_ Git - youtube-dl/blob - youtube_dl/extractor/vimeo.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import re
   6 import itertools
   7
   8 from .common import InfoExtractor
   9 from ..compat import (
  10     compat_HTTPError,
  11     compat_urlparse,
  12 )
  13 from ..utils import (
  14     encode_dict,
  15     ExtractorError,
  16     InAdvancePagedList,
  17     int_or_none,
  18     RegexNotFoundError,
  19     sanitized_Request,
  20     smuggle_url,
  21     std_headers,
  22     unified_strdate,
  23     unsmuggle_url,
  24     urlencode_postdata,
  25     unescapeHTML,
  26     parse_filesize,
  27 )
  28
  29
  30 class VimeoBaseInfoExtractor(InfoExtractor):
  31     _NETRC_MACHINE = 'vimeo'
  32     _LOGIN_REQUIRED = False
  33     _LOGIN_URL = 'https://vimeo.com/log_in'
  34
  35     def _login(self):
  36         (username, password) = self._get_login_info()
  37         if username is None:
  38             if self._LOGIN_REQUIRED:
  39                 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
  40             return
  41         self.report_login()
  42         webpage = self._download_webpage(self._LOGIN_URL, None, False)
  43         token, vuid = self._extract_xsrft_and_vuid(webpage)
  44         data = urlencode_postdata(encode_dict({
  45             'action': 'login',
  46             'email': username,
  47             'password': password,
  48             'service': 'vimeo',
  49             'token': token,
  50         }))
  51         login_request = sanitized_Request(self._LOGIN_URL, data)
  52         login_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  53         login_request.add_header('Referer', self._LOGIN_URL)
  54         self._set_vimeo_cookie('vuid', vuid)
  55         self._download_webpage(login_request, None, False, 'Wrong login info')
  56
  57     def _extract_xsrft_and_vuid(self, webpage):
  58         xsrft = self._search_regex(
  59             r'xsrft\s*[=:]\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
  60             webpage, 'login token', group='xsrft')
  61         vuid = self._search_regex(
  62             r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
  63             webpage, 'vuid', group='vuid')
  64         return xsrft, vuid
  65
  66     def _set_vimeo_cookie(self, name, value):
  67         self._set_cookie('vimeo.com', name, value)
  68
  69
  70 class VimeoIE(VimeoBaseInfoExtractor):
  71     """Information extractor for vimeo.com."""
  72
  73     # _VALID_URL matches Vimeo URLs
  74     _VALID_URL = r'''(?x)
  75         https?://
  76         (?:(?:www|(?P<player>player))\.)?
  77         vimeo(?P<pro>pro)?\.com/
  78         (?!channels/[^/?#]+/?(?:$|[?#])|album/)
  79         (?:.*?/)?
  80         (?:(?:play_redirect_hls|moogaloop\.swf)\?clip_id=)?
  81         (?:videos?/)?
  82         (?P<id>[0-9]+)
  83         /?(?:[?&].*)?(?:[#].*)?$'''
  84     IE_NAME = 'vimeo'
  85     _TESTS = [
  86         {
  87             'url': 'http://vimeo.com/56015672#at=0',
  88             'md5': '8879b6cc097e987f02484baf890129e5',
  89             'info_dict': {
  90                 'id': '56015672',
  91                 'ext': 'mp4',
  92                 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
  93                 'description': 'md5:2d3305bad981a06ff79f027f19865021',
  94                 'upload_date': '20121220',
  95                 'uploader_id': 'user7108434',
  96                 'uploader': 'Filippo Valsorda',
  97                 'duration': 10,
  98             },
  99         },
 100         {
 101             'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
 102             'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
 103             'note': 'Vimeo Pro video (#1197)',
 104             'info_dict': {
 105                 'id': '68093876',
 106                 'ext': 'mp4',
 107                 'uploader_id': 'openstreetmapus',
 108                 'uploader': 'OpenStreetMap US',
 109                 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
 110                 'description': 'md5:fd69a7b8d8c34a4e1d2ec2e4afd6ec30',
 111                 'duration': 1595,
 112             },
 113         },
 114         {
 115             'url': 'http://player.vimeo.com/video/54469442',
 116             'md5': '619b811a4417aa4abe78dc653becf511',
 117             'note': 'Videos that embed the url in the player page',
 118             'info_dict': {
 119                 'id': '54469442',
 120                 'ext': 'mp4',
 121                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
 122                 'uploader': 'The BLN & Business of Software',
 123                 'uploader_id': 'theblnbusinessofsoftware',
 124                 'duration': 3610,
 125                 'description': None,
 126             },
 127         },
 128         {
 129             'url': 'http://vimeo.com/68375962',
 130             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 131             'note': 'Video protected with password',
 132             'info_dict': {
 133                 'id': '68375962',
 134                 'ext': 'mp4',
