是否存在一种万能函数，可以很好地为SQL注入和XSS攻击清除用户输入，同时仍然允许某些类型的HTML标记?
当前回答
PHP现在有了新的不错的filter_input函数，例如，现在有了内置的FILTER_VALIDATE_EMAIL类型，可以将您从寻找“最终的电子邮件正则表达式”中解放出来
我自己的过滤器类(使用JavaScript突出显示有错误的字段)可以由ajax请求或普通表单post发起。(见下面的例子) <？ ／** *猪肉成型验证器。通过正则表达式验证字段，并可以清除它们。使用PHP filter_var内置函数和额外的正则表达式 *包装猪肉 * /
/**
* Pork.FormValidator
* Validates arrays or properties by setting up simple arrays.
* Note that some of the regexes are for dutch input!
* Example:
*
* $validations = array('name' => 'anything','email' => 'email','alias' => 'anything','pwd'=>'anything','gsm' => 'phone','birthdate' => 'date');
* $required = array('name', 'email', 'alias', 'pwd');
* $sanitize = array('alias');
*
* $validator = new FormValidator($validations, $required, $sanitize);
*
* if($validator->validate($_POST))
* {
* $_POST = $validator->sanitize($_POST);
* // now do your saving, $_POST has been sanitized.
* die($validator->getScript()."<script type='text/javascript'>alert('saved changes');</script>");
* }
* else
* {
* die($validator->getScript());
* }
*
* To validate just one element:
* $validated = new FormValidator()->validate('blah@bla.', 'email');
*
* To sanitize just one element:
* $sanitized = new FormValidator()->sanitize('<b>blah</b>', 'string');
*
* @package pork
* @author SchizoDuckie
* @copyright SchizoDuckie 2008
* @version 1.0
* @access public
*/
class FormValidator
{
public static $regexes = Array(
'date' => "^[0-9]{1,2}[-/][0-9]{1,2}[-/][0-9]{4}\$",
'amount' => "^[-]?[0-9]+\$",
'number' => "^[-]?[0-9,]+\$",
'alfanum' => "^[0-9a-zA-Z ,.-_\\s\?\!]+\$",
'not_empty' => "[a-z0-9A-Z]+",
'words' => "^[A-Za-z]+[A-Za-z \\s]*\$",
'phone' => "^[0-9]{10,11}\$",
'zipcode' => "^[1-9][0-9]{3}[a-zA-Z]{2}\$",
'plate' => "^([0-9a-zA-Z]{2}[-]){2}[0-9a-zA-Z]{2}\$",
'price' => "^[0-9.,]*(([.,][-])|([.,][0-9]{2}))?\$",
'2digitopt' => "^\d+(\,\d{2})?\$",
'2digitforce' => "^\d+\,\d\d\$",
'anything' => "^[\d\D]{1,}\$"
);
private $validations, $sanatations, $mandatories, $errors, $corrects, $fields;
public function __construct($validations=array(), $mandatories = array(), $sanatations = array())
{
$this->validations = $validations;
$this->sanitations = $sanitations;
$this->mandatories = $mandatories;
$this->errors = array();
$this->corrects = array();
}
/**
* Validates an array of items (if needed) and returns true or false
*
*/
public function validate($items)
{
$this->fields = $items;
$havefailures = false;
foreach($items as $key=>$val)
{
if((strlen($val) == 0 || array_search($key, $this->validations) === false) && array_search($key, $this->mandatories) === false)
{
$this->corrects[] = $key;
continue;
}
$result = self::validateItem($val, $this->validations[$key]);
if($result === false) {
$havefailures = true;
$this->addError($key, $this->validations[$key]);
}
else
{
$this->corrects[] = $key;
}
}
return(!$havefailures);
}
/**
*
* Adds unvalidated class to thos elements that are not validated. Removes them from classes that are.
*/
public function getScript() {
if(!empty($this->errors))
{
$errors = array();
foreach($this->errors as $key=>$val) { $errors[] = "'INPUT[name={$key}]'"; }
$output = '$$('.implode(',', $errors).').addClass("unvalidated");';
$output .= "new FormValidator().showMessage();";
}
if(!empty($this->corrects))
{
$corrects = array();
foreach($this->corrects as $key) { $corrects[] = "'INPUT[name={$key}]'"; }
$output .= '$$('.implode(',', $corrects).').removeClass("unvalidated");';
}
$output = "<script type='text/javascript'>{$output} </script>";
return($output);
}
/**
*
* Sanitizes an array of items according to the $this->sanitations
* sanitations will be standard of type string, but can also be specified.
