PHP通用的XSS攻击过滤函数，Discuz系统中 防止XSS漏洞攻击，过滤HTML危险标签属性的PHP函数

XSS攻击在最近很是流行，往往在某段代码里一不小心就会被人放上XSS攻击的代码，看到国外有人写上了函数，咱也偷偷懒，悄悄的贴上来。。。
原文如下：

The goal of this function is to be a generic function that can be used to parse almost any input and render it XSS safe. For more information on actual XSS attacks, check out http://ha.ckers.org/xss.html. Another excellent site is the XSS Database which details each attack and how it works.

<?php
function RemoveXSS($val) {
   // remove all non-printable characters. CR(0a) and LF(0b) and TAB(9) are allowed
   // this prevents some character re-spacing such as <javascript>
   // note that you have to handle splits with
,
, and 	 later since they *are* allowed in some inputs
   $val = preg_replace(‘/([x00-x08,x0b-x0c,x0e-x19])/‘, ‘‘, $val);  

   // straight replacements, the user should never need these since they‘re normal characters
   // this prevents like <IMG [email protected]:alert(‘XSS‘)>
   $search = ‘abcdefghijklmnopqrstuvwxyz‘;
   $search .= ‘ABCDEFGHIJKLMNOPQRSTUVWXYZ‘;
   $search .= ‘[email protected]#$%^&*()‘;
   $search .= ‘~`";:?+/={}[]-_|‘\‘;
   for ($i = 0; $i < strlen($search); $i++) {
	  // ;? matches the ;, which is optional
	  // 0{0,7} matches any padded zeros, which are optional and go up to 8 chars 

	  // @ @ search for the hex values
	  $val = preg_replace(‘/(&#[xX]0{0,8}‘.dechex(ord($search[$i])).‘;?)/i‘, $search[$i], $val); // with a ;
	  // @ @ 0{0,7} matches ‘0‘ zero to seven times
	  $val = preg_replace(‘/(&#0{0,8}‘.ord($search[$i]).‘;?)/‘, $search[$i], $val); // with a ;
   } 

   // now the only remaining whitespace attacks are 	,
, and 

   $ra1 = Array(‘javascript‘, ‘vbscript‘, ‘expression‘, ‘applet‘, ‘meta‘, ‘xml‘, ‘blink‘, ‘link‘, ‘style‘, ‘script‘, ‘embed‘, ‘object‘, ‘iframe‘, ‘frame‘, ‘frameset‘, ‘ilayer‘, ‘layer‘, ‘bgsound‘, ‘title‘, ‘base‘);
   $ra2 = Array(‘onabort‘, ‘onactivate‘, ‘onafterprint‘, ‘onafterupdate‘, ‘onbeforeactivate‘, ‘onbeforecopy‘, ‘onbeforecut‘, ‘onbeforedeactivate‘, ‘onbeforeeditfocus‘, ‘onbeforepaste‘, ‘onbeforeprint‘, ‘onbeforeunload‘, ‘onbeforeupdate‘, ‘onblur‘, ‘onbounce‘, ‘oncellchange‘, ‘onchange‘, ‘onclick‘, ‘oncontextmenu‘, ‘oncontrolselect‘, ‘oncopy‘, ‘oncut‘, ‘ondataavailable‘, ‘ondatasetchanged‘, ‘ondatasetcomplete‘, ‘ondblclick‘, ‘ondeactivate‘, ‘ondrag‘, ‘ondragend‘, ‘ondragenter‘, ‘ondragleave‘, ‘ondragover‘, ‘ondragstart‘, ‘ondrop‘, ‘onerror‘, ‘onerrorupdate‘, ‘onfilterchange‘, ‘onfinish‘, ‘onfocus‘, ‘onfocusin‘, ‘onfocusout‘, ‘onhelp‘, ‘onkeydown‘, ‘onkeypress‘, ‘onkeyup‘, ‘onlayoutcomplete‘, ‘onload‘, ‘onlosecapture‘, ‘onmousedown‘, ‘onmouseenter‘, ‘onmouseleave‘, ‘onmousemove‘, ‘onmouseout‘, ‘onmouseover‘, ‘onmouseup‘, ‘onmousewheel‘, ‘onmove‘, ‘onmoveend‘, ‘onmovestart‘, ‘onpaste‘, ‘onpropertychange‘, ‘onreadystatechange‘, ‘onreset‘, ‘onresize‘, ‘onresizeend‘, ‘onresizestart‘, ‘onrowenter‘, ‘onrowexit‘, ‘onrowsdelete‘, ‘onrowsinserted‘, ‘onscroll‘, ‘onselect‘, ‘onselectionchange‘, ‘onselectstart‘, ‘onstart‘, ‘onstop‘, ‘onsubmit‘, ‘onunload‘);
   $ra = array_merge($ra1, $ra2); 

