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
|
import json
import re
from .common import InfoExtractor
class CollegeHumorIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/?(?P<shorttitle>.*)$'
_TESTS = [{
u'url': u'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
u'file': u'6902724.mp4',
u'md5': u'dcc0f5c1c8be98dc33889a191f4c26bd',
u'info_dict': {
u'title': u'Comic-Con Cosplay Catastrophe',
u'description': u'Fans get creative this year at San Diego. Too',
},
},
{
u'url': u'http://www.collegehumor.com/video/3505939/font-conference',
u'file': u'3505939.mp4',
u'md5': u'72fa701d8ef38664a4dbb9e2ab721816',
u'info_dict': {
u'title': u'Font Conference',
u'description': u'This video wasn\'t long enough, so we made it double-spaced.',
},
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('videoid')
jsonUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id + '.json'
data = json.loads(self._download_webpage(
jsonUrl, video_id, u'Downloading info JSON'))
vdata = data['video']
PREFS = {'high_quality': 2, 'low_quality': 0}
formats = []
for format_key in ('mp4', 'webm'):
for qname, qurl in vdata[format_key].items():
formats.append({
'format_id': format_key + '_' + qname,
'url': qurl,
'format': format_key,
'preference': PREFS.get(qname),
})
self._sort_formats(formats)
return {
'id': video_id,
'title': vdata['title'],
'description': vdata.get('description'),
'thumbnail': vdata.get('thumbnail'),
'formats': formats,
}
|
