git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/vimeo.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import re
   6 import itertools
   7
   8 from .common import InfoExtractor
   9 from ..compat import (
  10     compat_HTTPError,
  11     compat_urllib_parse,
  12     compat_urllib_request,
  13     compat_urlparse,
  14 )
  15 from ..utils import (
  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({
  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 who love them.',
 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
 186     @staticmethod
 187     def _extract_vimeo_url(url, webpage):
 188         # Look for embedded (iframe) Vimeo player
 189         mobj = re.search(
 190             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/.+?)\1', webpage)
 191         if mobj:
 192             player_url = unescapeHTML(mobj.group('url'))
 193             surl = smuggle_url(player_url, {'Referer': url})
 194             return surl
 195         # Look for embedded (swf embed) Vimeo player
 196         mobj = re.search(
 197             r'<embed[^>]+?src="((?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)"', webpage)
 198         if mobj:
 199             return mobj.group(1)
 200
 201     def _verify_video_password(self, url, video_id, webpage):
 202         password = self._downloader.params.get('videopassword', None)
 203         if password is None:
 204             raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
 205         token, vuid = self._extract_xsrft_and_vuid(webpage)
 206         data = urlencode_postdata({
 207             'password': password,
 208             'token': token,
 209         })
 210         if url.startswith('http://'):
 211             # vimeo only supports https now, but the user can give an http url
 212             url = url.replace('http://', 'https://')
 213         password_request = compat_urllib_request.Request(url + '/password', data)
 214         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 215         password_request.add_header('Cookie', 'clip_test2=1; vuid=%s' % vuid)
 216         password_request.add_header('Referer', url)
 217         return self._download_webpage(
 218             password_request, video_id,
 219             'Verifying the password', 'Wrong password')
 220
 221     def _verify_player_video_password(self, url, video_id):
 222         password = self._downloader.params.get('videopassword', None)
 223         if password is None:
 224             raise ExtractorError('This video is protected by a password, use the --video-password option')
 225         data = compat_urllib_parse.urlencode({'password': password})
 226         pass_url = url + '/check-password'
 227         password_request = compat_urllib_request.Request(pass_url, data)
 228         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
 229         return self._download_json(
 230             password_request, video_id,
 231             'Verifying the password',
 232             'Wrong password')
 233
 234     def _real_initialize(self):
 235         self._login()
 236
 237     def _real_extract(self, url):
 238         url, data = unsmuggle_url(url)
 239         headers = std_headers
 240         if data is not None:
 241             headers = headers.copy()
 242             headers.update(data)
 243         if 'Referer' not in headers:
 244             headers['Referer'] = url
 245
 246         # Extract ID from URL
 247         mobj = re.match(self._VALID_URL, url)
 248         video_id = mobj.group('id')
 249         orig_url = url
 250         if mobj.group('pro') or mobj.group('player'):
 251             url = 'https://player.vimeo.com/video/' + video_id
 252         else:
 253             url = 'https://vimeo.com/' + video_id
 254
 255         # Retrieve video webpage to extract further information
 256         request = compat_urllib_request.Request(url, None, headers)
 257         try:
 258             webpage = self._download_webpage(request, video_id)
 259         except ExtractorError as ee:
 260             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
 261                 errmsg = ee.cause.read()
 262                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 263                     raise ExtractorError(
 264                         'Cannot download embed-only video without embedding '
 265                         'URL. Please call youtube-dl with the URL of the page '
 266                         'that embeds this video.',
 267                         expected=True)
 268             raise
 269
 270         # Now we begin extracting as much information as we can from what we
 271         # retrieved. First we extract the information common to all extractors,
 272         # and latter we extract those that are Vimeo specific.
