IT博客汇
  • 首页
  • 精华
  • 技术
  • 设计
  • 资讯
  • 扯淡
  • 权利声明
  • 登录 注册

    php过滤HTML标签、属性等正则表达式汇总

    usity发表于 2016-08-18 08:55:55
    love 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()


    过滤所有html标签的正则表达式: 
    </?[^>]+>
     
    //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<p>,即不过滤<p>):
    </?[^pP/>]+>

    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):
    </?[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]*

    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);
    }



沪ICP备19023445号-2号
友情链接