public string checkStr(string html)
{
System.Text.RegularExpressions.Regex regex1 = new System.Text.RegularExpressions.Regex(@"<script[\s\S]+</script *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase)
System.Text.RegularExpressions.Regex regex2 = new System.Text.RegularExpressions.Regex(@" href *= *[\s\S]*script *:", System.Text.RegularExpressions.RegexOptions.IgnoreCase)
System.Text.RegularExpressions.Regex regex3 = new System.Text.RegularExpressions.Regex(@" on[\s\S]*=", System.Text.RegularExpressions.RegexOptions.IgnoreCase)
System.Text.RegularExpressions.Regex regex4 = new System.Text.RegularExpressions.Regex(@"<iframe[\s\S]+</iframe *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase)
System.Text.RegularExpressions.Regex regex5 = new System.Text.RegularExpressions.Regex(@"<frameset[\s\S]+</frameset *>", System.Text.RegularExpressions.RegexOptions.IgnoreCase)
System.Text.RegularExpressions.Regex regex6 = new System.Text.RegularExpressions.Regex(@"\<img[^\>]+\>", System.Text.RegularExpressions.RegexOptions.IgnoreCase)
System.Text.RegularExpressions.Regex regex7 = new System.Text.RegularExpressions.Regex(@"</p>", System.Text.RegularExpressions.RegexOptions.IgnoreCase)
System.Text.RegularExpressions.Regex regex8 = new System.Text.RegularExpressions.Regex(@"<p>", System.Text.RegularExpressions.RegexOptions.IgnoreCase)
System.Text.RegularExpressions.Regex regex9 = new System.Text.RegularExpressions.Regex(@"<[^>]*>", System.Text.RegularExpressions.RegexOptions.IgnoreCase)
html = regex1.Replace(html, "")//过滤<script></script>标记
html = regex2.Replace(html, "")//过滤href=javascript: (<A>) 属性
html = regex3.Replace(html, " _disibledevent=")//过滤其它控件的on...事件
html = regex4.Replace(html, "")//过滤iframe
html = regex5.Replace(html, "")//过滤frameset
html = regex6.Replace(html, "")//过滤frameset
html = regex7.Replace(html, "")//过滤frameset
html = regex8.Replace(html, "")//过滤frameset
html = regex9.Replace(html, "")
html = html.Replace(" ", "")
html = html.Replace("</strong>", "")
html = html.Replace("<strong>", "")
return html
}
1、过滤所有html标签的属性的正则表达式：$search = array ("'<script[^>]*?>.*?</script>'si", // 去掉 JavaScript
"'<[\/\!]*?[^<>]*?>'si", // 去掉 HTML 标记
"'([\r\n])[\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"
) // 作为 PHP 代码运行
$replace = array ("","","\\1","\"","&","<",">"," ")
$html = preg_replace($search, $replace, $html)
顶
$str=preg_replace("/\s+/", " ", $str)//过滤多余回车$str=preg_replace("/<[ ]+/si","<",$str)//过滤<__("<"号后面带空格)
$str=preg_replace("/<\!--.*?-->/si","",$str)//注释
$str=preg_replace("/<(\!.*?)>/si","",$str)//过滤DOCTYPE
$str=preg_replace("/<(\/?html.*?)>/si","",$str)//过滤html标签
$str=preg_replace("/<(\/?head.*?)>/si","",$str)//过滤head标签
$str=preg_replace("/<(\/?meta.*?)>/si","",$str)//过滤meta标签
$str=preg_replace("/<(\/?body.*?)>/si","",$str)//过滤body标签
$str=preg_replace("/<(\/?link.*?)>/si","",$str)//过滤link标签
$str=preg_replace("/<(\/?form.*?)>/si","",$str)//过滤form标签
$str=preg_replace("/cookie/si","COOKIE",$str)//过滤COOKIE标签
$str=preg_replace("/<(applet.*?)>(.*?)<(\/applet.*?)>/si","",$str)//过滤applet标签
$str=preg_replace("/<(\/?applet.*?)>/si","",$str)//过滤applet标签
$str=preg_replace("/<(style.*?)>(.*?)<(\/style.*?)>/si","",$str)//过滤style标签
$str=preg_replace("/<(\/?style.*?)>/si","",$str)//过滤style标签
$str=preg_replace("/<(title.*?)>(.*?)<(\/title.*?)>/si","",$str)//过滤title标签
$str=preg_replace("/<(\/?title.*?)>/si","",$str)//过滤title标签
$str=preg_replace("/<(object.*?)>(.*?)<(\/object.*?)>/si","",$str)//过滤object标签
$str=preg_replace("/<(\/?objec.*?)>/si","",$str)//过滤object标签
$str=preg_replace("/<(noframes.*?)>(.*?)<(\/noframes.*?)>/si","",$str)//过滤noframes标签
$str=preg_replace("/<(\/?noframes.*?)>/si","",$str)//过滤noframes标签
$str=preg_replace("/<(i?frame.*?)>(.*?)<(\/i?frame.*?)>/si","",$str)//过滤frame标签
$str=preg_replace("/<(\/?i?frame.*?)>/si","",$str)//过滤frame标签
$str=preg_replace("/<(script.*?)>(.*?)<(\/script.*?)>/si","",$str)//过滤script标签
$str=preg_replace("/<(\/?script.*?)>/si","",$str)//过滤script标签
$str=preg_replace("/javascript/si","Javascript",$str)//过滤script标签
$str=preg_replace("/vbscript/si","Vbscript",$str)//过滤script标签
$str=preg_replace("/on([a-z]+)\s*=/si","On\\1=",$str)//过滤script标签
$str=preg_replace("//si","&＃",$str)//过滤script标签，如javAsCript:alert(
清除空格，换行
function DeleteHtml($str)
{
$str = trim($str)
$str = strip_tags($str,"")
$str = ereg_replace("\t","",$str)
$str = ereg_replace("\r\n","",$str)
$str = ereg_replace("\r","",$str)
$str = ereg_replace("\n","",$str)
$str = ereg_replace(" "," ",$str)
return trim($str)
}
过滤HTML属性
1，过滤所有html标签的正则表达式：
复制代码 代码如下:
</?[^>]+>
//过滤所有html标签的属性的正则表达式：
$html = preg_replace("/<([a-zA-Z]+)[^>]*>/","<\\1>",$html)
3，过滤部分html标签的正则表达式的排除式（比如排除<p>，即不过滤<p>）：
复制代码 代码如下:
</?[^pP/>]+>
4，过滤部分html标签的正则表达式的枚举式（比如需要过滤<a><p><b>等）：
复制代码 代码如下:
</?[aApPbB][^>]*>
5，过滤部分html标签的属性的正则表达式的排除式（比如排除alt属性，即不过滤alt属性）：
复制代码 代码如下:
\s(?!alt)[a-zA-Z]+=[^\s]*
6，过滤部分html标签的属性的正则表达式的枚举式（比如alt属性）：
复制代码 代码如下:
(\s)alt=[^\s]*