 273         self.report_extraction(video_id)
 274
 275         vimeo_config = self._search_regex(
 276             r'vimeo\.config\s*=\s*({.+?});', webpage,
 277             'vimeo config', default=None)
 278         if vimeo_config:
 279             seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
 280             if seed_status.get('state') == 'failed':
 281                 raise ExtractorError(
 282                     '%s returned error: %s' % (self.IE_NAME, seed_status['title']),
 283                     expected=True)
 284
 285         # Extract the config JSON
 286         try:
 287             try:
 288                 config_url = self._html_search_regex(
 289                     r' data-config-url="(.+?)"', webpage,
 290                     'config URL', default=None)
 291                 if not config_url:
 292                     # Sometimes new react-based page is served instead of old one that require
 293                     # different config URL extraction approach (see
 294                     # https://github.com/rg3/youtube-dl/pull/7209)
 295                     vimeo_clip_page_config = self._search_regex(
 296                         r'vimeo\.clip_page_config\s*=\s*({.+?});', webpage,
 297                         'vimeo clip page config')
 298                     config_url = self._parse_json(
 299                         vimeo_clip_page_config, video_id)['player']['config_url']
 300                 config_json = self._download_webpage(config_url, video_id)
 301                 config = json.loads(config_json)
 302             except RegexNotFoundError:
 303                 # For pro videos or player.vimeo.com urls
 304                 # We try to find out to which variable is assigned the config dic
 305                 m_variable_name = re.search('(\w)\.video\.id', webpage)
 306                 if m_variable_name is not None:
 307                     config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))
 308                 else:
 309                     config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
 310                 config = self._search_regex(config_re, webpage, 'info section',
 311                                             flags=re.DOTALL)
 312                 config = json.loads(config)
 313         except Exception as e:
 314             if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
 315                 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
 316
 317             if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
 318                 if data and '_video_password_verified' in data:
 319                     raise ExtractorError('video password verification failed!')
 320                 self._verify_video_password(url, video_id, webpage)
 321                 return self._real_extract(
 322                     smuggle_url(url, {'_video_password_verified': 'verified'}))
 323             else:
 324                 raise ExtractorError('Unable to extract info section',
 325                                      cause=e)
 326         else:
 327             if config.get('view') == 4:
 328                 config = self._verify_player_video_password(url, video_id)
 329
 330         # Extract title
 331         video_title = config["video"]["title"]
 332
 333         # Extract uploader and uploader_id
 334         video_uploader = config["video"]["owner"]["name"]
 335         video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None
 336
 337         # Extract video thumbnail
 338         video_thumbnail = config["video"].get("thumbnail")
 339         if video_thumbnail is None:
 340             video_thumbs = config["video"].get("thumbs")
 341             if video_thumbs and isinstance(video_thumbs, dict):
 342                 _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
 343
 344         # Extract video description
 345
 346         video_description = self._html_search_regex(
 347             r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 348             webpage, 'description', default=None)
 349         if not video_description:
 350             video_description = self._html_search_meta(
 351                 'description', webpage, default=None)
 352         if not video_description and mobj.group('pro'):
 353             orig_webpage = self._download_webpage(
 354                 orig_url, video_id,
 355                 note='Downloading webpage for description',
 356                 fatal=False)
 357             if orig_webpage:
 358                 video_description = self._html_search_meta(
 359                     'description', orig_webpage, default=None)
 360         if not video_description and not mobj.group('player'):
 361             self._downloader.report_warning('Cannot find video description')
 362
 363         # Extract video duration
