Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/fox9.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .anvato import AnvatoIE
   5
   6
   7 class FOX9IE(AnvatoIE):
   8     _VALID_URL = r'https?://(?:www\.)?fox9\.com/(?:[^/]+/)+(?P<id>\d+)-story'
   9     _TESTS = [{
  10         'url': 'http://www.fox9.com/news/215123287-story',
  11         'md5': 'd6e1b2572c3bab8a849c9103615dd243',
  12         'info_dict': {
  13             'id': '314473',
  14             'ext': 'mp4',
  15             'title': 'Bear climbs tree in downtown Duluth',
  16             'description': 'md5:6a36bfb5073a411758a752455408ac90',
  17             'duration': 51,
  18             'timestamp': 1478123580,
  19             'upload_date': '20161102',
  20             'uploader': 'EPFOX',
  21             'categories': ['News', 'Sports'],
  22             'tags': ['news', 'video'],
  23         },
  24     }, {
  25         'url': 'http://www.fox9.com/news/investigators/214070684-story',
  26         'only_matching': True,
  27     }]
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31
  32         webpage = self._download_webpage(url, video_id)
  33
  34         video_id = self._parse_json(
  35             self._search_regex(
  36                 r"this\.videosJson\s*=\s*'(\[.+?\])';",
  37                 webpage, 'anvato playlist'),
  38             video_id)[0]['video']
  39
  40         return self._get_anvato_videos(
  41             'anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b',
  42             video_id)