 135                 'title': 'youtube-dl password protected test video',
 136                 'upload_date': '20130614',
 137                 'uploader_id': 'user18948128',
 138                 'uploader': 'Jaime Marquínez Ferrándiz',
 139                 'duration': 10,
 140                 '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',
 141             },
 142             'params': {
 143                 'videopassword': 'youtube-dl',
 144             },
 145         },
 146         {
 147             'url': 'http://vimeo.com/channels/keypeele/75629013',
 148             'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
 149             'note': 'Video is freely available via original URL '
 150                     'and protected with password when accessed via http://vimeo.com/75629013',
 151             'info_dict': {
 152                 'id': '75629013',
 153                 'ext': 'mp4',
 154                 'title': 'Key & Peele: Terrorist Interrogation',
 155                 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
 156                 'uploader_id': 'atencio',
 157                 'uploader': 'Peter Atencio',
 158                 'upload_date': '20130927',
 159                 'duration': 187,
 160             },
 161         },
 162         {
 163             'url': 'http://vimeo.com/76979871',
 164             'note': 'Video with subtitles',
 165             'info_dict': {
 166                 'id': '76979871',
 167                 'ext': 'mp4',
 168                 'title': 'The New Vimeo Player (You Know, For Videos)',
 169                 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
 170                 'upload_date': '20131015',
 171                 'uploader_id': 'staff',
 172                 'uploader': 'Vimeo Staff',
 173                 'duration': 62,
 174             }
 175         },
 176         {
 177             # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
 178             'url': 'https://player.vimeo.com/video/98044508',
 179             'note': 'The js code contains assignments to the same variable as the config',
 180             'info_dict': {
 181                 'id': '98044508',
 182                 'ext': 'mp4',
 183                 'title': 'Pier Solar OUYA Official Trailer',
 184                 'uploader': 'Tulio Gonçalves',
 185                 'uploader_id': 'user28849593',
 186             },
 187         },
 188         {
 189             # contains original format
 190             'url': 'https://vimeo.com/33951933',
 191             'md5': '53c688fa95a55bf4b7293d37a89c5c53',
 192             'info_dict': {
 193                 'id': '33951933',
 194                 'ext': 'mp4',
 195                 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
 196                 'uploader': 'The DMCI',
 197                 'uploader_id': 'dmci',
 198                 'upload_date': '20111220',
 199                 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
 200             },
 201         },
 202         {
 203             'url': 'https://vimeo.com/109815029',
 204             'note': 'Video not completely processed, "failed" seed status',
 205             'only_matching': True,
 206         },
 207         {
 208             'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
 209             'only_matching': True,
 210         },
 211     ]
 212
 213     @staticmethod
 214     def _extract_vimeo_url(url, webpage):
 215         # Look for embedded (iframe) Vimeo player
 216         mobj = re.search(
 217             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
 218         if mobj:
 219             player_url = unescapeHTML(mobj.group('url'))
 220             surl = smuggle_url(player_url, {'http_headers': {'Referer': url}})
 221             return surl
 222         # Look for embedded (swf embed) Vimeo player
 223         mobj = re.search(
 224             r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
 225         if mobj:
 226             return mobj.group(1)
 227
 228     def _verify_video_password(self, url, video_id, webpage):
 229         password = self._downloader.params.get('videopassword', None)
 230         if password is None:
 231             raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
 232         token, vuid = self._extract_xsrft_and_vuid(webpage)
 233         data = urlencode_postdata(encode_dict({
 234             'password': password,
 235             'token': token,
 236         }))
 237         if url.startswith('http://'):
 238             # vimeo only supports https now, but the user can give an http url
 239             url = url.replace('http://', 'https://')
 240         password_request = sanitized_Request(url + '/password', data)
 241         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 242         password_request.add_header('Referer', url)
 243         self._set_vimeo_cookie('vuid', vuid)
 244         return self._download_webpage(
 245             password_request, video_id,
 246             'Verifying the password', 'Wrong password')
 247
 248     def _verify_player_video_password(self, url, video_id):