 364         video_duration = int_or_none(config["video"].get("duration"))
 365
 366         # Extract upload date
 367         video_upload_date = None
 368         mobj = re.search(r'<time[^>]+datetime="([^"]+)"', webpage)
 369         if mobj is not None:
 370             video_upload_date = unified_strdate(mobj.group(1))
 371
 372         try:
 373             view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
 374             like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
 375             comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
 376         except RegexNotFoundError:
 377             # This info is only available in vimeo.com/{id} urls
 378             view_count = None
 379             like_count = None
 380             comment_count = None
 381
 382         # Vimeo specific: extract request signature and timestamp
 383         sig = config['request']['signature']
 384         timestamp = config['request']['timestamp']
 385
 386         # Vimeo specific: extract video codec and quality information
 387         # First consider quality, then codecs, then take everything
 388         codecs = [('vp6', 'flv'), ('vp8', 'flv'), ('h264', 'mp4')]
 389         files = {'hd': [], 'sd': [], 'other': []}
 390         config_files = config["video"].get("files") or config["request"].get("files")
 391         for codec_name, codec_extension in codecs:
 392             for quality in config_files.get(codec_name, []):
 393                 format_id = '-'.join((codec_name, quality)).lower()
 394                 key = quality if quality in files else 'other'
 395                 video_url = None
 396                 if isinstance(config_files[codec_name], dict):
 397                     file_info = config_files[codec_name][quality]
 398                     video_url = file_info.get('url')
 399                 else:
 400                     file_info = {}
 401                 if video_url is None:
 402                     video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
 403                         % (video_id, sig, timestamp, quality, codec_name.upper())
 404
 405                 files[key].append({
 406                     'ext': codec_extension,
 407                     'url': video_url,
 408                     'format_id': format_id,
 409                     'width': int_or_none(file_info.get('width')),
 410                     'height': int_or_none(file_info.get('height')),
 411                     'tbr': int_or_none(file_info.get('bitrate')),
 412                 })
 413         formats = []
 414         m3u8_url = config_files.get('hls', {}).get('all')
 415         if m3u8_url:
 416             m3u8_formats = self._extract_m3u8_formats(
 417                 m3u8_url, video_id, 'mp4', 'm3u8_native', 0, 'hls', fatal=False)
 418             if m3u8_formats:
 419                 formats.extend(m3u8_formats)
 420         for key in ('other', 'sd', 'hd'):
 421             formats += files[key]
 422         self._sort_formats(formats)
 423
 424         subtitles = {}
 425         text_tracks = config['request'].get('text_tracks')
 426         if text_tracks:
 427             for tt in text_tracks:
 428                 subtitles[tt['lang']] = [{
 429                     'ext': 'vtt',
 430                     'url': 'https://vimeo.com' + tt['url'],
 431                 }]
 432
 433         return {
 434             'id': video_id,
 435             'uploader': video_uploader,
 436             'uploader_id': video_uploader_id,
 437             'upload_date': video_upload_date,
 438             'title': video_title,
 439             'thumbnail': video_thumbnail,
 440             'description': video_description,
 441             'duration': video_duration,
 442             'formats': formats,
 443             'webpage_url': url,
 444             'view_count': view_count,
 445             'like_count': like_count,
 446             'comment_count': comment_count,
 447             'subtitles': subtitles,
 448         }
 449
 450
 451 class VimeoChannelIE(VimeoBaseInfoExtractor):
 452     IE_NAME = 'vimeo:channel'
 453     _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
 454     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
 455     _TITLE = None
 456     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
 457     _TESTS = [{
 458         'url': 'https://vimeo.com/channels/tributes',
 459         'info_dict': {
 460             'id': 'tributes',
 461             'title': 'Vimeo Tributes',
 462         },
 463         'playlist_mincount': 25,
 464     }]
 465
 466     def _page_url(self, base_url, pagenum):
 467         return '%s/videos/page:%d/' % (base_url, pagenum)
 468
 469     def _extract_list_title(self, webpage):
 470         return self._TITLE or self._html_search_regex(self._TITLE_RE, webpage, 'list title')
