 503             'title': 'Staff Favorites: November 2013',
 504         },
 505         'playlist_mincount': 13,
 506     }, {
 507         'note': 'Password-protected album',
 508         'url': 'https://vimeo.com/album/3253534',
 509         'info_dict': {
 510             'title': 'test',
 511             'id': '3253534',
 512         },
 513         'playlist_count': 1,
 514         'params': {
 515             'videopassword': 'youtube-dl',
 516         }
 517     }]
 518
 519     def _page_url(self, base_url, pagenum):
 520         return '%s/page:%d/' % (base_url, pagenum)
 521
 522     def _real_extract(self, url):
 523         album_id = self._match_id(url)
 524         return self._extract_videos(album_id, 'http://vimeo.com/album/%s' % album_id)
 525
 526
 527 class VimeoGroupsIE(VimeoAlbumIE):
 528     IE_NAME = 'vimeo:group'
 529     _VALID_URL = r'(?:https?://)?vimeo\.com/groups/(?P<name>[^/]+)'
 530     _TESTS = [{
 531         'url': 'http://vimeo.com/groups/rolexawards',
 532         'info_dict': {
 533             'title': 'Rolex Awards for Enterprise',
 534         },
 535         'playlist_mincount': 73,
 536     }]
 537
 538     def _extract_list_title(self, webpage):
 539         return self._og_search_title(webpage)
 540
 541     def _real_extract(self, url):
 542         mobj = re.match(self._VALID_URL, url)
 543         name = mobj.group('name')
 544         return self._extract_videos(name, 'http://vimeo.com/groups/%s' % name)
 545
 546
 547 class VimeoReviewIE(InfoExtractor):
 548     IE_NAME = 'vimeo:review'
 549     IE_DESC = 'Review pages on vimeo'
 550     _VALID_URL = r'https?://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
 551     _TESTS = [{
 552         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
 553         'md5': 'c507a72f780cacc12b2248bb4006d253',
 554         'info_dict': {
 555             'id': '75524534',
 556             'ext': 'mp4',
 557             'title': "DICK HARDWICK 'Comedian'",
 558             'uploader': 'Richard Hardwick',
 559         }
 560     }, {
 561         'note': 'video player needs Referer',
 562         'url': 'http://vimeo.com/user22258446/review/91613211/13f927e053',
 563         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
 564         'info_dict': {
 565             'id': '91613211',
 566             'ext': 'mp4',
 567             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
 568             'uploader': 'DevWeek Events',
 569             'duration': 2773,
 570             'thumbnail': 're:^https?://.*\.jpg$',
 571         }
 572     }]
 573
 574     def _real_extract(self, url):
 575         mobj = re.match(self._VALID_URL, url)
 576         video_id = mobj.group('id')
 577         player_url = 'https://player.vimeo.com/player/' + video_id
 578         return self.url_result(player_url, 'Vimeo', video_id)
 579
 580
 581 class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE):
 582     IE_NAME = 'vimeo:watchlater'
 583     IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
 584     _VALID_URL = r'https?://vimeo\.com/home/watchlater|:vimeowatchlater'
 585     _LOGIN_REQUIRED = True
 586     _TITLE_RE = r'href="/home/watchlater".*?>(.*?)<'
 587     _TESTS = [{
 588         'url': 'http://vimeo.com/home/watchlater',
 589         'only_matching': True,
 590     }]
 591
 592     def _real_initialize(self):
 593         self._login()
 594
 595     def _page_url(self, base_url, pagenum):
 596         url = '%s/page:%d/' % (base_url, pagenum)
 597         request = compat_urllib_request.Request(url)
 598         # Set the header to get a partial html page with the ids,
 599         # the normal page doesn't contain them.
 600         request.add_header('X-Requested-With', 'XMLHttpRequest')
 601         return request
 602
 603     def _real_extract(self, url):
 604         return self._extract_videos('watchlater', 'https://vimeo.com/home/watchlater')
 605
 606
 607 class VimeoLikesIE(InfoExtractor):
 608     _VALID_URL = r'https?://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
 609     IE_NAME = 'vimeo:likes'
 610     IE_DESC = 'Vimeo user likes'
 611     _TEST = {
 612         'url': 'https://vimeo.com/user755559/likes/',
 613         'playlist_mincount': 293,
 614         "info_dict": {
 615             "description": "See all the videos urza likes",
 616             "title": 'Videos urza likes',
 617         },
 618     }
 619
 620     def _real_extract(self, url):
 621         user_id = self._match_id(url)
 622         webpage = self._download_webpage(url, user_id)
 623         page_count = self._int(
 624             self._search_regex(
 625                 r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
 626                     .*?</a></li>\s*<li\s+class="pagination_next">
 627                 ''', webpage, 'page count'),
 628             'page count', fatal=True)
 629         PAGE_SIZE = 12
 630         title = self._html_search_regex(
 631             r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
 632         description = self._html_search_meta('description', webpage)
 633
 634         def _get_page(idx):
 635             page_url = '%s//vimeo.com/user%s/likes/page:%d/sort:date' % (
 636                 self.http_scheme(), user_id, idx + 1)
 637             webpage = self._download_webpage(
 638                 page_url, user_id,
 639                 note='Downloading page %d/%d' % (idx + 1, page_count))
 640             video_list = self._search_regex(
 641                 r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
 642                 webpage, 'video content')
 643             paths = re.findall(
 644                 r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
 645             for path in paths:
 646                 yield {
 647                     '_type': 'url',
 648                     'url': compat_urlparse.urljoin(page_url, path),
 649                 }
 650
 651         pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
 652
 653         return {
 654             '_type': 'playlist',
 655             'id': 'user%s_likes' % user_id,
 656             'title': title,
 657             'description': description,
 658             'entries': pl,
 659         }