Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vimeo.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5 import re
   6 import itertools
   7 import hashlib
   8
   9 from .common import InfoExtractor
  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):
  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', expected=True)
 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         password = self._downloader.params.get('videopassword', None)
 229         if password:
 230             headers['Cookie'] = '%s_password=%s' % (
 231                 video_id, hashlib.md5(password.encode('utf-8')).hexdigest())
 232
 233         # Retrieve video webpage to extract further information
 234         request = compat_urllib_request.Request(url, None, headers)
 235         try:
 236             webpage = self._download_webpage(request, video_id)
 237         except ExtractorError as ee:
 238             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
 239                 errmsg = ee.cause.read()
 240                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 241                     raise ExtractorError(
 242                         'Cannot download embed-only video without embedding '
 243                         'URL. Please call youtube-dl with the URL of the page '
 244                         'that embeds this video.',
 245                         expected=True)
 246             raise
 247
 248         # Now we begin extracting as much information as we can from what we
 249         # retrieved. First we extract the information common to all extractors,
 250         # and latter we extract those that are Vimeo specific.
 251         self.report_extraction(video_id)
 252
 253         # Extract the config JSON
 254         try:
 255             try:
 256                 config_url = self._html_search_regex(
 257                     r' data-config-url="(.+?)"', webpage, 'config URL')
 258                 config_json = self._download_webpage(config_url, video_id)
 259                 config = json.loads(config_json)
 260             except RegexNotFoundError:
 261                 # For pro videos or player.vimeo.com urls
 262                 # We try to find out to which variable is assigned the config dic
 263                 m_variable_name = re.search('(\w)\.video\.id', webpage)
 264                 if m_variable_name is not None:
 265                     config_re = r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))
 266                 else:
 267                     config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
 268                 config = self._search_regex(config_re, webpage, 'info section',
 269                                             flags=re.DOTALL)
 270                 config = json.loads(config)
 271         except Exception as e:
 272             if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
 273                 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
 274
 275             if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
 276                 if data and '_video_password_verified' in data:
 277                     raise ExtractorError('video password verification failed!')
 278                 self._verify_video_password(url, video_id, webpage)
 279                 return self._real_extract(
 280                     smuggle_url(url, {'_video_password_verified': 'verified'}))
 281             else:
 282                 raise ExtractorError('Unable to extract info section',
 283                                      cause=e)
 284         else:
 285             if config.get('view') == 4:
 286                 config = self._verify_player_video_password(url, video_id)
 287
 288         # Extract title
 289         video_title = config["video"]["title"]
 290
 291         # Extract uploader and uploader_id
 292         video_uploader = config["video"]["owner"]["name"]
 293         video_uploader_id = config["video"]["owner"]["url"].split('/')[-1] if config["video"]["owner"]["url"] else None
 294
 295         # Extract video thumbnail
 296         video_thumbnail = config["video"].get("thumbnail")
 297         if video_thumbnail is None:
 298             video_thumbs = config["video"].get("thumbs")
 299             if video_thumbs and isinstance(video_thumbs, dict):
 300                 _, video_thumbnail = sorted((int(width if width.isdigit() else 0), t_url) for (width, t_url) in video_thumbs.items())[-1]
 301
 302         # Extract video description
 303
 304         video_description = self._html_search_regex(
 305             r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 306             webpage, 'description', default=None)
 307         if not video_description:
 308             video_description = self._html_search_meta(
 309                 'description', webpage, default=None)
 310         if not video_description and mobj.group('pro'):
 311             orig_webpage = self._download_webpage(
 312                 orig_url, video_id,