 471
 472     def _login_list_password(self, page_url, list_id, webpage):
 473         login_form = self._search_regex(
 474             r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
 475             webpage, 'login form', default=None)
 476         if not login_form:
 477             return webpage
 478
 479         password = self._downloader.params.get('videopassword', None)
 480         if password is None:
 481             raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
 482         fields = self._hidden_inputs(login_form)
 483         token, vuid = self._extract_xsrft_and_vuid(webpage)
 484         fields['token'] = token
 485         fields['password'] = password
 486         post = urlencode_postdata(fields)
 487         password_path = self._search_regex(
 488             r'action="([^"]+)"', login_form, 'password URL')
 489         password_url = compat_urlparse.urljoin(page_url, password_path)
 490         password_request = compat_urllib_request.Request(password_url, post)
 491         password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
 492         password_request.add_header('Cookie', 'vuid=%s' % vuid)
 493         self._set_cookie('vimeo.com', 'xsrft', token)
 494
 495         return self._download_webpage(
 496             password_request, list_id,
 497             'Verifying the password', 'Wrong password')
 498
 499     def _extract_videos(self, list_id, base_url):
 500         video_ids = []
 501         for pagenum in itertools.count(1):
 502             page_url = self._page_url(base_url, pagenum)
 503             webpage = self._download_webpage(
 504                 page_url, list_id,
 505                 'Downloading page %s' % pagenum)
 506
 507             if pagenum == 1:
 508                 webpage = self._login_list_password(page_url, list_id, webpage)
 509
 510             video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage))
 511             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
 512                 break
 513
 514         entries = [self.url_result('https://vimeo.com/%s' % video_id, 'Vimeo')
 515                    for video_id in video_ids]
 516         return {'_type': 'playlist',
 517                 'id': list_id,
 518                 'title': self._extract_list_title(webpage),
 519                 'entries': entries,
 520                 }
 521
 522     def _real_extract(self, url):
 523         mobj = re.match(self._VALID_URL, url)
 524         channel_id = mobj.group('id')
 525         return self._extract_videos(channel_id, 'https://vimeo.com/channels/%s' % channel_id)
 526
 527
 528 class VimeoUserIE(VimeoChannelIE):
 529     IE_NAME = 'vimeo:user'
 530     _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
 531     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
 532     _TESTS = [{
 533         'url': 'https://vimeo.com/nkistudio/videos',
 534         'info_dict': {
 535             'title': 'Nki',
 536             'id': 'nkistudio',
 537         },
 538         'playlist_mincount': 66,
 539     }]
 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, 'https://vimeo.com/%s' % name)
 545
 546
 547 class VimeoAlbumIE(VimeoChannelIE):
 548     IE_NAME = 'vimeo:album'
 549     _VALID_URL = r'https://vimeo\.com/album/(?P<id>\d+)'
 550     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
 551     _TESTS = [{
 552         'url': 'https://vimeo.com/album/2632481',
 553         'info_dict': {
 554             'id': '2632481',
 555             'title': 'Staff Favorites: November 2013',
 556         },
 557         'playlist_mincount': 13,
 558     }, {
 559         'note': 'Password-protected album',
 560         'url': 'https://vimeo.com/album/3253534',
 561         'info_dict': {
 562             'title': 'test',
 563             'id': '3253534',
 564         },
 565         'playlist_count': 1,
 566         'params': {
 567             'videopassword': 'youtube-dl',
 568         }
 569     }]
 570
 571     def _page_url(self, base_url, pagenum):
 572         return '%s/page:%d/' % (base_url, pagenum)
 573
 574     def _real_extract(self, url):
 575         album_id = self._match_id(url)
 576         return self._extract_videos(album_id, 'https://vimeo.com/album/%s' % album_id)
 577
 578
 579 class VimeoGroupsIE(VimeoAlbumIE):
 580     IE_NAME = 'vimeo:group'
 581     _VALID_URL = r'https://vimeo\.com/groups/(?P<name>[^/]+)'
 582     _TESTS = [{
 583         'url': 'https://vimeo.com/groups/rolexawards',
 584         'info_dict': {
 585             'id': 'rolexawards',
 586             'title': 'Rolex Awards for Enterprise',
 587         },
 588         'playlist_mincount': 73,
 589     }]
 590
 591     def _extract_list_title(self, webpage):
 592         return self._og_search_title(webpage)
 593
 594     def _real_extract(self, url):
