youtube_dl/extractor/ministrygrid.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     smuggle_url,
   7 )
   8
   9
  10 class MinistryGridIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?ministrygrid\.com/([^/?#]*/)*(?P<id>[^/#?]+)/?(?:$|[?#])'
  12
  13     _TEST = {
  14         'url': 'http://www.ministrygrid.com/training-viewer/-/training/t4g-2014-conference/the-gospel-by-numbers-4/the-gospel-by-numbers',
  15         'md5': '844be0d2a1340422759c2a9101bab017',
  16         'info_dict': {
  17             'id': '3453494717001',
  18             'ext': 'mp4',
  19             'title': 'The Gospel by Numbers',
  20             'thumbnail': r're:^https?://.*\.jpg',
  21             'upload_date': '20140410',
  22             'description': 'Coming soon from T4G 2014!',
  23             'uploader_id': '2034960640001',
  24             'timestamp': 1397145591,
  25         },
  26         'params': {
  27             # m3u8 download
  28             'skip_download': True,
  29         },
  30         'add_ie': ['TDSLifeway'],
  31     }
  32
  33     def _real_extract(self, url):
  34         video_id = self._match_id(url)
  35
  36         webpage = self._download_webpage(url, video_id)
  37         portlets = self._parse_json(self._search_regex(
  38             r'Liferay\.Portlet\.list=(\[.+?\])', webpage, 'portlet list'),
  39             video_id)
  40         pl_id = self._search_regex(
  41             r'getPlid:function\(\){return"(\d+)"}', webpage, 'p_l_id')
  42
  43         for i, portlet in enumerate(portlets):
  44             portlet_url = 'http://www.ministrygrid.com/c/portal/render_portlet?p_l_id=%s&p_p_id=%s' % (pl_id, portlet)
  45             portlet_code = self._download_webpage(
  46                 portlet_url, video_id,
  47                 note='Looking in portlet %s (%d/%d)' % (portlet, i + 1, len(portlets)),
  48                 fatal=False)
  49             video_iframe_url = self._search_regex(
  50                 r'<iframe.*?src="([^"]+)"', portlet_code, 'video iframe',
  51                 default=None)
  52             if video_iframe_url:
  53                 return self.url_result(
  54                     smuggle_url(video_iframe_url, {'force_videoid': video_id}),
  55                     video_id=video_id)
  56
  57         raise ExtractorError('Could not find video iframe in any portlets')