 313                 note='Downloading webpage for description',
 314                 fatal=False)
 315             if orig_webpage:
 316                 video_description = self._html_search_meta(
 317                     'description', orig_webpage, default=None)
 318         if not video_description and not mobj.group('player'):
 319             self._downloader.report_warning('Cannot find video description')
 320
 321         # Extract video duration
 322         video_duration = int_or_none(config["video"].get("duration"))
 323
 324         # Extract upload date
 325         video_upload_date = None
 326         mobj = re.search(r'<meta itemprop="dateCreated" content="(\d{4})-(\d{2})-(\d{2})T', webpage)
 327         if mobj is not None:
 328             video_upload_date = mobj.group(1) + mobj.group(2) + mobj.group(3)
 329
 330         try:
 331             view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
 332             like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
 333             comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
 334         except RegexNotFoundError:
 335             # This info is only available in vimeo.com/{id} urls
 336             view_count = None
 337             like_count = None
 338             comment_count = None
 339
 340         # Vimeo specific: extract request signature and timestamp
 341         sig = config['request']['signature']
 342         timestamp = config['request']['timestamp']
 343
 344         # Vimeo specific: extract video codec and quality information
 345         # First consider quality, then codecs, then take everything
 346         codecs = [('vp6', 'flv'), ('vp8', 'flv'), ('h264', 'mp4')]
 347         files = {'hd': [], 'sd': [], 'other': []}
 348         config_files = config["video"].get("files") or config["request"].get("files")
 349         for codec_name, codec_extension in codecs:
 350             for quality in config_files.get(codec_name, []):
 351                 format_id = '-'.join((codec_name, quality)).lower()
 352                 key = quality if quality in files else 'other'
 353                 video_url = None
 354                 if isinstance(config_files[codec_name], dict):
 355                     file_info = config_files[codec_name][quality]
 356                     video_url = file_info.get('url')
 357                 else:
 358                     file_info = {}
 359                 if video_url is None:
 360                     video_url = "http://player.vimeo.com/play_redirect?clip_id=%s&sig=%s&time=%s&quality=%s&codecs=%s&type=moogaloop_local&embed_location=" \
 361                         % (video_id, sig, timestamp, quality, codec_name.upper())
 362
 363                 files[key].append({
 364                     'ext': codec_extension,
 365                     'url': video_url,
 366                     'format_id': format_id,
 367                     'width': file_info.get('width'),
 368                     'height': file_info.get('height'),
 369                 })
 370         formats = []
 371         for key in ('other', 'sd', 'hd'):
 372             formats += files[key]
 373         if len(formats) == 0:
 374             raise ExtractorError('No known codec found')
 375
 376         subtitles = {}
 377         text_tracks = config['request'].get('text_tracks')
 378         if text_tracks:
 379             for tt in text_tracks:
 380                 subtitles[tt['lang']] = [{
 381                     'ext': 'vtt',
 382                     'url': 'http://vimeo.com' + tt['url'],
 383                 }]
 384
 385         return {
 386             'id': video_id,
 387             'uploader': video_uploader,
 388             'uploader_id': video_uploader_id,
 389             'upload_date': video_upload_date,
 390             'title': video_title,
 391             'thumbnail': video_thumbnail,
 392             'description': video_description,
 393             'duration': video_duration,
 394             'formats': formats,
 395             'webpage_url': url,
 396             'view_count': view_count,
 397             'like_count': like_count,
 398             'comment_count': comment_count,
 399             'subtitles': subtitles,
 400         }
 401
 402
 403 class VimeoChannelIE(InfoExtractor):
 404     IE_NAME = 'vimeo:channel'
 405     _VALID_URL = r'https?://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
 406     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
 407     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
 408     _TESTS = [{
 409         'url': 'http://vimeo.com/channels/tributes',
 410         'info_dict': {
 411             'id': 'tributes',
 412             'title': 'Vimeo Tributes',
 413         },
 414         'playlist_mincount': 25,
 415     }]
 416
 417     def _page_url(self, base_url, pagenum):
 418         return '%s/videos/page:%d/' % (base_url, pagenum)
 419
 420     def _extract_list_title(self, webpage):
 421         return self._html_search_regex(self._TITLE_RE, webpage, 'list title')
 422