 249         password = self._downloader.params.get('videopassword', None)
 250         if password is None:
 251             raise ExtractorError('This video is protected by a password, use the --video-password option')
 252         data = urlencode_postdata(encode_dict({'password': password}))
 253         pass_url = url + '/check-password'
 254         password_request = sanitized_Request(pass_url, data)
 255         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 256         return self._download_json(
 257             password_request, video_id,
 258             'Verifying the password',
 259             'Wrong password')
 260
 261     def _real_initialize(self):
 262         self._login()
 263
 264     def _real_extract(self, url):
 265         url, data = unsmuggle_url(url, {})
 266         headers = std_headers
 267         if 'http_headers' in data:
 268             headers = headers.copy()
 269             headers.update(data['http_headers'])
 270         if 'Referer' not in headers:
 271             headers['Referer'] = url
 272
 273         # Extract ID from URL
 274         mobj = re.match(self._VALID_URL, url)
 275         video_id = mobj.group('id')
 276         orig_url = url
 277         if mobj.group('pro') or mobj.group('player'):
 278             url = 'https://player.vimeo.com/video/' + video_id
 279         else:
 280             url = 'https://vimeo.com/' + video_id
 281
 282         # Retrieve video webpage to extract further information
 283         request = sanitized_Request(url, None, headers)
 284         try:
 285             webpage = self._download_webpage(request, video_id)
 286         except ExtractorError as ee:
 287             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
 288                 errmsg = ee.cause.read()
 289                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 290                     raise ExtractorError(
 291                         'Cannot download embed-only video without embedding '
 292                         'URL. Please call youtube-dl with the URL of the page '
 293                         'that embeds this video.',
 294                         expected=True)
 295             raise
 296
 297         # Now we begin extracting as much information as we can from what we
 298         # retrieved. First we extract the information common to all extractors,
 299         # and latter we extract those that are Vimeo specific.
 300         self.report_extraction(video_id)
 301
 302         vimeo_config = self._search_regex(
 303             r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage,
 304             'vimeo config', default=None)
 305         if vimeo_config:
 306             seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
 307             if seed_status.get('state') == 'failed':
 308                 raise ExtractorError(
 309                     '%s said: %s' % (self.IE_NAME, seed_status['title']),
 310                     expected=True)
 311
 312         # Extract the config JSON
 313         try:
 314             try:
 315                 config_url = self._html_search_regex(
 316                     r' data-config-url="(.+?)"', webpage,
 317                     'config URL', default=None)
 318                 if not config_url:
 319                     # Sometimes new react-based page is served instead of old one that require
 320                     # different config URL extraction approach (see
 321                     # https://github.com/rg3/youtube-dl/pull/7209)
 322                     vimeo_clip_page_config = self._search_regex(
 323                         r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
 324                         'vimeo clip page config')
 325                     config_url = self._parse_json(
 326                         vimeo_clip_page_config, video_id)['player']['config_url']
 327                 config_json = self._download_webpage(config_url, video_id)
 328                 config = json.loads(config_json)
 329             except RegexNotFoundError:
 330                 # For pro videos or player.vimeo.com urls
 331                 # We try to find out to which variable is assigned the config dic
 332                 m_variable_name = re.search('(\w)\.video\.id', webpage)
 333                 if m_variable_name is not None:
 334                     config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))
 335                 else:
 336                     config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
 337                 config = self._search_regex(config_re, webpage, 'info section',
 338                                             flags=re.DOTALL)
 339                 config = json.loads(config)
 340         except Exception as e:
 341             if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
 342                 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
 343
 344             if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
 345                 if '_video_password_verified' in data:
 346                     raise ExtractorError('video password verification failed!')
