1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
|
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote_plus
from ..utils import int_or_none
class KUSIIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?kusi\.com/(?P<path>story/.+|video\?clipId=(?P<clipId>\d+))'
_TESTS = [{
'url': 'http://www.kusi.com/story/31183873/turko-files-case-closed-put-on-hold',
'md5': 'f926e7684294cf8cb7bdf8858e1b3988',
'info_dict': {
'id': '12203019',
'ext': 'mp4',
'title': 'Turko Files: Case Closed! & Put On Hold!',
'duration': 231000,
},
}, {
'url': 'http://kusi.com/video?clipId=12203019',
'info_dict': {
'id': '12203019',
'ext': 'mp4',
'title': 'Turko Files: Case Closed! & Put On Hold!',
'duration': 231000,
},
'params': {
'skip_download': True, # Same as previous one
},
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj.group('clipId') is not None:
video_id = mobj.group('clipId')
else:
webpage = self._download_webpage(url, mobj.group('path'))
video_id = self._html_search_regex(r'"clipId", "(\d+)"', webpage,
'clipId')
xml_url = 'http://www.kusi.com/build.asp?buildtype=buildfeaturexml'\
'request&featureType=Clip&featureid={0}&affiliateno=956&'\
'clientgroupid=1&rnd=562461'.format(video_id)
doc = self._download_xml(xml_url, video_id,
note='Downloading video info',
errnote='Failed to download video info')
video_title = doc.find('HEADLINE').text
duration = int_or_none(doc.find('DURATION'), get_attr='text')
description = doc.find('ABSTRACT')
quality_options = doc.find('{http://search.yahoo.com/mrss/}group').findall('{http://search.yahoo.com/mrss/}content')
formats = []
for quality in quality_options:
if 'height' in quality.attrib:
formats.append({
'url': compat_urllib_parse_unquote_plus(quality.attrib['url']),
'height': quality.attrib['height'],
})
self._sort_formats(formats)
return {
'id': video_id,
'title': video_title,
'description': description,
'duration': duration,
'formats': formats,
}
|
