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

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