   $found = true; // keep replacing as long as the previous round replaced something
   while ($found == true) {
	  $val_before = $val;
	  for ($i = 0; $i < sizeof($ra); $i++) {
		 $pattern = ‘/‘;
		 for ($j = 0; $j < strlen($ra[$i]); $j++) {
			if ($j > 0) {
			   $pattern .= ‘(‘;
			   $pattern .= ‘(&#[xX]0{0,8}([9ab]);)‘;
			   $pattern .= ‘|‘;
			   $pattern .= ‘|(&#0{0,8}([9|10|13]);)‘;
			   $pattern .= ‘)*‘;
			}
			$pattern .= $ra[$i][$j];
		 }
		 $pattern .= ‘/i‘;
		 $replacement = substr($ra[$i], 0, 2).‘<x>‘.substr($ra[$i], 2); // add in <> to nerf the tag
		 $val = preg_replace($pattern, $replacement, $val); // filter out the hex tags
		 if ($val_before == $val) {
			// no replacements were made, so exit the loop
			$found = false;
		 }
	  }
   }  

   return $val;
}
?>

经过这样的过滤后，应该被攻击的机会会少上很多吧？试试看呢？

//屏蔽html
function checkhtml($html) {
	$html = stripslashes($html);
	if(!checkperm(‘allowhtml‘)) {

		preg_match_all("/<([^<]+)>/is", $html, $ms);

		$searchs[] = ‘<‘;
		$replaces[] = ‘<‘;
		$searchs[] = ‘>‘;
		$replaces[] = ‘>‘;

		if($ms[1]) {
			$allowtags = ‘img|a|font|div|table|tbody|caption|tr|td|th|br
						|p|b|strong|i|u|em|span|ol|ul|li|blockquote
						|object|param|embed‘;//允许的标签
			$ms[1] = array_unique($ms[1]);
			foreach ($ms[1] as $value) {
				$searchs[] = "<".$value.">";
				$value = shtmlspecialchars($value);
				$value = str_replace(array(‘\‘,‘/*‘), array(‘.‘,‘/.‘), $value);
				$skipkeys = array(
						‘onabort‘,‘onactivate‘,‘onafterprint‘,‘onafterupdate‘,
						‘onbeforeactivate‘,‘onbeforecopy‘,‘onbeforecut‘,
						‘onbeforedeactivate‘,‘onbeforeeditfocus‘,‘onbeforepaste‘,
						‘onbeforeprint‘,‘onbeforeunload‘,‘onbeforeupdate‘,
						‘onblur‘,‘onbounce‘,‘oncellchange‘,‘onchange‘,
						‘onclick‘,‘oncontextmenu‘,‘oncontrolselect‘,
						‘oncopy‘,‘oncut‘,‘ondataavailable‘,
						‘ondatasetchanged‘,‘ondatasetcomplete‘,‘ondblclick‘,
						‘ondeactivate‘,‘ondrag‘,‘ondragend‘,
						‘ondragenter‘,‘ondragleave‘,‘ondragover‘,
						‘ondragstart‘,‘ondrop‘,‘onerror‘,‘onerrorupdate‘,
						‘onfilterchange‘,‘onfinish‘,‘onfocus‘,‘onfocusin‘,
						‘onfocusout‘,‘onhelp‘,‘onkeydown‘,‘onkeypress‘,
						‘onkeyup‘,‘onlayoutcomplete‘,‘onload‘,
						‘onlosecapture‘,‘onmousedown‘,‘onmouseenter‘,
						‘onmouseleave‘,‘onmousemove‘,‘onmouseout‘,
						‘onmouseover‘,‘onmouseup‘,‘onmousewheel‘,
						‘onmove‘,‘onmoveend‘,‘onmovestart‘,‘onpaste‘,
						‘onpropertychange‘,‘onreadystatechange‘,‘onreset‘,
						‘onresize‘,‘onresizeend‘,‘onresizestart‘,
						‘onrowenter‘,‘onrowexit‘,‘onrowsdelete‘,
						‘onrowsinserted‘,‘onscroll‘,‘onselect‘,
						‘onselectionchange‘,‘onselectstart‘,‘onstart‘,
						‘onstop‘,‘onsubmit‘,‘onunload‘,‘javascript‘,
						‘script‘,‘eval‘,‘behaviour‘,‘expression‘,
						‘style‘,‘class‘
					);
				$skipstr = implode(‘|‘, $skipkeys);
				$value = preg_replace(array("/($skipstr)/i"), ‘.‘, $value);
				if(!preg_match("/^[/|s]?($allowtags)(s+|$)/is", $value)) {
					$value = ‘‘;
				}
				$replaces[] = empty($value)?‘‘:"<".str_replace(‘"‘, ‘"‘, $value).">";
			}
		}
		$html = str_replace($searchs, $replaces, $html);
	}
	$html = addslashes($html);

	return $html;
}