asp中去除html中style,javascript,css代码

asp函数代码

<%
function removehtml(str)
dim objregexp, match,strhtml
if isnull(str) then
str=""
end if
strhtml=str
strhtml=replace(replace(replace(strhtml,vblf,""),vbcr,""),vbcrlf,"")


set objregexp = new regexp
objregexp.ignorecase = true
objregexp.global = true

objregexp.pattern = "<script[^>]*?>.*?</script>"
strhtml = objregexp.replace(strhtml,"")

objregexp.pattern = "<style[^>]*?>.*?</style>"
strhtml = objregexp.replace(strhtml,"")

objregexp.pattern = "<.+?>"
strhtml = objregexp.replace(strhtml,"")

set objregexp = nothing

removehtml=strhtml
end function
%>

php中的代码

<?php
$search = array ("'<script[^>]*?>.*?</script>'si", // 去掉 javascript
"'<style[^>]*?>.*?</style>'si", // 去掉 css
"'<[/!]*?[^<>]*?>'si", // 去掉 html 标记
"'<!--[/!]*?[^<>]*?>'si", // 去掉 注释标记
"'([rn])[s]+'", // 去掉空白字符
"'&(quot|#34);'i", // 替换 html 实体
"'&(amp|#38);'i",
"'&(lt|#60);'i",
"'&(gt|#62);'i",
"'&(nbsp|#160);'i",
"'&(iexcl|#161);'i",
"'&(cent|#162);'i",
"'&(pound|#163);'i",
"'&(copy|#169);'i",
"'(d+);'e"); // 作为 php 代码运行

$replace = array ("",
"",
"",
"",
"\1",
"\"",
"&",
"<",
">",
" ",
chr(161),
chr(162),
chr(163),
chr(169),
"chr(\1)");
//$document为需要处理字符串，如果来源为文件可以$document = file_get_contents('http://www.sina.com.cn');
$out = preg_replace($search, $replace, $document);
echo $out;
?>

存为get.php即可。