github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-30 12:01:28 -05:00
Code Issues Projects Releases Packages Wiki Activity

[porn91] Simplify

Browse source
This commit is contained in:
Yen Chi Hsuan 2015-05-31 00:03:19 +08:00
parent 9ff811c5cd
commit 1c22238756
1 changed files with 16 additions and 22 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

38
youtube_dl/extractor/porn91.py
View file

@ -1,8 +1,6 @@
# encoding: utf-8 # encoding: utf-8
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from ..compat import compat_urllib_parse from ..compat import compat_urllib_parse
from .common import InfoExtractor from .common import InfoExtractor
@ -22,38 +20,34 @@ class Porn91IE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id')
url = 'http://91porn.com/view_video.php?viewkey=%s' % video_id url = 'http://91porn.com/view_video.php?viewkey=%s' % video_id
self._set_cookie('91porn.com', 'language', 'cn_CN') self._set_cookie('91porn.com', 'language', 'cn_CN')
webpage = self._download_webpage(url, video_id, "get HTML content") webpage = self._download_webpage(url, video_id, "get HTML content")
title = self._search_regex( title = self._search_regex(
r'<div id="viewvideo-title">(?P<title>.+?)</div>', r'<div id="viewvideo-title">([^<]+)</div>', webpage, 'title')
webpage, 'title', flags=re.DOTALL)
title = title.replace('\n', '') title = title.replace('\n', '')
# get real url # get real url
n1 = self._search_regex( file_id = self._search_regex(
r'so.addVariable\(\'file\',\'(?P<n1>\d+)\'', webpage, 'n1') r'so.addVariable\(\'file\',\'(\d+)\'', webpage, 'file id')
n2 = self._search_regex( sec_code = self._search_regex(
r'so.addVariable\(\'seccode\',\'(?P<n2>.+?)\'', webpage, 'n2') r'so.addVariable\(\'seccode\',\'([^\']+)\'', webpage, 'sec code')
n3 = self._search_regex( max_vid = self._search_regex(
r'so.addVariable\(\'max_vid\',\'(?P<n3>\d+)\'', webpage, 'n3') r'so.addVariable\(\'max_vid\',\'(\d+)\'', webpage, 'max vid')
url_params = compat_urllib_parse.urlencode({ url_params = compat_urllib_parse.urlencode({
'VID': n1, 'VID': file_id,
'mp4': '1', 'mp4': '1',
'seccode': n2, 'seccode': sec_code,
'max_vid': n3, 'max_vid': max_vid,
}) })
t_url = 'http://91porn.com/getfile.php?' + url_params info_cn = self._download_webpage(
info_cn = self._download_webpage(t_url, video_id, "get real video_url") 'http://91porn.com/getfile.php?' + url_params, video_id,
video_url = self._search_regex(r'file=(?P<url>http.+?)&', info_cn, 'url') "get real video url")
video_url = self._search_regex(r'file=([^&]+)&', info_cn, 'url')
# construct info return {
info = {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'url': video_url, 'url': video_url,
} }
return info