]>
Commit | Line | Data |
---|---|---|
e423e0ba S |
1 | from __future__ import unicode_literals |
2 | ||
ef4fd848 PH |
3 | import json |
4 | import re | |
5 | ||
6 | from .common import InfoExtractor | |
7 | ||
8 | ||
9 | class WistiaIE(InfoExtractor): | |
e423e0ba | 10 | _VALID_URL = r'https?://(?:fast\.)?wistia\.net/embed/iframe/(?P<id>[a-z0-9]+)' |
ef4fd848 PH |
11 | |
12 | _TEST = { | |
e423e0ba S |
13 | 'url': 'http://fast.wistia.net/embed/iframe/sh7fpupwlt', |
14 | 'md5': 'cafeb56ec0c53c18c97405eecb3133df', | |
15 | 'info_dict': { | |
16 | 'id': 'sh7fpupwlt', | |
17 | 'ext': 'mov', | |
18 | 'title': 'Being Resourceful', | |
19 | 'duration': 117, | |
ef4fd848 PH |
20 | }, |
21 | } | |
22 | ||
23 | def _real_extract(self, url): | |
24 | mobj = re.match(self._VALID_URL, url) | |
25 | video_id = mobj.group('id') | |
26 | ||
27 | webpage = self._download_webpage(url, video_id) | |
28 | data_json = self._html_search_regex( | |
e423e0ba | 29 | r'Wistia\.iframeInit\((.*?), {}\);', webpage, 'video data') |
ef4fd848 PH |
30 | |
31 | data = json.loads(data_json) | |
32 | ||
33 | formats = [] | |
34 | thumbnails = [] | |
35 | for atype, a in data['assets'].items(): | |
36 | if atype == 'still': | |
37 | thumbnails.append({ | |
38 | 'url': a['url'], | |
39 | 'resolution': '%dx%d' % (a['width'], a['height']), | |
40 | }) | |
41 | continue | |
42 | if atype == 'preview': | |
43 | continue | |
44 | formats.append({ | |
45 | 'format_id': atype, | |
46 | 'url': a['url'], | |
47 | 'width': a['width'], | |
48 | 'height': a['height'], | |
49 | 'filesize': a['size'], | |
50 | 'ext': a['ext'], | |
08d13955 | 51 | 'preference': 1 if atype == 'original' else None, |
ef4fd848 | 52 | }) |
539179f4 PH |
53 | |
54 | self._sort_formats(formats) | |
ef4fd848 PH |
55 | |
56 | return { | |
57 | 'id': video_id, | |
58 | 'title': data['name'], | |
59 | 'formats': formats, | |
60 | 'thumbnails': thumbnails, | |
e423e0ba | 61 | 'duration': data.get('duration'), |
ef4fd848 | 62 | } |