1 from __future__ import unicode_literals
6 from .common import InfoExtractor
12 class CSpanIE(InfoExtractor):
13 _VALID_URL = r'http://www\.c-spanvideo\.org/program/(.*)'
16 'url': 'http://www.c-spanvideo.org/program/HolderonV',
18 'md5': '8e44ce11f0f725527daccc453f553eb0',
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.',
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')
31 title = self._html_search_regex(
32 r'<!-- title -->\n\s*<h1[^>]*>(.*?)</h1>', webpage, 'title')
33 description = self._og_search_description(webpage)
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)
40 url = unescapeHTML(data['video']['files'][0]['path']['#text'])
46 'description': description,
47 'thumbnail': self._og_search_thumbnail(webpage),