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
|
import json
import re
from .common import InfoExtractor
class WistiaIE(InfoExtractor):
_VALID_URL = r'^https?://(?:fast\.)?wistia\.net/embed/iframe/(?P<id>[a-z0-9]+)'
_TEST = {
u"url": u"http://fast.wistia.net/embed/iframe/sh7fpupwlt",
u"file": u"sh7fpupwlt.mov",
u"md5": u"cafeb56ec0c53c18c97405eecb3133df",
u"info_dict": {
u"title": u"cfh_resourceful_zdkh_final_1"
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
data_json = self._html_search_regex(
r'Wistia.iframeInit\((.*?), {}\);', webpage, u'video data')
data = json.loads(data_json)
formats = []
thumbnails = []
for atype, a in data['assets'].items():
if atype == 'still':
thumbnails.append({
'url': a['url'],
'resolution': '%dx%d' % (a['width'], a['height']),
})
continue
if atype == 'preview':
continue
formats.append({
'format_id': atype,
'url': a['url'],
'width': a['width'],
'height': a['height'],
'filesize': a['size'],
'ext': a['ext'],
})
formats.sort(key=lambda a: a['filesize'])
return {
'id': video_id,
'title': data['name'],
'formats': formats,
'thumbnails': thumbnails,
}
|
