php过滤HTML标签、属性等正则表达式汇总

2017-09-08 15:09:28 查看 1823 回复 0
$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
</?[^>]+>
 
//过滤所有html标签的属性的正则表达式:
 
$html = preg_replace("/<([a-zA-Z]+)[^>]*>/","<\\1>",$html);

过滤部分html标签的正则表达式的排除式(比如排除,即不过滤):


</?[^pP/>]+>

过滤部分html标签的正则表达式的枚举式(比如需要过滤等):

</?[aApPbB][^>]*>

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):

\s(?!alt)[a-zA-Z]+=[^\s]*

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):

(\s)alt=[^\s]*

JavaScript正则表达式在线测试工具: http://tools.jb51.net/regex/javascript

正则表达式在线生成工具: http://tools.jb51.net/regex/create_reg

正则测试工具:http://regex.zjmainstay.cn/r/IFxNoT/7