youtube_dl/extractor/morningstar.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class MorningstarIE(InfoExtractor):
  10     IE_DESC = 'morningstar.com'
  11     _VALID_URL = r'https?://(?:www\.)?morningstar\.com/[cC]over/video[cC]enter\.aspx\?id=(?P<id>[0-9]+)'
  12     _TEST = {
  13         'url': 'http://www.morningstar.com/cover/videocenter.aspx?id=615869',
  14         'md5': '6c0acface7a787aadc8391e4bbf7b0f5',
  15         'info_dict': {
  16             'id': '615869',
  17             'ext': 'mp4',
  18             'title': 'Get Ahead of the Curve on 2013 Taxes',
  19             'description': "Vanguard's Joel Dickson on managing higher tax rates for high-income earners and fund capital-gain distributions in 2013.",
  20             'thumbnail': r're:^https?://.*m(?:orning)?star\.com/.+thumb\.jpg$'
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         mobj = re.match(self._VALID_URL, url)
  26         video_id = mobj.group('id')
  27
  28         webpage = self._download_webpage(url, video_id)
  29         title = self._html_search_regex(
  30             r'<h1 id="titleLink">(.*?)</h1>', webpage, 'title')
  31         video_url = self._html_search_regex(
  32             r'<input type="hidden" id="hidVideoUrl" value="([^"]+)"',
  33             webpage, 'video URL')
  34         thumbnail = self._html_search_regex(
  35             r'<input type="hidden" id="hidSnapshot" value="([^"]+)"',
  36             webpage, 'thumbnail', fatal=False)
  37         description = self._html_search_regex(
  38             r'<div id="mstarDeck".*?>(.*?)</div>',
  39             webpage, 'description', fatal=False)
  40
  41         return {
  42             'id': video_id,
  43             'title': title,
  44             'url': video_url,
  45             'thumbnail': thumbnail,
  46             'description': description,
  47         }