 347                 self._verify_video_password(url, video_id, webpage)
 348                 return self._real_extract(
 349                     smuggle_url(url, {'_video_password_verified': 'verified'}))
 350             else:
 351                 raise ExtractorError('Unable to extract info section',
 352                                      cause=e)
 353         else:
 354             if config.get('view') == 4:
 355                 config = self._verify_player_video_password(url, video_id)
 356
 357         if '>You rented this title.<' in webpage:
 358             feature_id = config.get('video', {}).get('vod', {}).get('feature_id')
 359             if feature_id and not data.get('force_feature_id', False):
 360                 return self.url_result(smuggle_url(
 361                     'https://player.vimeo.com/player/%s' % feature_id,
 362                     {'force_feature_id': True}), 'Vimeo')
 363
 364         # Extract title
 365         video_title = config["video"]["title"]
 366
 367         # Extract uploader and uploader_id
 368         video_uploader = config["video"]["owner"]["name"]
 369         video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None
 370
 371         # Extract video thumbnail
 372         video_thumbnail = config["video"].get("thumbnail")
 373         if video_thumbnail is None:
 374             video_thumbs = config["video"].get("thumbs")
 375             if video_thumbs and isinstance(video_thumbs, dict):
 376                 _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
 377
 378         # Extract video description
 379
 380         video_description = self._html_search_regex(
 381             r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 382             webpage, 'description', default=None)
 383         if not video_description:
 384             video_description = self._html_search_meta(
 385                 'description', webpage, default=None)
 386         if not video_description and mobj.group('pro'):
 387             orig_webpage = self._download_webpage(
 388                 orig_url, video_id,
 389                 note='Downloading webpage for description',
 390                 fatal=False)
 391             if orig_webpage:
 392                 video_description = self._html_search_meta(
 393                     'description', orig_webpage, default=None)
 394         if not video_description and not mobj.group('player'):
 395             self._downloader.report_warning('Cannot find video description')
 396
 397         # Extract video duration
 398         video_duration = int_or_none(config["video"].get("duration"))
 399
 400         # Extract upload date
 401         video_upload_date = None
 402         mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage)
 403         if mobj is not None:
 404             video_upload_date = unified_strdate(mobj.group(1))
 405
 406         try:
 407             view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
 408             like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
 409             comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
 410         except RegexNotFoundError:
 411             # This info is only available in vimeo.com/{id} urls
 412             view_count = None
 413             like_count = None
 414             comment_count = None
 415
 416         formats = []
 417         download_request = sanitized_Request('https://vimeo.com/%s?action=load_download_config' % video_id, headers={
 418             'X-Requested-With': 'XMLHttpRequest'})
 419         download_data = self._download_json(download_request, video_id, fatal=False)
 420         if download_data:
 421             source_file = download_data.get('source_file')
 422             if source_file and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
 423                 formats.append({
 424                     'url': source_file['download_url'],
 425                     'ext': source_file['extension'].lower(),
 426                     'width': int_or_none(source_file.get('width')),
 427                     'height': int_or_none(source_file.get('height')),
 428                     'filesize': parse_filesize(source_file.get('size')),
 429                     'format_id': source_file.get('public_name', 'Original'),
 430                     'preference': 1,
 431                 })
 432         config_files = config['video'].get('files') or config['request'].get('files', {})
 433         for f in config_files.get('progressive', []):
 434             video_url = f.get('url')
 435             if not video_url:
 436                 continue
 437             formats.append({
 438                 'url': video_url,
 439                 'format_id': 'http-%s' % f.get('quality'),
 440                 'width': int_or_none(f.get('width')),
 441                 'height': int_or_none(f.get('height')),
 442                 'fps': int_or_none(f.get('fps')),
 443                 'tbr': int_or_none(f.get('bitrate')),
 444             })
 445         m3u8_url = config_files.get('hls', {}).get('url')
 446         if m3u8_url:
 447             formats.extend(self._extract_m3u8_formats(
 448                 m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
 449         # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
 450         # at the same time without actual units specified. This lead to wrong sorting.
