_ 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     _VALID_URL = r'http://(?:www\.)?firstpost\.com/[^/]+/.*-(?P<id>[0-9]+)\.html'
  10
  11     _TEST = {
  12         'url': 'http://www.firstpost.com/india/india-to-launch-indigenous-aircraft-carrier-monday-1025403.html',
  13         'md5': 'ee9114957692f01fb1263ed87039112a',
  14         'info_dict': {
  15             'id': '1025403',
  16             'ext': 'mp4',
  17             'title': 'India to launch indigenous aircraft carrier INS Vikrant today',
  18         }
  19     }
  20
  21     def _real_extract(self, url):
  22         mobj = re.match(self._VALID_URL, url)
  23         video_id = mobj.group('id')
  24
  25         data = self._download_xml(
  26             'http://www.firstpost.com/getvideoxml-%s.xml' % video_id, video_id,
  27             'Downloading video XML')
  28
  29         item = data.find('./playlist/item')
  30         thumbnail = item.find('./image').text
  31         title = item.find('./title').text
  32
  33         formats = [
  34             {
  35                 'url': details.find('./file').text,
  36                 'format_id': details.find('./label').text.strip(),
  37                 'width': int(details.find('./width').text.strip()),
  38                 'height': int(details.find('./height').text.strip()),
  39             } for details in item.findall('./source/file_details') if details.find('./file').text
  40         ]
  41
  42         return {
  43             'id': video_id,
  44             'title': title,
  45             'thumbnail': thumbnail,
  46             'formats': formats,
  47         }