mirror of
https://github.com/l1ving/youtube-dl
synced 2024-11-27 19:32:54 +08:00
53 lines
1.7 KiB
Python
53 lines
1.7 KiB
Python
from __future__ import unicode_literals
|
|
|
|
import re
|
|
|
|
from .common import InfoExtractor
|
|
|
|
|
|
class FirstpostIE(InfoExtractor):
|
|
_VALID_URL = r'http://(?:www\.)?firstpost\.com/[^/]+/.*-(?P<id>[0-9]+)\.html'
|
|
|
|
_TEST = {
|
|
'url': 'http://www.firstpost.com/india/india-to-launch-indigenous-aircraft-carrier-monday-1025403.html',
|
|
'md5': 'ee9114957692f01fb1263ed87039112a',
|
|
'info_dict': {
|
|
'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')
|
|
|
|
page = self._download_webpage(url, video_id)
|
|
title = self._html_search_meta('twitter:title', page, 'title')
|
|
description = self._html_search_meta('twitter:description', page, 'title')
|
|
|
|
data = self._download_xml(
|
|
'http://www.firstpost.com/getvideoxml-%s.xml' % video_id, video_id,
|
|
'Downloading video XML')
|
|
|
|
item = data.find('./playlist/item')
|
|
thumbnail = item.find('./image').text
|
|
|
|
formats = [
|
|
{
|
|
'url': details.find('./file').text,
|
|
'format_id': details.find('./label').text.strip(),
|
|
'width': int(details.find('./width').text.strip()),
|
|
'height': int(details.find('./height').text.strip()),
|
|
} for details in item.findall('./source/file_details') if details.find('./file').text
|
|
]
|
|
|
|
return {
|
|
'id': video_id,
|
|
'title': title,
|
|
'description': description,
|
|
'thumbnail': thumbnail,
|
|
'formats': formats,
|
|
}
|