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
}
用正则表达式过滤html中所有Script 的方法：1、定义正则表达式：
/<script\b[^<]*(?:(?!<\/script>)<[^<]*)*<\/script>/gi
2、用正则表达式处理script的方法如下：
<html>
<head>
<!--此处引入script脚本用于测试开始-->
<script type="text/javascript" src="/jquery/jquery.js"></script>
<script type="text/javascript">
$(document).ready(function(){
$(".btn1").click(function(){
alert($("p").html())
})
})
</script>
<!--此处引入script脚本用于测试结束-->
</head>
<body>
<p>This is a paragraph.</p>
<!--这里增加一个按钮，点击后会删除所有的script块的代码-->
<button class="btn1" onclick="removeAllScript()">删除script</button>
</body>
</html>
<!--定义function处理删除-->
function removeAllScript(obj){
//定义正则表达式，只要是存在于<script>和</script>之间的内容都会被删除
var SCRIPT_REGEX = /<script\b[^<]*(?:(?!<\/script>)<[^<]*)*<\/script>/gi
while (SCRIPT_REGEX.test(obj)) {//传入文档对象，获取整体内容
text = text.replace(SCRIPT_REGEX, "")//正则替换为空
}
}
