PHP常用工具函数小结【移除XSS攻击、UTF8与GBK编码转换等】

 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  // note that you have to handle splits with \n, \r, and \t 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  $search = 'abcdefghijklmnopqrstuvwxyz'; $search .= 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'; $search .= '1234567890!@#$%^&*()'; $search .= '~`";:?+/={}[]-_|\'\\'; for ($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], $val);<b style="color:transparent">来源gao@dai!ma.com搞$代^码网</b> // 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 \t, \n, and \r $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  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[$i], 0, 2).''.substr($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; } 

 function GBKtoUTF8($str) { if(is_array($str)) { foreach ($str as &$value) { $value = GBKtoUTF8($value); } return $str; }elseif(is_string($str)){ $str = iconv("GB18030", "UTF-8//IGNORE", $str); return $str; }else{ return $str; } } 

 function UTF8toGBK(&$str) { if(is_array($str)) { foreach ($str as &$value) { $value = UTF8toGBK($value); } return $str; }elseif (is_string($str)){ $str = iconv("UTF-8", "GB18030//IGNORE", $str); return $str; }else{ return $str; } }