* For ease of use, this syntax is accepted:
* $sanitations = array('fieldname', 'otherfieldname'=>'float');
*/
public function sanitize($items)
{
foreach($items as $key=>$val)
{
if(array_search($key, $this->sanitations) === false && !array_key_exists($key, $this->sanitations)) continue;
$items[$key] = self::sanitizeItem($val, $this->validations[$key]);
}
return($items);
}
/**
*
* Adds an error to the errors array.
*/
private function addError($field, $type='string')
{
$this->errors[$field] = $type;
}
/**
*
* Sanitize a single var according to $type.
* Allows for static calling to allow simple sanitization
*/
public static function sanitizeItem($var, $type)
{
$flags = NULL;
switch($type)
{
case 'url':
$filter = FILTER_SANITIZE_URL;
break;
case 'int':
$filter = FILTER_SANITIZE_NUMBER_INT;
break;
case 'float':
$filter = FILTER_SANITIZE_NUMBER_FLOAT;
$flags = FILTER_FLAG_ALLOW_FRACTION | FILTER_FLAG_ALLOW_THOUSAND;
break;
case 'email':
$var = substr($var, 0, 254);
$filter = FILTER_SANITIZE_EMAIL;
break;
case 'string':
default:
$filter = FILTER_SANITIZE_STRING;
$flags = FILTER_FLAG_NO_ENCODE_QUOTES;
break;
}
$output = filter_var($var, $filter, $flags);
return($output);
}
/**
*
* Validates a single var according to $type.
* Allows for static calling to allow simple validation.
*
*/
public static function validateItem($var, $type)
{
if(array_key_exists($type, self::$regexes))
{
$returnval = filter_var($var, FILTER_VALIDATE_REGEXP, array("options"=> array("regexp"=>'!'.self::$regexes[$type].'!i'))) !== false;
return($returnval);
}
$filter = false;
switch($type)
{
case 'email':
$var = substr($var, 0, 254);
$filter = FILTER_VALIDATE_EMAIL;
break;
case 'int':
$filter = FILTER_VALIDATE_INT;
break;
case 'boolean':
$filter = FILTER_VALIDATE_BOOLEAN;
break;
case 'ip':
$filter = FILTER_VALIDATE_IP;
break;
case 'url':
$filter = FILTER_VALIDATE_URL;
break;
}
return ($filter === false) ? false : filter_var($var, $filter) !== false ? true : false;
}
}
当然，请记住，您也需要根据您使用的db类型进行sql查询转义(mysql_real_escape_string()对于sql server来说是无用的)。您可能希望在适当的应用程序层(如ORM)自动处理这个问题。另外，如上所述:对于输出到html使用其他php专用函数，如htmlspecialchars;)
真正允许HTML输入的类和/或标签依赖于一个专用的xss验证包。不要编写自己的正则表达式来解析html !
其他回答
不。你不能在没有任何上下文的情况下过滤数据。有时你想把SQL查询作为输入，有时你想把HTML作为输入。
您需要筛选白名单上的输入——确保数据符合您所期望的某些规范。然后，您需要在使用它之前对它进行转义，这取决于您使用它的上下文。
为SQL转义数据(防止SQL注入)的过程与为(X)HTML转义数据(防止XSS)的过程非常不同。
PHP 5.2引入了filter_var函数。
它支持大量的SANITIZE, VALIDATE过滤器。
避免在清理输入和转义数据时出错的最简单方法是使用Symfony、Nette等PHP框架或该框架的一部分(模板引擎、数据库层、ORM)。
像Twig或Latte这样的模板引擎默认有输出转义-如果你根据上下文(HTML或Javascript部分的网页)正确地转义了你的输出，你不必手动解决。
框架会自动清理输入，你不应该直接使用$_POST， $_GET或$_SESSION变量，而是通过路由，会话处理等机制。
对于数据库(模型)层，有像Doctrine这样的ORM框架或围绕PDO的包装器，如Nette database。
你可以在这里阅读更多关于它的内容-什么是软件框架?
