论坛徽章:: 0

电梯直达

1楼 [收藏(0)] [报告]

发表于 2004-02-27 17:11 |只看该作者 |倒序浏览

看精华贴时可以把一些BBCode转成html
本人初学，时间仓促，请大家多指教

#! C:\Python23\python.exe
# -*- coding: cp936 -*-
import BaseHTTPServer
import urllib
import webbrowser
import re
PORT = 10080
CUDistillateRoot = "http://www.chinaunix.net/jh/";
pageStyle = r"""
<!--
.code {
font-family: 'song',Verdana; font-size: 12px; color: #006600;
background-color: #FAFAFA; border: #D1D7DC; border-style: solid;
border-left-width: 1px; border-top-width: 1px; border-right-width: 1px; border-bottom-width: 1px
}
.quote {
font-family: 'song',Verdana; font-size: 12px; color: #444444; line-height: 125%;
background-color: #FAFAFA; border: #D1D7DC; border-style: solid;
border-left-width: 1px; border-top-width: 1px; border-right-width: 1px; border-bottom-width: 1px
}
-->
</style>
"""
def main():
httpserver = BaseHTTPServer.HTTPServer(("", PORT), CUDistillateHandler)
webbrowser.open("http://localhost:" + `PORT`);
httpserver.serve_forever()
def replace_TAG(htmlcode):
htmlcode = re.compile(r'(src="?)(/images/\w*"?)').sub(r"\1http://www.chinaunix.net\2", htmlcode)
htmlcode = re.compile(r'(<a href="?)http://www.chinaunix.net/jh(/\d{1,3}/\d*\.html?"?)').sub(r"\1\2", htmlcode)
return htmlcode
def replace_BBCode(htmlcode):
htmlcode = re.compile(r'</style>',re.VERBOSE).sub(pageStyle, htmlcode)
htmlcode = re.compile(r'\[b:[^\]]*\]').sub(r'<span style="font-weight: bold">', htmlcode)
htmlcode = re.compile(r'\[/b:[^\]]*\]').sub(r'</span>', htmlcode)
htmlcode = re.compile(r'\[color=(\w*):[^\]]*\]').sub(r'<span style="color: \1">', htmlcode)
htmlcode = re.compile(r'\[/color:[^\]]*\]').sub(r'</span>', htmlcode)
htmlcode = re.compile(r'\[url=([^\]]*)\]([^\[]*)\[/url\]').sub(r'<a href=\1 target=_blank>\2</a>', htmlcode)
htmlcode = re.compile(r'\[url\]([^\[]*)\[/url\]').sub(r'<a href=\1 target=_blank>\1</a>', htmlcode)
htmlcode = re.compile(r'\[code:\w{1,}:[^\]]*\]').sub(r"""
<table width=90% border=0 align=center cellspacing=1 cellpadding=3><tr><td class=code>""", htmlcode)
htmlcode = re.compile(r'\[/code:\w{1,}:[^\]]*\]').sub(r'</td></tr></table>', htmlcode)
htmlcode = re.compile(r'\[quote:\w{1,}="([^"]*)"\]').sub(r"""
<table width=90% border=0 align=center cellspacing=1 cellpadding=3>
<tr><td><br/><b>\1写到:</b></td></tr>
<tr><td class=quote>""", htmlcode)
htmlcode = re.compile(r'\[/quote:[^\]]*\]').sub(r'</td></tr></table>', htmlcode)
htmlcode = re.compile(r'\[list:[^\]]*\]').sub(r'<ol>', htmlcode)
htmlcode = re.compile(r'\[list=(\w{1}):[^\]]*\]').sub(r'<ol type=\1>', htmlcode)
htmlcode = re.compile(r'\[/list[^\]]*\]').sub(r'</ol>', htmlcode)
htmlcode = re.compile(r'\[\*:\w*\]').sub(r'<li>', htmlcode)
return htmlcode
class CUDistillateHandler(BaseHTTPServer.BaseHTTPRequestHandler):
def do_GET(self):
if re.match("^/\d{1,3}", self.path):
srcurl = CUDistillateRoot + self.path
else:
srcurl = CUDistillateRoot
try:
htmlpage = urllib.urlopen(srcurl).read()
htmlpage = replace_TAG(htmlpage)
if re.match("^/\d{1,3}/\d{1,}\.html$", self.path):
htmlpage = replace_BBCode(htmlpage)
except:
htmlpage = """
<html>
<body><h1>不能访问www.chinaunix.net，请检查网络连接</h1>
</body>
</html>
"""
self.send_response(200)
self.send_header("Content-type", "text/html")
self.end_headers()
self.wfile.write(htmlpage)
if __name__ == '__main__':
main()