<%
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
$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
"'&amp;(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;
?>