remove_xss
function remove_xss($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); // with a ; // @ @ 0{0,7} matches '0' zero to seven times $val = preg_replace('/(�{0,8}'.ord($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 .= '|(�{0,8}([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;}
strip_tags
strip_tags — 从字符串中去除 HTML 和 PHP 标记
说明
string strip_tags ( string $str [, string $allowable_tags ] )
该函数尝试返回给定的字符串 str 去除空字符、HTML 和 PHP 标记后的结果。它使用与函数 一样的机制去除标记
参数
str
输入字符串。
allowable_tags
使用可选的第二个参数指定不被去除的字符列表。
Note:
HTML 注释和 PHP 标签也会被去除。这里是硬编码处理的，所以无法通过 allowable_tags 参数进行改变。
返回值
返回处理后的字符串。
htmlspecialchars
htmlspecialchars — 将特殊字符转换为 HTML 实体
说明
string htmlspecialchars ( string
$string [, int $flags = ENT_COMPAT | ENT_HTML401 [, string $encoding = ini_get("default_charset") [, bool $double_encode = TRUE ]]] ) | & (& 符号) | & |
| " (双引号) | "，除非设置了 ENT_NOQUOTES |
| ' (单引号) | 设置了 ENT_QUOTES 后， ' (如果是 ENT_HTML401) ，或者 ' (如果是 ENT_XML1、 ENT_XHTML 或 ENT_HTML5)。 |
| < (小于) | < |
| > (大于) | > |
参数
string
待转换的 。
返回值
转换后的 。