]>
Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/porn91.py
2 from __future__
import unicode_literals
4 from .common
import InfoExtractor
12 class Porn91IE(InfoExtractor
):
14 _VALID_URL
= r
'(?:https?://)(?:www\.|)91porn\.com/.+?\?viewkey=(?P<id>[\w\d]+)'
17 'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134',
18 'md5': '7fcdb5349354f40d41689bd0fa8db05a',
20 'id': '7e42283b4f5ab36da134',
21 'title': '18岁大一漂亮学妹,水嫩性感,再爽一次!',
28 def _real_extract(self
, url
):
29 video_id
= self
._match
_id
(url
)
30 self
._set
_cookie
('91porn.com', 'language', 'cn_CN')
32 webpage
= self
._download
_webpage
(
33 'http://91porn.com/view_video.php?viewkey=%s' % video_id
, video_id
)
35 if '作为游客,你每天只可观看10个视频' in webpage
:
36 raise ExtractorError('91 Porn says: Daily limit 10 videos exceeded', expected
=True)
38 title
= self
._search
_regex
(
39 r
'<div id="viewvideo-title">([^<]+)</div>', webpage
, 'title')
40 title
= title
.replace('\n', '')
42 video_link_url
= self
._search
_regex
(
43 r
'<textarea[^>]+id=["\']fm
-video_link
[^
>]+>([^
<]+)</textarea
>',
44 webpage, 'video link
')
45 videopage = self._download_webpage(video_link_url, video_id)
47 info_dict = self._parse_html5_media_entries(url, videopage, video_id)[0]
49 duration = parse_duration(self._search_regex(
50 r'时长
:\s
*</span
>\s
*(\d
+:\d
+)', webpage, 'duration
', fatal=False))
52 comment_count = int_or_none(self._search_regex(
53 r'留言
:\s
*</span
>\s
*(\d
+)', webpage, 'comment count
', fatal=False))
59 'comment_count
': comment_count,
60 'age_limit
': self._rta_search(webpage),