去除标签使用 strip_tags 函数
去掉字符串str的所有html标签。参数二是可保留的标签列表
strip_tags($str[, $allow]);
参数二,使用字符串表示。比如 strip_tags($str, “<p><b>”) 则表示保留p和b标签。
此函数要求字符串中的标签正确闭合,否则解析后的字符串不正常。
另外,对于 等字符实体,不会自动转换。如果需要,则使用 str_replace 把 替换为 ”
strip_tags(str_replace(' ','',$str));
批量替换为空字符串:
str_replace(array(" ","&nbsp;","\t","\r\n","\r","\n"),"")
正则消除标签:
$str=preg_replace("/<s*imgs+[^>]*?srcs*=s*(''|")(.*?)\1[^>]*?/?s*>/i","", $str); //过滤img标签
$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
去除 < 和 > 包裹的标签:
function delhtml($str){ //清除html标签
$st=-1; //开始
$et=-1; //结束
$stmp=array();
$stmp[]=" ";
$len=strlen($str);
for($i=0;$i<$len;$i++){
$ss=substr($str,$i,1);
if(ord($ss)==60){ //ord("<")==60
$st=$i;
}
if(ord($ss)==62){ //ord(">")==62
$et=$i;
if($st!=-1){
$stmp[]=substr($str,$st,$et-$st+1);
}
}
}
$str=str_replace($stmp,"",$str);
return $str;
}
纯正则消除标签和字符实体:
function clear_html_label($html)
{
$search = array ("''<script[^>]*?>.*?</script>''si", "''<[/!]*?[^<>]*?>''si", "''([rn])[s]+''", "''&(quot|#34);''i", "''&(amp|#38);''i", "''&(lt|#60);''i", "''&(gt|#62);''i", "''&(nbsp|#160);''i", "''&(iexcl|#161);''i", "''&(cent|#162);''i", "''&(pound|#163);''i", "''&(copy|#169);''i", "''&#(d+);''e");
$replace = array ("", "", "1", """, "&", "<", ">", " ", chr(161), chr(162), chr(163), chr(169), "chr(1)");
return preg_replace($search, $replace, $html);
}