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