]> Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/porn91.py
073fc3e21db07f05deef1a337aca7685f62b4079
[youtubedl] / youtube_dl / extractor / porn91.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from ..compat import (
5 compat_urllib_parse_unquote,
6 compat_urllib_parse_urlencode,
7 )
8 from .common import InfoExtractor
9 from ..utils import (
10 parse_duration,
11 int_or_none,
12 ExtractorError,
13 )
14
15
16 class Porn91IE(InfoExtractor):
17 IE_NAME = '91porn'
18 _VALID_URL = r'(?:https?://)(?:www\.|)91porn\.com/.+?\?viewkey=(?P<id>[\w\d]+)'
19
20 _TEST = {
21 'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134',
22 'md5': '6df8f6d028bc8b14f5dbd73af742fb20',
23 'info_dict': {
24 'id': '7e42283b4f5ab36da134',
25 'title': '18岁大一漂亮学妹,水嫩性感,再爽一次!',
26 'ext': 'mp4',
27 'duration': 431,
28 'age_limit': 18,
29 }
30 }
31
32 def _real_extract(self, url):
33 video_id = self._match_id(url)
34 self._set_cookie('91porn.com', 'language', 'cn_CN')
35
36 webpage = self._download_webpage(
37 'http://91porn.com/view_video.php?viewkey=%s' % video_id, video_id)
38
39 if '作为游客,你每天只可观看10个视频' in webpage:
40 raise ExtractorError('91 Porn says: Daily limit 10 videos exceeded', expected=True)
41
42 title = self._search_regex(
43 r'<div id="viewvideo-title">([^<]+)</div>', webpage, 'title')
44 title = title.replace('\n', '')
45
46 # get real url
47 file_id = self._search_regex(
48 r'so.addVariable\(\'file\',\'(\d+)\'', webpage, 'file id')
49 sec_code = self._search_regex(
50 r'so.addVariable\(\'seccode\',\'([^\']+)\'', webpage, 'sec code')
51 max_vid = self._search_regex(
52 r'so.addVariable\(\'max_vid\',\'(\d+)\'', webpage, 'max vid')
53 url_params = compat_urllib_parse_urlencode({
54 'VID': file_id,
55 'mp4': '1',
56 'seccode': sec_code,
57 'max_vid': max_vid,
58 })
59 info_cn = self._download_webpage(
60 'http://91porn.com/getfile.php?' + url_params, video_id,
61 'Downloading real video url')
62 video_url = compat_urllib_parse_unquote(self._search_regex(
63 r'file=([^&]+)&', info_cn, 'url'))
64
65 duration = parse_duration(self._search_regex(
66 r'时长:\s*</span>\s*(\d+:\d+)', webpage, 'duration', fatal=False))
67
68 comment_count = int_or_none(self._search_regex(
69 r'留言:\s*</span>\s*(\d+)', webpage, 'comment count', fatal=False))
70
71 return {
72 'id': video_id,
73 'title': title,
74 'url': video_url,
75 'duration': duration,
76 'comment_count': comment_count,
77 'age_limit': self._rta_search(webpage),
78 }