 595         mobj = re.match(self._VALID_URL, url)
 596         name = mobj.group('name')
 597         return self._extract_videos(name, 'https://vimeo.com/groups/%s' % name)
 598
 599
 600 class VimeoReviewIE(InfoExtractor):
 601     IE_NAME = 'vimeo:review'
 602     IE_DESC = 'Review pages on vimeo'
 603     _VALID_URL = r'https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
 604     _TESTS = [{
 605         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
 606         'md5': 'c507a72f780cacc12b2248bb4006d253',
 607         'info_dict': {
 608             'id': '75524534',
 609             'ext': 'mp4',
 610             'title': "DICK HARDWICK 'Comedian'",
 611             'uploader': 'Richard Hardwick',
 612         }
 613     }, {
 614         'note': 'video player needs Referer',
 615         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
 616         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
 617         'info_dict': {
 618             'id': '91613211',
 619             'ext': 'mp4',
 620             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
 621             'uploader': 'DevWeek Events',
 622             'duration': 2773,
 623             'thumbnail': 're:^https?://.*\.jpg$',
 624         }
 625     }]
 626
 627     def _real_extract(self, url):
 628         mobj = re.match(self._VALID_URL, url)
 629         video_id = mobj.group('id')
 630         player_url = 'https://player.vimeo.com/player/' + video_id
 631         return self.url_result(player_url, 'Vimeo', video_id)
 632
 633
 634 class VimeoWatchLaterIE(VimeoChannelIE):
 635     IE_NAME = 'vimeo:watchlater'
 636     IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
 637     _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
 638     _TITLE = 'Watch Later'
 639     _LOGIN_REQUIRED = True
 640     _TESTS = [{
 641         'url': 'https://vimeo.com/watchlater',
 642         'only_matching': True,
 643     }]
 644
 645     def _real_initialize(self):
 646         self._login()
 647
 648     def _page_url(self, base_url, pagenum):
 649         url = '%s/page:%d/' % (base_url, pagenum)
 650         request = compat_urllib_request.Request(url)
 651         # Set the header to get a partial html page with the ids,
 652         # the normal page doesn't contain them.
 653         request.add_header('X-Requested-With', 'XMLHttpRequest')
 654         return request
 655
 656     def _real_extract(self, url):
 657         return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
 658
 659
 660 class VimeoLikesIE(InfoExtractor):
 661     _VALID_URL = r'https://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
 662     IE_NAME = 'vimeo:likes'
 663     IE_DESC = 'Vimeo user likes'
 664     _TEST = {
 665         'url': 'https://vimeo.com/user755559/likes/',
 666         'playlist_mincount': 293,
 667         "info_dict": {
 668             'id': 'user755559_likes',
 669             "description": "See all the videos urza likes",
 670             "title": 'Videos urza likes',
 671         },
 672     }
 673
 674     def _real_extract(self, url):
 675         user_id = self._match_id(url)
 676         webpage = self._download_webpage(url, user_id)
 677         page_count = self._int(
 678             self._search_regex(
 679                 r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
 680                     .*?</a></li>\s*<li\s+class="pagination_next">
 681                 ''', webpage, 'page count'),
 682             'page count', fatal=True)
 683         PAGE_SIZE = 12
 684         title = self._html_search_regex(
 685             r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
 686         description = self._html_search_meta('description', webpage)
 687
 688         def _get_page(idx):
 689             page_url = 'https://vimeo.com/user%s/likes/page:%d/sort:date' % (
 690                 user_id, idx + 1)
 691             webpage = self._download_webpage(
 692                 page_url, user_id,
 693                 note='Downloading page %d/%d' % (idx + 1, page_count))
 694             video_list = self._search_regex(
 695                 r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
 696                 webpage, 'video content')
 697             paths = re.findall(
 698                 r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
 699             for path in paths:
 700                 yield {
 701                     '_type': 'url',
 702                     'url': compat_urlparse.urljoin(page_url, path),
 703                 }
 704
 705         pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
 706
 707         return {
 708             '_type': 'playlist',
 709             'id': 'user%s_likes' % user_id,
 710             'title': title,
 711             'description': description,
 712             'entries': pl,
 713         }