 423     def _login_list_password(self, page_url, list_id, webpage):
 424         login_form = self._search_regex(
 425             r'(?s)<form[^>]+?id="pw_form"(.*?)</form>',
 426             webpage, 'login form', default=None)
 427         if not login_form:
 428             return webpage
 429
 430         password = self._downloader.params.get('videopassword', None)
 431         if password is None:
 432             raise ExtractorError('This album is protected by a password, use the --video-password option', expected=True)
 433         fields = dict(re.findall(r'''(?x)<input\s+
 434             type="hidden"\s+
 435             name="([^"]+)"\s+
 436             value="([^"]*)"
 437             ''', login_form))
 438         token = self._search_regex(r'xsrft: \'(.*?)\'', webpage, 'login token')
 439         fields['token'] = token
 440         fields['password'] = password
 441         post = compat_urllib_parse.urlencode(fields)
 442         password_path = self._search_regex(
 443             r'action="([^"]+)"', login_form, 'password URL')
 444         password_url = compat_urlparse.urljoin(page_url, password_path)
 445         password_request = compat_urllib_request.Request(password_url, post)
 446         password_request.add_header('Content-type', 'application/x-www-form-urlencoded')
 447         self._set_cookie('vimeo.com', 'xsrft', token)
 448
 449         return self._download_webpage(
 450             password_request, list_id,
 451             'Verifying the password', 'Wrong password')
 452
 453     def _extract_videos(self, list_id, base_url):
 454         video_ids = []
 455         for pagenum in itertools.count(1):
 456             page_url = self._page_url(base_url, pagenum)
 457             webpage = self._download_webpage(
 458                 page_url, list_id,
 459                 'Downloading page %s' % pagenum)
 460
 461             if pagenum == 1:
 462                 webpage = self._login_list_password(page_url, list_id, webpage)
 463
 464             video_ids.extend(re.findall(r'id="clip_(\d+?)"', webpage))
 465             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
 466                 break
 467
 468         entries = [self.url_result('http://vimeo.com/%s' % video_id, 'Vimeo')
 469                    for video_id in video_ids]
 470         return {'_type': 'playlist',
 471                 'id': list_id,
 472                 'title': self._extract_list_title(webpage),
 473                 'entries': entries,
 474                 }
 475
 476     def _real_extract(self, url):
 477         mobj = re.match(self._VALID_URL, url)
 478         channel_id = mobj.group('id')
 479         return self._extract_videos(channel_id, 'http://vimeo.com/channels/%s' % channel_id)
 480
 481
 482 class VimeoUserIE(VimeoChannelIE):
 483     IE_NAME = 'vimeo:user'
 484     _VALID_URL = r'https?://vimeo\.com/(?![0-9]+(?:$|[?#/]))(?P<name>[^/]+)(?:/videos|[#?]|$)'
 485     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
 486     _TESTS = [{
 487         'url': 'http://vimeo.com/nkistudio/videos',
 488         'info_dict': {
 489             'title': 'Nki',
 490             'id': 'nkistudio',
 491         },
 492         'playlist_mincount': 66,
 493     }]
 494
 495     def _real_extract(self, url):
 496         mobj = re.match(self._VALID_URL, url)
 497         name = mobj.group('name')
 498         return self._extract_videos(name, 'http://vimeo.com/%s' % name)
 499
 500
 501 class VimeoAlbumIE(VimeoChannelIE):
 502     IE_NAME = 'vimeo:album'
 503     _VALID_URL = r'https?://vimeo\.com/album/(?P<id>\d+)'
 504     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
 505     _TESTS = [{
 506         'url': 'http://vimeo.com/album/2632481',
 507         'info_dict': {
 508             'id': '2632481',
 509             'title': 'Staff Favorites: November 2013',
 510         },
 511         'playlist_mincount': 13,
 512     }, {
 513         'note': 'Password-protected album',
 514         'url': 'https://vimeo.com/album/3253534',
 515         'info_dict': {
 516             'title': 'test',
 517             'id': '3253534',
 518         },
 519         'playlist_count': 1,
 520         'params': {
 521             'videopassword': 'youtube-dl',
 522         }
 523     }]
 524
 525     def _page_url(self, base_url, pagenum):
 526         return '%s/page:%d/' % (base_url, pagenum)
 527
 528     def _real_extract(self, url):
 529         album_id = self._match_id(url)
 530         return self._extract_videos(album_id, 'http://vimeo.com/album/%s' % album_id)
 531
 532
 533 class VimeoGroupsIE(VimeoAlbumIE):
 534     IE_NAME = 'vimeo:group'
 535     _VALID_URL = r'(?:https?://)?vimeo\.com/groups/(?P<name>[^/]+)'
 536     _TESTS = [{
 537         'url': 'http://vimeo.com/groups/rolexawards',
 538         'info_dict': {
 539             'id': 'rolexawards',
 540             'title': 'Rolex Awards for Enterprise',
 541         },
 542         'playlist_mincount': 73,
 543     }]
 544
 545     def _extract_list_title(self, webpage):
