diff options
author | Yen Chi Hsuan <yan12125@gmail.com> | 2015-05-30 23:33:10 +0800 |
---|---|---|
committer | Yen Chi Hsuan <yan12125@gmail.com> | 2015-05-30 23:33:10 +0800 |
commit | 1ebc05df91b769452da50c5fad0b413550d5e1de (patch) | |
tree | 42cec38922326ff6b2225264b4ea10c594191f14 /youtube_dl/extractor/porn91.py | |
parent | 386bdfa698a7f06c43df91913677db3732e29900 (diff) | |
parent | 806598b94dec1268566ae71d671116060f7971d6 (diff) | |
download | youtube-dl-1ebc05df91b769452da50c5fad0b413550d5e1de.tar.xz |
Merge branch 'porn91' of https://github.com/PeterDing/youtube-dl into PeterDing-porn91
Diffstat (limited to 'youtube_dl/extractor/porn91.py')
-rw-r--r-- | youtube_dl/extractor/porn91.py | 60 |
1 files changed, 60 insertions, 0 deletions
diff --git a/youtube_dl/extractor/porn91.py b/youtube_dl/extractor/porn91.py new file mode 100644 index 000000000..b62eec92d --- /dev/null +++ b/youtube_dl/extractor/porn91.py @@ -0,0 +1,60 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from ..compat import compat_urllib_parse +from .common import InfoExtractor +from ..utils import ExtractorError + + +class Porn91IE(InfoExtractor): + IE_NAME = '91porn' + _VALID_URL = r'(?:https?://)(?:www\.|)91porn\.com/.+?\?viewkey=(?P<id>[\w\d]+)' + + _TEST = { + 'url': 'http://91porn.com/view_video.php?viewkey=7e42283b4f5ab36da134', + 'md5': '6df8f6d028bc8b14f5dbd73af742fb20', + 'info_dict': { + 'id': '7e42283b4f5ab36da134', + 'title': '18岁大一漂亮学妹,水嫩性感,再爽一次!', + 'ext': 'mp4' + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + url = 'http://91porn.com/view_video.php?viewkey=%s' % video_id + self._set_cookie('91porn.com', 'language', 'cn_CN') + webpage = self._download_webpage(url, video_id, "get HTML content") + title = self._search_regex( + r'<div id="viewvideo-title">(?P<title>.+?)</div>', + webpage, 'title', flags=re.DOTALL) + title = title.replace('\n', '') + + # get real url + n1 = self._search_regex( + r'so.addVariable\(\'file\',\'(?P<n1>\d+)\'', webpage, 'n1') + n2 = self._search_regex( + r'so.addVariable\(\'seccode\',\'(?P<n2>.+?)\'', webpage, 'n2') + n3 = self._search_regex( + r'so.addVariable\(\'max_vid\',\'(?P<n3>\d+)\'', webpage, 'n3') + url_params = compat_urllib_parse.urlencode({ + 'VID': n1, + 'mp4': '1', + 'seccode': n2, + 'max_vid': n3, + }) + t_url = 'http://91porn.com/getfile.php?' + url_params + info_cn = self._download_webpage(t_url, video_id, "get real video_url") + video_url = self._search_regex(r'file=(?P<url>http.+?)&', info_cn, 'url') + + # construct info + info = { + 'id': video_id, + 'title': title, + 'url': video_url, + } + + return info |