没有万能函数，因为有多个关注点需要解决。
SQL注入——如今，一般来说，每个PHP项目都应该通过PHP数据对象(PDO)使用准备好的语句作为最佳实践，以防止错误引用以及针对注入的全功能解决方案。这也是最灵活和安全的方式来访问您的数据库。
检查(唯一正确的)PDO教程几乎所有你需要知道的关于PDO。(衷心感谢顶级SO贡献者@YourCommonSense，为这个主题提供了很棒的资源。)
XSS -消毒数据的方式…
HTML Purifier has been around a long time and is still actively updated. You can use it to sanitize malicious input, while still allowing a generous & configurable whitelist of tags. Works great with many WYSIWYG editors, but it might be heavy for some use cases. In other instances, where we don't want to accept HTML/Javascript at all, I've found this simple function useful (and has passed multiple audits against XSS): /* Prevent XSS input */ function sanitizeXSS () { $_GET = filter_input_array(INPUT_GET, FILTER_SANITIZE_STRING); $_POST = filter_input_array(INPUT_POST, FILTER_SANITIZE_STRING); $_REQUEST = (array)$_POST + (array)$_GET + (array)$_REQUEST; }
XSS -在输出时消毒数据…除非你保证数据在添加到你的数据库之前被正确地消毒，否则你需要在显示给你的用户之前消毒它，我们可以利用这些有用的PHP函数:
当您调用echo或print来显示用户提供的值时，请使用htmlspecialchars，除非数据已经过适当的安全处理并允许显示HTML。 json_encode是一种从PHP向Javascript提供用户提供值的安全方法
您是否使用exec()或system()函数调用外部shell命令，或使用反勾运算符?如果是这样，除了SQL注入和XSS之外，您可能还需要解决一个额外的问题，即用户在您的服务器上运行恶意命令。如果您想转义整个命令或escapeshellarg来转义单个参数，则需要使用escapeshellcmd。
PHP现在有了新的不错的filter_input函数，例如，现在有了内置的FILTER_VALIDATE_EMAIL类型，可以将您从寻找“最终的电子邮件正则表达式”中解放出来
我自己的过滤器类(使用JavaScript突出显示有错误的字段)可以由ajax请求或普通表单post发起。(见下面的例子) <？ ／** *猪肉成型验证器。通过正则表达式验证字段，并可以清除它们。使用PHP filter_var内置函数和额外的正则表达式 *包装猪肉 * /
/**
* Pork.FormValidator
* Validates arrays or properties by setting up simple arrays.
* Note that some of the regexes are for dutch input!
* Example:
*
* $validations = array('name' => 'anything','email' => 'email','alias' => 'anything','pwd'=>'anything','gsm' => 'phone','birthdate' => 'date');
* $required = array('name', 'email', 'alias', 'pwd');
* $sanitize = array('alias');
*
* $validator = new FormValidator($validations, $required, $sanitize);
*
* if($validator->validate($_POST))
* {
* $_POST = $validator->sanitize($_POST);
* // now do your saving, $_POST has been sanitized.
* die($validator->getScript()."<script type='text/javascript'>alert('saved changes');</script>");
* }
* else
* {
* die($validator->getScript());
* }
*
* To validate just one element:
* $validated = new FormValidator()->validate('blah@bla.', 'email');
*
* To sanitize just one element:
* $sanitized = new FormValidator()->sanitize('<b>blah</b>', 'string');
*
* @package pork
* @author SchizoDuckie
* @copyright SchizoDuckie 2008
* @version 1.0
* @access public
*/
class FormValidator
{
public static $regexes = Array(
'date' => "^[0-9]{1,2}[-/][0-9]{1,2}[-/][0-9]{4}\$",
'amount' => "^[-]?[0-9]+\$",
'number' => "^[-]?[0-9,]+\$",
'alfanum' => "^[0-9a-zA-Z ,.-_\\s\?\!]+\$",
'not_empty' => "[a-z0-9A-Z]+",
'words' => "^[A-Za-z]+[A-Za-z \\s]*\$",
'phone' => "^[0-9]{10,11}\$",
'zipcode' => "^[1-9][0-9]{3}[a-zA-Z]{2}\$",
'plate' => "^([0-9a-zA-Z]{2}[-]){2}[0-9a-zA-Z]{2}\$",
'price' => "^[0-9.,]*(([.,][-])|([.,][0-9]{2}))?\$",
'2digitopt' => "^\d+(\,\d{2})?\$",
'2digitforce' => "^\d+\,\d\d\$",
'anything' => "^[\d\D]{1,}\$"
);
private $validations, $sanatations, $mandatories, $errors, $corrects, $fields;
public function __construct($validations=array(), $mandatories = array(), $sanatations = array())
{
$this->validations = $validations;
$this->sanitations = $sanitations;
$this->mandatories = $mandatories;
$this->errors = array();
$this->corrects = array();
}
/**
* Validates an array of items (if needed) and returns true or false
*
*/
public function validate($items)
{
$this->fields = $items;
$havefailures = false;
foreach($items as $key=>$val)
{
if((strlen($val) == 0 || array_search($key, $this->validations) === false) && array_search($key, $this->mandatories) === false)
{
$this->corrects[] = $key;
continue;
}
$result = self::validateItem($val, $this->validations[$key]);
if($result === false) {
$havefailures = true;
$this->addError($key, $this->validations[$key]);
}
else
{
$this->corrects[] = $key;
}
}
return(!$havefailures);
}
/**
*
* Adds unvalidated class to thos elements that are not validated. Removes them from classes that are.
