yt_dlp/extractor/fox9.py

   1 from .common import InfoExtractor
   2
   3
   4 class FOX9IE(InfoExtractor):
   5     _VALID_URL = r'https?://(?:www\.)?fox9\.com/video/(?P<id>\d+)'
   6
   7     def _real_extract(self, url):
   8         video_id = self._match_id(url)
   9         return self.url_result(
  10             'anvato:anvato_epfox_app_web_prod_b3373168e12f423f41504f207000188daf88251b:' + video_id,
  11             'Anvato', video_id)
  12
  13
  14 class FOX9NewsIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?fox9\.com/news/(?P<id>[^/?&#]+)'
  16     _TEST = {
  17         'url': 'https://www.fox9.com/news/black-bear-in-tree-draws-crowd-in-downtown-duluth-minnesota',
  18         'md5': 'd6e1b2572c3bab8a849c9103615dd243',
  19         'info_dict': {
  20             'id': '314473',
  21             'ext': 'mp4',
  22             'title': 'Bear climbs tree in downtown Duluth',
  23             'description': 'md5:6a36bfb5073a411758a752455408ac90',
  24             'duration': 51,
  25             'timestamp': 1478123580,
  26             'upload_date': '20161102',
  27             'uploader': 'EPFOX',
  28             'categories': ['News', 'Sports'],
  29             'tags': ['news', 'video'],
  30         },
  31     }
  32
  33     def _real_extract(self, url):
  34         display_id = self._match_id(url)
  35         webpage = self._download_webpage(url, display_id)
  36         anvato_id = self._search_regex(
  37             r'anvatoId\s*:\s*[\'"](\d+)', webpage, 'anvato id')
  38         return self.url_result('https://www.fox9.com/video/' + anvato_id, 'FOX9')