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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class FirstpostIE(InfoExtractor):
   9     IE_NAME = 'Firstpost.com'
  10     _VALID_URL = r'http://(?:www\.)?firstpost\.com/[^/]+/.*-(?P<id>[0-9]+)\.html'
  11
  12     _TEST = {
  13         'url': 'http://www.firstpost.com/india/india-to-launch-indigenous-aircraft-carrier-monday-1025403.html',
  14         'md5': 'ee9114957692f01fb1263ed87039112a',
  15         'info_dict': {
  16             'id': '1025403',
  17             'ext': 'mp4',
  18             'title': 'India to launch indigenous aircraft carrier INS Vikrant today',
  19             'description': 'Its flight deck is over twice the size of a football field, its power unit can light up the entire Kochi city and the cabling is enough to cover the distance between here to Delhi.',
  20         }
  21     }
  22
  23     def _real_extract(self, url):
  24         mobj = re.match(self._VALID_URL, url)
  25         video_id = mobj.group('id')
  26
  27         webpage = self._download_webpage(url, video_id)
  28         video_url = self._html_search_regex(
  29             r'<div.*?name="div_video".*?flashvars="([^"]+)">',
  30             webpage, 'video URL')
  31
  32         return {
  33             'id': video_id,
  34             'url': video_url,
  35             'title': self._og_search_title(webpage),
  36             'description': self._og_search_description(webpage),
  37             'thumbnail': self._og_search_thumbnail(webpage),
  38         }