1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
youtube-dl/youtube_dl/extractor/cspan.py

49 lines
1.8 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
import json
2013-06-26 15:55:54 +00:00
import re
from .common import InfoExtractor
from ..utils import (
unescapeHTML,
2013-06-26 15:55:54 +00:00
)
2013-06-26 15:55:54 +00:00
class CSpanIE(InfoExtractor):
_VALID_URL = r'http://www\.c-spanvideo\.org/program/(.*)'
IE_DESC = 'C-SPAN'
2013-06-27 18:46:46 +00:00
_TEST = {
'url': 'http://www.c-spanvideo.org/program/HolderonV',
'file': '315139.mp4',
'md5': '8e44ce11f0f725527daccc453f553eb0',
'info_dict': {
'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
'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.',
2013-06-27 18:46:46 +00:00
},
}
2013-06-26 15:55:54 +00:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
prog_name = mobj.group(1)
webpage = self._download_webpage(url, prog_name)
video_id = self._search_regex(r'programid=(.*?)&', webpage, 'video id')
title = self._html_search_regex(
r'<!-- title -->\n\s*<h1[^>]*>(.*?)</h1>', webpage, 'title')
description = self._og_search_description(webpage)
info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
data_json = self._download_webpage(
info_url, video_id, 'Downloading video info')
data = json.loads(data_json)
url = unescapeHTML(data['video']['files'][0]['path']['#text'])
return {
'id': video_id,
'title': title,
'url': url,
'description': description,
'thumbnail': self._og_search_thumbnail(webpage),
}