]>
Commit | Line | Data |
---|---|---|
1 | from __future__ import unicode_literals | |
2 | ||
3 | import re | |
4 | ||
5 | from .common import InfoExtractor | |
6 | from ..utils import ( | |
7 | parse_duration, | |
8 | int_or_none, | |
9 | ) | |
10 | ||
11 | ||
12 | class SunPornoIE(InfoExtractor): | |
13 | _VALID_URL = r'https?://(?:www\.)?sunporno\.com/videos/(?P<id>\d+)' | |
14 | _TEST = { | |
15 | 'url': 'http://www.sunporno.com/videos/807778/', | |
16 | 'md5': '6457d3c165fd6de062b99ef6c2ff4c86', | |
17 | 'info_dict': { | |
18 | 'id': '807778', | |
19 | 'ext': 'flv', | |
20 | 'title': 'md5:0a400058e8105d39e35c35e7c5184164', | |
21 | 'description': 'md5:a31241990e1bd3a64e72ae99afb325fb', | |
22 | 'duration': 302, | |
23 | } | |
24 | } | |
25 | ||
26 | def _real_extract(self, url): | |
27 | mobj = re.match(self._VALID_URL, url) | |
28 | video_id = mobj.group('id') | |
29 | ||
30 | webpage = self._download_webpage(url, video_id) | |
31 | ||
32 | video_url = self._html_search_regex( | |
33 | r'videoSource\s*=\s*\'<source\s*src="([^"]*)"', webpage, 'video URL') | |
34 | ||
35 | title = self._html_search_regex(r'<title>([^<]*)</title>', webpage, 'title') | |
36 | ||
37 | description = self._html_search_regex( | |
38 | r'<meta name="description" content="([^"]*)"', webpage, 'description', fatal=False) | |
39 | ||
40 | thumbnail = self._html_search_regex( | |
41 | r'poster="([^"]*)"', webpage, 'thumbnail', fatal=False) | |
42 | ||
43 | duration = parse_duration(self._search_regex( | |
44 | r'<span>Duration: (\d+:\d+)</span>', webpage, 'duration', fatal=False)) | |
45 | ||
46 | view_count = int_or_none(self._html_search_regex( | |
47 | r'<span class="views">(\d+)</span>', webpage, 'view count', fatal=False)) | |
48 | ||
49 | return { | |
50 | 'id': video_id, | |
51 | 'url': video_url, | |
52 | 'title': title, | |
53 | 'description': description, | |
54 | 'thumbnail': thumbnail, | |
55 | 'duration': duration, | |
56 | 'view_count': view_count, | |
57 | } |