]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/firstpost.py
Merge tag 'upstream/2014.12.01'
[youtubedl] / youtube_dl / extractor / firstpost.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6
7
8 class FirstpostIE(InfoExtractor):
9 _VALID_URL = r'http://(?:www\.)?firstpost\.com/[^/]+/.*-(?P<id>[0-9]+)\.html'
10
11 _TEST = {
12 'url': 'http://www.firstpost.com/india/india-to-launch-indigenous-aircraft-carrier-monday-1025403.html',
13 'md5': 'ee9114957692f01fb1263ed87039112a',
14 'info_dict': {
15 'id': '1025403',
16 'ext': 'mp4',
17 'title': 'India to launch indigenous aircraft carrier INS Vikrant today',
18 'description': 'md5:feef3041cb09724e0bdc02843348f5f4',
19 }
20 }
21
22 def _real_extract(self, url):
23 mobj = re.match(self._VALID_URL, url)
24 video_id = mobj.group('id')
25
26 page = self._download_webpage(url, video_id)
27 title = self._html_search_meta('twitter:title', page, 'title')
28 description = self._html_search_meta('twitter:description', page, 'title')
29
30 data = self._download_xml(
31 'http://www.firstpost.com/getvideoxml-%s.xml' % video_id, video_id,
32 'Downloading video XML')
33
34 item = data.find('./playlist/item')
35 thumbnail = item.find('./image').text
36
37 formats = [
38 {
39 'url': details.find('./file').text,
40 'format_id': details.find('./label').text.strip(),
41 'width': int(details.find('./width').text.strip()),
42 'height': int(details.find('./height').text.strip()),
43 } for details in item.findall('./source/file_details') if details.find('./file').text
44 ]
45
46 return {
47 'id': video_id,
48 'title': title,
49 'description': description,
50 'thumbnail': thumbnail,
51 'formats': formats,
52 }