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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class CloserToTruthIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?closertotruth\.com/(episodes/|(series|interviews)/(?:[^#]+#video-)?(?P<id>\d+))'
   9     _TESTS = [
  10         {
  11             'url': 'http://closertotruth.com/series/solutions-the-mind-body-problem#video-3688',
  12             'md5': '5c548bde260a9247ddfdc07c7458ed29',
  13             'info_dict': {
  14                 'id': '0_zof1ktre',
  15                 'ext': 'mov',
  16                 'title': 'Solutions to the Mind-Body Problem?',
  17                 'upload_date': '20140221',
  18                 'timestamp': 1392956007,
  19                 'uploader_id': 'CTTXML'
  20             }
  21         },
  22         {
  23             'url': 'http://closertotruth.com/interviews/1725',
  24             'md5': 'b00598fd6a38372edb976408f72c5792',
  25             'info_dict': {
  26                 'id': '0_19qv5rn1',
  27                 'ext': 'mov',
  28                 'title': 'AyaFr-002 - Francisco J. Ayala',
  29                 'upload_date': '20140307',
  30                 'timestamp': 1394236431,
  31                 'uploader_id': 'CTTXML'
  32             }
  33         },
  34         {
  35             'url': 'http://closertotruth.com/episodes/how-do-brains-work',
  36             'md5': '4dd96aa0a5c296afa5c0bd24895c2f16',
  37             'info_dict': {
  38                 'id': '0_iuxai6g6',
  39                 'ext': 'mov',
  40                 'title': 'How do Brains Work?',
  41                 'upload_date': '20140221',
  42                 'timestamp': 1392956024,
  43                 'uploader_id': 'CTTXML'
  44             }
  45         },
  46     ]
  47
  48     def _real_extract(self, url):
  49         video_id = self._match_id(url)
  50         webpage = self._download_webpage(url, video_id)
  51
  52         video_title = self._search_regex(r'<title>(.+) \|.+</title>', webpage, 'video title')
  53
  54         entry_id = self._search_regex(r'<a[^>]+id="(?:video-%s|embed-kaltura)"[^>]+data-kaltura="([^"]+)' % video_id, webpage, "video entry_id")
  55
  56         interviewee_name = self._search_regex(r'<div id="(?:node_interview_full_group_white_wrapper|node_interview_series_full_group_ajax_content)"(?:.|\n)*<h3>(.*)</h3>.+', webpage, "video interviewee_name", False)
  57
  58         if interviewee_name:
  59             video_title = video_title + ' - ' + interviewee_name
  60
  61         p_id = self._search_regex(r'<script[^>]+src=["\'].+?partner_id/(\d+)', webpage, "kaltura partner_id")
  62
  63         return {
  64             '_type': 'url_transparent',
  65             'id': entry_id,
  66             'url': 'kaltura:%s:%s' % (p_id, entry_id),
  67             'ie_key': 'Kaltura',
  68             'title': video_title
  69         }