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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_str
   6 from ..utils import (
   7     parse_iso8601,
   8     int_or_none,
   9     ExtractorError,
  10 )
  11
  12
  13 class TheInterceptIE(InfoExtractor):
  14     _VALID_URL = r'https?://theintercept\.com/fieldofvision/(?P<id>[^/?#]+)'
  15     _TESTS = [{
  16         'url': 'https://theintercept.com/fieldofvision/thisisacoup-episode-four-surrender-or-die/',
  17         'md5': '145f28b41d44aab2f87c0a4ac8ec95bd',
  18         'info_dict': {
  19             'id': '46214',
  20             'ext': 'mp4',
  21             'title': '#ThisIsACoup – Episode Four: Surrender or Die',
  22             'description': 'md5:74dd27f0e2fbd50817829f97eaa33140',
  23             'timestamp': 1450429239,
  24             'upload_date': '20151218',
  25             'comment_count': int,
  26         }
  27     }]
  28
  29     def _real_extract(self, url):
  30         display_id = self._match_id(url)
  31         webpage = self._download_webpage(url, display_id)
  32
  33         json_data = self._parse_json(self._search_regex(
  34             r'initialStoreTree\s*=\s*(?P<json_data>{.+})', webpage,
  35             'initialStoreTree'), display_id)
  36
  37         for post in json_data['resources']['posts'].values():
  38             if post['slug'] == display_id:
  39                 return {
  40                     '_type': 'url_transparent',
  41                     'url': 'jwplatform:%s' % post['fov_videoid'],
  42                     'id': compat_str(post['ID']),
  43                     'display_id': display_id,
  44                     'title': post['title'],
  45                     'description': post.get('excerpt'),
  46                     'timestamp': parse_iso8601(post.get('date')),
  47                     'comment_count': int_or_none(post.get('comments_number')),
  48                 }
  49         raise ExtractorError('Unable to find the current post')