Upstream/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-13 14:37:43 +01:00
Code Issues Packages Projects Releases Wiki Activity

[porn91] change re to _search_regex

Browse Source
This commit is contained in:
PeterDing 2015-05-28 01:37:24 +08:00
parent d90b3854ca
commit 703d78bbf5
1 changed files with 15 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
youtube_dl/extractor/porn91.py
View File

@ -2,7 +2,6 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
import json
from ..compat import compat_urllib_parse from ..compat import compat_urllib_parse
from .common import InfoExtractor from .common import InfoExtractor
@ -29,30 +28,32 @@ def _real_extract(self, url):
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 = re.search( title = self._search_regex(
r'<div id="viewvideo-title">(.+?)</div>', r'<div id="viewvideo-title">(?P<title>.+?)</div>',
webpage, webpage, 'title', flags=re.DOTALL)
re.DOTALL)
assert title assert title
title = title.group(1).replace('\n', '') title = title.replace('\n', '')
# get real url # get real url
n1 = re.search(r'so.addVariable\(\'file\',\'(\d+)\'', webpage) n1 = self._search_regex(
n2 = re.search(r'so.addVariable\(\'seccode\',\'(.+?)\'', webpage) r'so.addVariable\(\'file\',\'(?P<n1>\d+)\'', webpage, 'n1')
n3 = re.search(r'so.addVariable\(\'max_vid\',\'(\d+)\'', webpage) 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')
if not (n1 and n2 and n3): if not (n1 and n2 and n3):
raise ExtractorError("You are Blocked by Server.") raise ExtractorError("You are Blocked by Server.")
url_params = compat_urllib_parse.urlencode({ url_params = compat_urllib_parse.urlencode({
'VID': n1.group(1), 'VID': n1,
'mp4': '1', 'mp4': '1',
'seccode': n2.group(1), 'seccode': n2,
'max_vid': n3.group(1), 'max_vid': n3,
}) })
t_url = 'http://91porn.com/getfile.php?' + url_params t_url = 'http://91porn.com/getfile.php?' + url_params
info_cn = self._download_webpage(t_url, video_id, "get real video_url") info_cn = self._download_webpage(t_url, video_id, "get real video_url")
video_url = re.search(r'file=(http.+?)&', info_cn).group(1) video_url = self._search_regex(r'file=(?P<url>http.+?)&', info_cn, 'url')
# construct info
info = { info = {
'id': video_id, 'id': video_id,
'title': title, 'title': title,