php各类过滤字符函数

收集的php各种过滤字符函数,从几个cms中提取的。随便拿来用

<?php /** * 安全过滤函数 * * @param $string * @return string */ function safe_replace($string) { $string = str_replace('%20','',$string); $string = str_replace('%27','',$string); $string = str_replace('%2527','',$string); $string = str_replace('*','',$string); $string = str_replace('"','&quot;',$string); $string = str_replace("'",'',$string); $string = str_replace('"','',$string); $string = str_replace(';','',$string); $string = str_replace('<','&lt;',$string); $string = str_replace('>','&gt;',$string); $string = str_replace("{",'',$string); $string = str_replace('}','',$string); $string = str_replace('\\','',$string); return $string; } ?> <?php /** * 返回经addslashes处理过的字符串或数组 * @param $string 需要处理的字符串或数组 * @return mixed */ function new_addslashes($string) { if(!is_array($string)) return addslashes($string); foreach($string as $key => $val) $string[$key] = new_addslashes($val); return $string; } ?><?php /** * 转义 javascript 代码标记 * * @param $str * @return mixed */ function trim_script($str) { if(is_array($str)){ foreach ($str as $key => $val){ $str[$key] = trim_script($val); } }else{ $str = preg_replace ( '/\<([\/]?)script([^\>]*?)\>/si', '&lt;\\1script\\2&gt;', $str ); $str = preg_replace ( '/\<([\/]?)iframe([^\>]*?)\>/si', '&lt;\\1iframe\\2&gt;', $str ); $str = preg_replace ( '/\<([\/]?)frame([^\>]*?)\>/si', '&lt;\\1frame\\2&gt;', $str ); $str = preg_replace ( '/]]\>/si', ']] >', $str ); } return $str; } ?><?php //对请求的字符串进行安全处理 /* $safestep 0 为不处理, 1 为禁止不安全HTML内容(javascript等), 2 完全禁止HTML内容,并替换部份不安全字符串(如:eval(、union、CONCAT(、--、等) */ function StringSafe($str, $safestep=-1){ $safestep = ($safestep > -1) ? $safestep : 1; if($safestep == 1){ $str = preg_replace("#script:#i", "script:", $str); $str = preg_replace("#<[\/]{0,1}(link|meta|ifr|fra|scr)[^>]*>#isU", '', $str); $str = preg_replace("#[\r\n\t ]{1,}#", ' ', $str); return $str; }else if($safestep == 2){ $str = addslashes(htmlspecialchars(stripslashes($str))); $str = preg_replace("#eval#i", 'eval', $str); $str = preg_replace("#union#i", 'union', $str); $str = preg_replace("#concat#i", 'concat', $str); $str = preg_replace("#--#", '--', $str); $str = preg_replace("#[\r\n\t ]{1,}#", ' ', $str); return $str; }else{ return $str; } } ?> <?php /** +---------------------------------------------------------- * 输出安全的html,用于过滤危险代码 +---------------------------------------------------------- * @access public +---------------------------------------------------------- * @param string $text 要处理的字符串 * @param mixed $tags 允许的标签列表,如 table|td|th|td +---------------------------------------------------------- * @return string +---------------------------------------------------------- */ static public function safeHtml($text, $tags = null) { $text = trim($text); //完全过滤注释 $text = preg_replace('/<!--?.*-->/','',$text); //完全过滤动态代码 $text = preg_replace('/<\?|\?'.'>/','',$text); //完全过滤js $text = preg_replace('/<script?.*\/script>/','',$text); $text = str_replace('[','&#091;',$text); $text = str_replace(']','&#093;',$text); $text = str_replace('|','&#124;',$text); //过滤换行符 $text = preg_replace('/\r?\n/','',$text); //br $text = preg_replace('/<br(\s\/)?'.'>/i','[br]',$text); $text = preg_replace('/(\[br\]\s*){10,}/i','[br]',$text); //过滤危险的属性,如:过滤on事件lang js while(preg_match('/(<[^><]+)(lang|on|action|background|codebase|dynsrc|lowsrc)[^><]+/i',$text,$mat)){ $text=str_replace($mat[0],$mat[1],$text); } while(preg_match('/(<[^><]+)(window\.|javascript:|js:|about:|file:|document\.|vbs:|cookie)([^><]*)/i',$text,$mat)){ $text=str_replace($mat[0],$mat[1].$mat[3],$text); } if( empty($allowTags) ) { $allowTags = self::$htmlTags['allow']; } //允许的HTML标签 $text = preg_replace('/<('.$allowTags.')( [^><\[\]]*)>/i','[\1\2]',$text); //过滤多余html if ( empty($banTag) ) { $banTag = self::$htmlTags['ban']; } $text = preg_replace('/<\/?('.$banTag.')[^><]*>/i','',$text); //过滤合法的html标签 while(preg_match('/<([a-z]+)[^><\[\]]*>[^><]*<\/\1>/i',$text,$mat)){ $text=str_replace($mat[0],str_replace('>',']',str_replace('<','[',$mat[0])),$text); } //转换引号 while(preg_match('/(\[[^\[\]]*=\s*)(\"|\')([^\2=\[\]]+)\2([^\[\]]*\])/i',$text,$mat)){ $text=str_replace($mat[0],$mat[1].'|'.$mat[3].'|'.$mat[4],$text); } //空属性转换 $text = str_replace('\'\'','||',$text); $text = str_replace('""','||',$text); //过滤错误的单个引号 while(preg_match('/\[[^\[\]]*(\"|\')[^\[\]]*\]/i',$text,$mat)){ $text=str_replace($mat[0],str_replace($mat[1],'',$mat[0]),$text); } //转换其它所有不合法的 < > $text = str_replace('<','&lt;',$text); $text = str_replace('>','&gt;',$text); $text = str_replace('"','&quot;',$text); //反转换 $text = str_replace('[','<',$text); $text = str_replace(']','>',$text); $text = str_replace('|','"',$text); //过滤多余空格 $text = str_replace(' ',' ',$text); return $text; } ?><?php function RemoveXSS($val) { // remove all non-printable characters. CR(0a) and LF(0b) and TAB(9) are allowed // this prevents some character re-spacing such as <java\0script> // 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 <IMG SRC=http://enenba.com/@avascript:alert('XSS')> $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);//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; $j < strlen($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; } ?>

end

内容版权声明:除非注明,否则皆为本站原创文章。

转载注明出处:https://www.heiqu.com/7789.html