 546         return self._og_search_title(webpage)
 547
 548     def _real_extract(self, url):
 549         mobj = re.match(self._VALID_URL, url)
 550         name = mobj.group('name')
 551         return self._extract_videos(name, 'http://vimeo.com/groups/%s' % name)
 552
 553
 554 class VimeoReviewIE(InfoExtractor):
 555     IE_NAME = 'vimeo:review'
 556     IE_DESC = 'Review pages on vimeo'
 557     _VALID_URL = r'https?://vimeo\.com/[^/]+/review/(?P<id>[^/]+)'
 558     _TESTS = [{
 559         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
 560         'md5': 'c507a72f780cacc12b2248bb4006d253',
 561         'info_dict': {
 562             'id': '75524534',
 563             'ext': 'mp4',
 564             'title': "DICK HARDWICK 'Comedian'",
 565             'uploader': 'Richard Hardwick',
 566         }
 567     }, {
 568         'note': 'video player needs Referer',
 569         'url': 'http://vimeo.com/user22258446/review/91613211/13f927e053',
 570         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
 571         'info_dict': {
 572             'id': '91613211',
 573             'ext': 'mp4',
 574             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
 575             'uploader': 'DevWeek Events',
 576             'duration': 2773,
 577             'thumbnail': 're:^https?://.*\.jpg$',
 578         }
 579     }]
 580
 581     def _real_extract(self, url):
 582         mobj = re.match(self._VALID_URL, url)
 583         video_id = mobj.group('id')
 584         player_url = 'https://player.vimeo.com/player/' + video_id
 585         return self.url_result(player_url, 'Vimeo', video_id)
 586
 587
 588 class VimeoWatchLaterIE(VimeoBaseInfoExtractor, VimeoChannelIE):
 589     IE_NAME = 'vimeo:watchlater'
 590     IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
 591     _VALID_URL = r'https?://vimeo\.com/home/watchlater|:vimeowatchlater'
 592     _LOGIN_REQUIRED = True
 593     _TITLE_RE = r'href="/home/watchlater".*?>(.*?)<'
 594     _TESTS = [{
 595         'url': 'http://vimeo.com/home/watchlater',
 596         'only_matching': True,
 597     }]
 598
 599     def _real_initialize(self):
 600         self._login()
 601
 602     def _page_url(self, base_url, pagenum):
 603         url = '%s/page:%d/' % (base_url, pagenum)
 604         request = compat_urllib_request.Request(url)
 605         # Set the header to get a partial html page with the ids,
 606         # the normal page doesn't contain them.
 607         request.add_header('X-Requested-With', 'XMLHttpRequest')
 608         return request
 609
 610     def _real_extract(self, url):
 611         return self._extract_videos('watchlater', 'https://vimeo.com/home/watchlater')
 612
 613
 614 class VimeoLikesIE(InfoExtractor):
 615     _VALID_URL = r'https?://(?:www\.)?vimeo\.com/user(?P<id>[0-9]+)/likes/?(?:$|[?#]|sort:)'
 616     IE_NAME = 'vimeo:likes'
 617     IE_DESC = 'Vimeo user likes'
 618     _TEST = {
 619         'url': 'https://vimeo.com/user755559/likes/',
 620         'playlist_mincount': 293,
 621         "info_dict": {
 622             'id': 'user755559_likes',
 623             "description": "See all the videos urza likes",
 624             "title": 'Videos urza likes',
 625         },
 626     }
 627
 628     def _real_extract(self, url):
 629         user_id = self._match_id(url)
 630         webpage = self._download_webpage(url, user_id)
 631         page_count = self._int(
 632             self._search_regex(
 633                 r'''(?x)<li><a\s+href="[^"]+"\s+data-page="([0-9]+)">
 634                     .*?</a></li>\s*<li\s+class="pagination_next">
 635                 ''', webpage, 'page count'),
 636             'page count', fatal=True)
 637         PAGE_SIZE = 12
 638         title = self._html_search_regex(
 639             r'(?s)<h1>(.+?)</h1>', webpage, 'title', fatal=False)
 640         description = self._html_search_meta('description', webpage)
 641
 642         def _get_page(idx):
 643             page_url = '%s//vimeo.com/user%s/likes/page:%d/sort:date' % (
 644                 self.http_scheme(), user_id, idx + 1)
 645             webpage = self._download_webpage(
 646                 page_url, user_id,
 647                 note='Downloading page %d/%d' % (idx + 1, page_count))
 648             video_list = self._search_regex(
 649                 r'(?s)<ol class="js-browse_list[^"]+"[^>]*>(.*?)</ol>',
 650                 webpage, 'video content')
 651             paths = re.findall(
 652                 r'<li[^>]*>\s*<a\s+href="([^"]+)"', video_list)
 653             for path in paths:
 654                 yield {
 655                     '_type': 'url',
 656                     'url': compat_urlparse.urljoin(page_url, path),
 657                 }
 658
 659         pl = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
 660
 661         return {
 662             '_type': 'playlist',
 663             'id': 'user%s_likes' % user_id,
 664             'title': title,
 665             'description': description,
 666             'entries': pl,
 667         }