Raphaël G. Git Repositories - youtubedl/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/(.*)'
  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     }
  24
  25     def _real_extract(self, url):
  26         mobj = re.match(self._VALID_URL, url)
  27         prog_name = mobj.group(1)
  28         webpage = self._download_webpage(url, prog_name)
  29         video_id = self._search_regex(r'programid=(.*?)&', webpage, 'video id')
  30
  31         title = self._html_search_regex(
  32             r'<!-- title -->\n\s*<h1[^>]*>(.*?)</h1>', webpage, 'title')
  33         description = self._og_search_description(webpage)
  34
  35         info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
  36         data_json = self._download_webpage(
  37             info_url, video_id, 'Downloading video info')
  38         data = json.loads(data_json)
  39
  40         url = unescapeHTML(data['video']['files'][0]['path']['#text'])
  41
  42         return {
  43             'id': video_id,
  44             'title': title,
  45             'url': url,
  46             'description': description,
  47             'thumbnail': self._og_search_thumbnail(webpage),
  48         }