<%
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 標(biāo)記
"'<!--[/!]*?[^<>]*?>'si", // 去掉 注釋標(biāo)記
"'([rn])[s]+'", // 去掉空白字符
"'&(quot|#34);'i", // 替換 HTML 實(shí)體
"'&(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"); // 作為 PHP 代碼運(yùn)行

$replace = array ("",
"",
"",
"",
"\1",
"\"",
"&",
"<",
">",
" ",
chr(161),
chr(162),
chr(163),
chr(169),
"chr(\1)");
//$document為需要處理字符串，如果來源為文件可以$document = file_get_contents('http://www.sina.com.cn');
$out = preg_replace($search, $replace, $document);
echo $out;
?>