yt_dlp/extractor/ministrygrid.py

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