]>
Commit | Line | Data |
---|---|---|
4cda41ac | 1 | from __future__ import unicode_literals |
2 | ||
3 | import re | |
4 | ||
5 | from .common import InfoExtractor | |
6 | ||
7 | class AlphaPornoIE(InfoExtractor): | |
8 | _VALID_URL = r'https?://(?:www\.)?alphaporno\.com/videos/(?P<display_id>[^/]+)' | |
9 | _TEST = { | |
10 | 'url': 'http://www.alphaporno.com/videos/sensual-striptease-porn-with-samantha-alexandra/', | |
11 | 'md5': 'feb6d3bba8848cd54467a87ad34bd38e', | |
12 | 'info_dict': { | |
13 | 'id': '258807', | |
14 | 'ext': 'mp4', | |
15 | 'title': 'Sensual striptease porn with Samantha Alexandra - Striptease Porn', | |
16 | 'description': 'md5:c4447dc80e5be4c5f2711f7806e45424', | |
17 | 'categories': list, # NSFW | |
18 | 'thumbnail': 're:https?://.*\.jpg$', | |
19 | 'age_limit': 18, | |
20 | } | |
21 | } | |
22 | ||
23 | def _real_extract(self, url): | |
24 | webpage = self._download_webpage(url, 'main') | |
25 | ||
26 | video_id = self._html_search_regex(r'video_id:\s*\'([^\']+)\'', webpage, 'id') | |
27 | ||
28 | video_url = self._html_search_regex(r'video_url:\s*\'([^\']+)\'', webpage, 'video_url') | |
29 | ||
30 | ext = self._html_search_meta('encodingFormat', webpage, 'ext')[1:] | |
31 | ||
32 | title = self._html_search_regex( | |
33 | r'<title>([^<]+)</title>', webpage, 'title') | |
34 | ||
35 | description = self._html_search_meta('description', webpage, 'description', fatal=False) | |
36 | ||
37 | thumbnail = self._html_search_meta('thumbnail', webpage, 'thumbnail', fatal=False) | |
38 | ||
39 | categories_str = self._html_search_meta( | |
40 | 'keywords', webpage, 'categories', fatal=False) | |
41 | categories = ( | |
42 | None if categories_str is None | |
43 | else categories_str.split(',')) | |
44 | ||
45 | return { | |
46 | 'id': video_id, | |
47 | 'url': video_url, | |
48 | 'title': title, | |
49 | 'ext': ext, | |
50 | 'description': description, | |
51 | 'thumbnail': thumbnail, | |
52 | 'categories': categories, | |
53 | 'age_limit': 18, | |
54 | } |