
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
}
}
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]*
欢迎分享,转载请注明来源:内存溢出
微信扫一扫
支付宝扫一扫
评论列表(0条)