from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
'id': '1025403',
'ext': 'mp4',
'title': 'India to launch indigenous aircraft carrier INS Vikrant today',
+ 'description': 'md5:feef3041cb09724e0bdc02843348f5f4',
}
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
+ page = self._download_webpage(url, video_id)
+
+ title = self._html_search_meta('twitter:title', page, 'title', fatal=True)
+ description = self._html_search_meta('twitter:description', page, 'title')
data = self._download_xml(
'http://www.firstpost.com/getvideoxml-%s.xml' % video_id, video_id,
item = data.find('./playlist/item')
thumbnail = item.find('./image').text
- title = item.find('./title').text
formats = [
{
'height': int(details.find('./height').text.strip()),
} for details in item.findall('./source/file_details') if details.find('./file').text
]
+ self._sort_formats(formats)
return {
'id': video_id,
'title': title,
+ 'description': description,
'thumbnail': thumbnail,
'formats': formats,
}