git.bitcoin.ninja Git - youtube-dl/blob - youtube_dl/extractor/cspan.py

   1 from __future__ import unicode_literals
   2
   3 import json
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     unescapeHTML,
   9 )
  10
  11
  12 class CSpanIE(InfoExtractor):
  13     _VALID_URL = r'http://(?:www\.)?c-spanvideo\.org/program/(?P<name>.*)'
  14     IE_DESC = 'C-SPAN'
  15     _TEST = {
  16         'url': 'http://www.c-spanvideo.org/program/HolderonV',
  17         'file': '315139.mp4',
  18         'md5': '8e44ce11f0f725527daccc453f553eb0',
  19         'info_dict': {
  20             'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
  21             'description': 'Attorney General Eric Holder spoke to reporters following the Supreme Court decision in [Shelby County v. Holder] in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced until Congress established new guidelines for review.',
  22         },
  23         'skip': 'Regularly fails on travis, for unknown reasons',
  24     }
  25
  26     def _real_extract(self, url):
  27         mobj = re.match(self._VALID_URL, url)
  28         prog_name = mobj.group('name')
  29         webpage = self._download_webpage(url, prog_name)
  30         video_id = self._search_regex(r'prog(?:ram)?id=(.*?)&', webpage, 'video id')
  31
  32         title = self._html_search_regex(
  33             r'<!-- title -->\n\s*<h1[^>]*>(.*?)</h1>', webpage, 'title')
  34         description = self._og_search_description(webpage)
  35
  36         info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
  37         data_json = self._download_webpage(
  38             info_url, video_id, 'Downloading video info')
  39         data = json.loads(data_json)
  40
  41         url = unescapeHTML(data['video']['files'][0]['path']['#text'])
  42
  43         return {
  44             'id': video_id,
  45             'title': title,
  46             'url': url,
  47             'description': description,
  48             'thumbnail': self._og_search_thumbnail(webpage),
  49         }