 451         self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'format_id'))
 452
 453         subtitles = {}
 454         text_tracks = config['request'].get('text_tracks')
 455         if text_tracks:
 456             for tt in text_tracks:
 457                 subtitles[tt['lang']] = [{
 458                     'ext': 'vtt',
 459                     'url': 'https://vimeo.com' + tt['url'],
 460                 }]
 461
 462         return {
 463             'id': video_id,
 464             'uploader': video_uploader,
 465             'uploader_id': video_uploader_id,
 466             'upload_date': video_upload_date,
 467             'title': video_title,
 468             'thumbnail': video_thumbnail,
 469             'description': video_description,
 470             'duration': video_duration,
 471             'formats': formats,
 472             'webpage_url': url,
 473             'view_count': view_count,
 474             'like_count': like_count,
 475             'comment_count': comment_count,
 476             'subtitles': subtitles,
 477         }
 478
 479
 480 class VimeoChannelIE(VimeoBaseInfoExtractor):
 481     IE_NAME = 'vimeo:channel'
 482     _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
 483     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
 484     _TITLE = None
 485     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
 486     _TESTS = [{
 487         'url': 'https://vimeo.com/channels/tributes',
 488         'info_dict': {
 489             'id': 'tributes',
 490             'title': 'Vimeo Tributes',
 491         },
 492         'playlist_mincount': 25,
 493     }]
 494
 495     def _page_url(self, base_url, pagenum):
 496         return '%s/videos/page:%d/' % (base_url, pagenum)
 497
 498     def _extract_list_title(self, webpage):
 499         return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title')
 500
 501     def _login_list_password(self, page_url, list_id, webpage):
 502         login_form = self._search_regex(
 503             r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
 504             webpage, 'login form', default=None)
 505         if not login_form:
 506             return webpage
 507
 508         password = self._downloader.params.get('videopassword', None)
 509         if password is None:
 510             raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
 511         fields = self._hidden_inputs(login_form)
 512         token, vuid = self._extract_xsrft_and_vuid(webpage)
 513         fields['token'] = token
 514         fields['password'] = password
 515         post = urlencode_postdata(encode_dict(fields))
 516         password_path = self._search_regex(
 517             r'action="([^"]+)"', login_form, 'password URL')
 518         password_url = compat_urlparse.urljoin(page_url, password_path)
 519         password_request = sanitized_Request(password_url, post)
 520         password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
 521         self._set_vimeo_cookie('vuid', vuid)
 522         self._set_vimeo_cookie('xsrft', token)
 523
 524         return self._download_webpage(
 525             password_request, list_id,
 526             'Verifying the password', 'Wrong password')
 527
 528     def _title_and_entries(self, list_id, base_url):
 529         for pagenum in itertools.count(1):
 530             page_url = self._page_url(base_url, pagenum)
 531             webpage = self._download_webpage(
 532                 page_url, list_id,
 533                 'Downloading page %s' % pagenum)
 534
 535             if pagenum == 1:
 536                 webpage = self._login_list_password(page_url, list_id, webpage)
 537                 yield self._extract_list_title(webpage)
 538
 539             for video_id in re.findall(r'id="clip_(\d+?)"', webpage):
 540                 yield self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo')
 541
 542             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
 543                 break
 544
 545     def _extract_videos(self, list_id, base_url):
 546         title_and_entries = self._title_and_entries(list_id, base_url)
 547         list_title = next(title_and_entries)
 548         return self.playlist_result(title_and_entries, list_id, list_title)
 549
 550     def _real_extract(self, url):
 551         mobj = re.match(self._VALID_URL, url)
 552         channel_id = mobj.group('id')
 553         return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
 554
 555
 556 class VimeoUserIE(VimeoChannelIE):
 557     IE_NAME = 'vimeo:user'
 558     _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
 559     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
 560     _TESTS = [{
 561         'url': 'https://vimeo.com/nkistudio/videos',
 562         'info_dict': {
 563             'title': 'Nki',
 564             'id': 'nkistudio',
 565         },
 566         'playlist_mincount': 66,
 567     }]
 568
 569     def _real_extract(self, url):
 570         mobj = re.match(self._VALID_URL, url)
 571         name = mobj.group('name')
 572         return self._extract_videos(name, 'https://vimeo.com/%s' % name)
 573
 574
 575 class VimeoAlbumIE(VimeoChannelIE):
 576     IE_NAME = 'vimeo:album'
 577     _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)'
 578     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
 579     _TESTS = [{
 580         'url': 'https://vimeo.com/album/2632481',
 581         'info_dict': {
 582             'id': '2632481',
 583             'title': 'Staff Favorites: November 2013',
 584         },
 585         'playlist_mincount': 13,
 586     }, {
 587         'note': 'Password-protected album',
 588         'url': 'https://vimeo.com/album/3253534',
 589         'info_dict': {
 590             'title': 'test',
 591             'id': '3253534',
