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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from .jwplatform import JWPlatformIE
   6 from ..utils import unified_strdate
   7
   8
   9 class TeamFourStarIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?teamfourstar\.com/(?P<id>[a-z0-9\-]+)'
  11     _TEST = {
  12         'url': 'http://teamfourstar.com/tfs-abridged-parody-episode-1-2/',
  13         'info_dict': {
  14             'id': '0WdZO31W',
  15             'title': 'TFS Abridged Parody Episode 1',
  16             'description': 'md5:d60bc389588ebab2ee7ad432bda953ae',
  17             'ext': 'mp4',
  18             'timestamp': 1394168400,
  19             'upload_date': '20080508',
  20         },
  21     }
  22
  23     def _real_extract(self, url):
  24         display_id = self._match_id(url)
  25         webpage = self._download_webpage(url, display_id)
  26
  27         jwplatform_url = JWPlatformIE._extract_url(webpage)
  28
  29         video_title = self._html_search_regex(
  30             r'<h1[^>]+class="entry-title"[^>]*>(?P<title>.+?)</h1>',
  31             webpage, 'title')
  32         video_date = unified_strdate(self._html_search_regex(
  33             r'<span[^>]+class="meta-date date updated"[^>]*>(?P<date>.+?)</span>',
  34             webpage, 'date', fatal=False))
  35         video_description = self._html_search_regex(
  36             r'(?s)<div[^>]+class="content-inner"[^>]*>.*?(?P<description><p>.+?)</div>',
  37             webpage, 'description', fatal=False)
  38         video_thumbnail = self._og_search_thumbnail(webpage)
  39
  40         return {
  41             '_type': 'url_transparent',
  42             'display_id': display_id,
  43             'title': video_title,
  44             'description': video_description,
  45             'upload_date': video_date,
  46             'thumbnail': video_thumbnail,
  47             'url': jwplatform_url,
  48         }