PHP常用工具函数小结【移除XSS攻击、UTF8与GBK编码转换等】

这篇文章主要介绍了PHP常用工具函数,结合实例形式总结分析了php移除XSS攻击、以及php操作UTF8与GBK编码转换等相关操作自定义函数实现方法,需要的朋友可以参考下。

本文实例总结了PHP常用工具函数,分享给大家供大家参考,具体如下:

移除XSS攻击脚本

  1. function RemoveXSS($val) {
  2. // remove all non-printable characters. CR(0a) and LF(0b) and TAB(9) are allowed
  3. // this prevents some character re-spacing such as <java\0script>
  4. // note that you have to handle splits with \n, \r, and \t later since they *are* allowed in some inputs
  5. $val = preg_replace('/([\x00-\x08,\x0b-\x0c,\x0e-\x19])/', '', $val);
  6. // straight replacements, the user should never need these since they're normal characters
  7. // this prevents like <IMG SRC=@avascript:alert('XSS')>
  8. $search = 'abcdefghijklmnopqrstuvwxyz';
  9. $search .= 'ABCDEFGHIJKLMNOPQRSTUVWXYZ';
  10. $search .= '1234567890!@#$%^&*()';
  11. $search .= '~`";:?+/={}[]-_|\'\\';
  12. for ($i = 0; $i < strlen($search); $i++) {
  13. // ;? matches the ;, which is optional
  14. // 0{0,7} matches any padded zeros, which are optional and go up to 8 chars
  15. // @ @ search for the hex values
  16. $val = preg_replace('/(&#[xX]0{0,8}'.dechex(ord($search[$i])).';?)/i', $search[$i], $val); // with a ;
  17. // @ @ 0{0,7} matches '0' zero to seven times
  18. $val = preg_replace('/(&#0{0,8}'.ord($search[$i]).';?)/', $search[$i], $val); // with a ;
  19. }
  20. // now the only remaining whitespace attacks are \t, \n, and \r
  21. $ra1 = array('javascript', 'vbscript', 'expression', 'applet', 'meta', 'xml', 'blink', 'link', 'style', 'script', 'embed', 'object', 'iframe', 'frame', 'frameset', 'ilayer', 'layer', 'bgsound', 'title', 'base');
  22. $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');
  23. $ra = array_merge($ra1, $ra2);
  24. $found = true; // keep replacing as long as the previous round replaced something
  25. while ($found == true) {
  26. $val_before = $val;
  27. for ($i = 0; $i < sizeof($ra); $i++) {
  28. $pattern = '/';
  29. for ($j = 0; $j < strlen($ra[$i]); $j++) {
  30. if ($j > 0) {
  31. $pattern .= '(';
  32. $pattern .= '(&#[xX]0{0,8}([9ab]);)';
  33. $pattern .= '|';
  34. $pattern .= '|(&#0{0,8}([9|10|13]);)';
  35. $pattern .= ')*';
  36. }
  37. $pattern .= $ra[$i][$j];
  38. }
  39. $pattern .= '/i';
  40. $replacement = substr($ra[$i], 0, 2).'<x>'.substr($ra[$i], 2); // add in <> to nerf the tag
  41. $val = preg_replace($pattern, $replacement, $val); // filter out the hex tags
  42. if ($val_before == $val) {
  43. // no replacements were made, so exit the loop
  44. $found = false;
  45. }
  46. }
  47. }
  48. return $val;
  49. }

GBK转UTF8

  1. function GBKtoUTF8($str)
  2. {
  3. if(is_array($str))
  4. {
  5. foreach ($str as &$value)
  6. {
  7. $value = GBKtoUTF8($value);
  8. }
  9. return $str;
  10. }elseif(is_string($str)){
  11. $str = iconv("GB18030", "UTF-8//IGNORE", $str);
  12. return $str;
  13. }else{
  14. return $str;
  15. }
  16. }

UTF8转GBK

  1. function UTF8toGBK(&$str)
  2. {
  3. if(is_array($str))
  4. {
  5. foreach ($str as &$value)
  6. {
  7. $value = UTF8toGBK($value);
  8. }
  9. return $str;
  10. }elseif (is_string($str)){
  11. $str = iconv("UTF-8", "GB18030//IGNORE", $str);
  12. return $str;
  13. }else{
  14. return $str;
  15. }
  16. }