yt_dlp/extractor/theintercept.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     ExtractorError,
   4     int_or_none,
   5     parse_iso8601,
   6 )
   7
   8
   9 class TheInterceptIE(InfoExtractor):
  10     _VALID_URL = r'https?://theintercept\.com/fieldofvision/(?P<id>[^/?#]+)'
  11     _TESTS = [{
  12         'url': 'https://theintercept.com/fieldofvision/thisisacoup-episode-four-surrender-or-die/',
  13         'md5': '145f28b41d44aab2f87c0a4ac8ec95bd',
  14         'info_dict': {
  15             'id': '46214',
  16             'ext': 'mp4',
  17             'title': '#ThisIsACoup – Episode Four: Surrender or Die',
  18             'description': 'md5:74dd27f0e2fbd50817829f97eaa33140',
  19             'timestamp': 1450429239,
  20             'upload_date': '20151218',
  21             'comment_count': int,
  22         },
  23     }]
  24
  25     def _real_extract(self, url):
  26         display_id = self._match_id(url)
  27         webpage = self._download_webpage(url, display_id)
  28
  29         json_data = self._parse_json(self._search_regex(
  30             r'initialStoreTree\s*=\s*(?P<json_data>{.+})', webpage,
  31             'initialStoreTree'), display_id)
  32
  33         for post in json_data['resources']['posts'].values():
  34             if post['slug'] == display_id:
  35                 return {
  36                     '_type': 'url_transparent',
  37                     'url': 'jwplatform:{}'.format(post['fov_videoid']),
  38                     'id': str(post['ID']),
  39                     'display_id': display_id,
  40                     'title': post['title'],
  41                     'description': post.get('excerpt'),
  42                     'timestamp': parse_iso8601(post.get('date')),
  43                     'comment_count': int_or_none(post.get('comments_number')),
  44                 }
  45         raise ExtractorError('Unable to find the current post')