 592         },
 593         'playlist_count': 1,
 594         'params': {
 595             'videopassword': 'youtube-dl',
 596         }
 597     }]
 598
 599     def _page_url(self, base_url, pagenum):
 600         return '%s/page:%d/' % (base_url, pagenum)
 601
 602     def _real_extract(self, url):
 603         album_id = self._match_id(url)
 604         return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id)
 605
 606
 607 class VimeoGroupsIE(VimeoAlbumIE):
 608     IE_NAME = 'vimeo:group'
 609     _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)(?:/(?!videos?/\d+)|$)'
 610     _TESTS = [{
 611         'url': 'https://vimeo.com/groups/rolexawards',
 612         'info_dict': {
 613             'id': 'rolexawards',
 614             'title': 'Rolex Awards for Enterprise',
 615         },
 616         'playlist_mincount': 73,
 617     }]
 618
 619     def _extract_list_title(self, webpage):
 620         return self._og_search_title(webpage)
 621
 622     def _real_extract(self, url):
 623         mobj = re.match(self._VALID_URL, url)
 624         name = mobj.group('name')
 625         return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
 626
 627
 628 class VimeoReviewIE(InfoExtractor):
 629     IE_NAME = 'vimeo:review'
 630     IE_DESC = 'Review pages on vimeo'
 631     _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
 632     _TESTS = [{
 633         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
 634         'md5': 'c507a72f780cacc12b2248bb4006d253',
 635         'info_dict': {
 636             'id': '75524534',
 637             'ext': 'mp4',
 638             'title': "DICK HARDWICK 'Comedian'",
 639             'uploader': 'Richard Hardwick',
 640         }
 641     }, {
 642         'note': 'video player needs Referer',
 643         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
 644         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
 645         'info_dict': {
 646             'id': '91613211',
 647             'ext': 'mp4',
 648             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
 649             'uploader': 'DevWeek Events',
 650             'duration': 2773,
 651             'thumbnail': 're:^https?://.*\.jpg$',
 652         }
 653     }]
 654
 655     def _real_extract(self, url):
 656         mobj = re.match(self._VALID_URL, url)
 657         video_id = mobj.group('id')
 658         player_url = 'https://player.vimeo.com/player/' + video_id
 659         return self.url_result(player_url, 'Vimeo', video_id)
 660
 661
 662 class VimeoWatchLaterIE(VimeoChannelIE):
 663     IE_NAME = 'vimeo:watchlater'
 664     IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
 665     _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
 666     _TITLE = 'Watch Later'
 667     _LOGIN_REQUIRED = True
 668     _TESTS = [{
 669         'url': 'https://vimeo.com/watchlater',
 670         'only_matching': True,
 671     }]
 672
 673     def _real_initialize(self):
 674         self._login()
 675
 676     def _page_url(self, base_url, pagenum):
 677         url = '%s/page:%d/' % (base_url, pagenum)
 678         request = sanitized_Request(url)
 679         # Set the header to get a partial html page with the ids,
 680         # the normal page doesn't contain them.
 681         request.add_header('X-Requested-With', 'XMLHttpRequest')
 682         return request
 683
 684     def _real_extract(self, url):
 685         return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
 686
 687
 688 class VimeoLikesIE(InfoExtractor):
 689     _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
 690     IE_NAME = 'vimeo:likes'
 691     IE_DESC = 'Vimeo user likes'
 692     _TEST = {
 693         'url': 'https://vimeo.com/user755559/likes/',
 694         'playlist_mincount': 293,
 695         "info_dict": {
 696             'id': 'user755559_likes',
 697             "description": "See all the videos urza likes",
 698             "title": 'Videos urza likes',
 699         },
 700     }
 701
 702     def _real_extract(self, url):
 703         user_id = self._match_id(url)
 704         webpage = self._download_webpage(url, user_id)
 705         page_count = self._int(
 706             self._search_regex(
 707                 r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
 708                     .*?</a></li>\s*<li\s+class="pagination_next">
 709                 ''', webpage, 'page count'),
 710             'page count', fatal=True)
 711         PAGE_SIZE = 12
 712         title = self._html_search_regex(
 713             r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
 714         description = self._html_search_meta('description', webpage)
 715
 716         def _get_page(idx):
 717             page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
 718                 user_id, idx + 1)
 719             webpage = self._download_webpage(
 720                 page_url, user_id,
 721                 note='Downloading page %d/%d' % (idx + 1, page_count))
 722             video_list = self._search_regex(
 723                 r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
 724                 webpage, 'video content')
 725             paths = re.findall(
 726                 r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
 727             for path in paths:
 728                 yield {
 729                     '_type': 'url',
 730                     'url': compat_urlparse.urljoin(page_url, path),
 731                 }
 732
 733         pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
 734
 735         return {
 736             '_type': 'playlist',
 737             'id': 'user%s_likes' % user_id,
 738             'title': title,
 739             'description': description,
 740             'entries': pl,
 741         }