*/
public function getScript() {
if(!empty($this->errors))
{
$errors = array();
foreach($this->errors as $key=>$val) { $errors[] = "'INPUT[name={$key}]'"; }
$output = '$$('.implode(',', $errors).').addClass("unvalidated");';
$output .= "new FormValidator().showMessage();";
}
if(!empty($this->corrects))
{
$corrects = array();
foreach($this->corrects as $key) { $corrects[] = "'INPUT[name={$key}]'"; }
$output .= '$$('.implode(',', $corrects).').removeClass("unvalidated");';
}
$output = "<script type='text/javascript'>{$output} </script>";
return($output);
}
/**
*
* Sanitizes an array of items according to the $this->sanitations
* sanitations will be standard of type string, but can also be specified.
* For ease of use, this syntax is accepted:
* $sanitations = array('fieldname', 'otherfieldname'=>'float');
*/
public function sanitize($items)
{
foreach($items as $key=>$val)
{
if(array_search($key, $this->sanitations) === false && !array_key_exists($key, $this->sanitations)) continue;
$items[$key] = self::sanitizeItem($val, $this->validations[$key]);
}
return($items);
}
/**
*
* Adds an error to the errors array.
*/
private function addError($field, $type='string')
{
$this->errors[$field] = $type;
}
/**
*
* Sanitize a single var according to $type.
* Allows for static calling to allow simple sanitization
*/
public static function sanitizeItem($var, $type)
{
$flags = NULL;
switch($type)
{
case 'url':
$filter = FILTER_SANITIZE_URL;
break;
case 'int':
$filter = FILTER_SANITIZE_NUMBER_INT;
break;
case 'float':
$filter = FILTER_SANITIZE_NUMBER_FLOAT;
$flags = FILTER_FLAG_ALLOW_FRACTION | FILTER_FLAG_ALLOW_THOUSAND;
break;
case 'email':
$var = substr($var, 0, 254);
$filter = FILTER_SANITIZE_EMAIL;
break;
case 'string':
default:
$filter = FILTER_SANITIZE_STRING;
$flags = FILTER_FLAG_NO_ENCODE_QUOTES;
break;
}
$output = filter_var($var, $filter, $flags);
return($output);
}
/**
*
* Validates a single var according to $type.
* Allows for static calling to allow simple validation.
*
*/
public static function validateItem($var, $type)
{
if(array_key_exists($type, self::$regexes))
{
$returnval = filter_var($var, FILTER_VALIDATE_REGEXP, array("options"=> array("regexp"=>'!'.self::$regexes[$type].'!i'))) !== false;
return($returnval);
}
$filter = false;
switch($type)
{
case 'email':
$var = substr($var, 0, 254);
$filter = FILTER_VALIDATE_EMAIL;
break;
case 'int':
$filter = FILTER_VALIDATE_INT;
break;
case 'boolean':
$filter = FILTER_VALIDATE_BOOLEAN;
break;
case 'ip':
$filter = FILTER_VALIDATE_IP;
break;
case 'url':
$filter = FILTER_VALIDATE_URL;
break;
}
return ($filter === false) ? false : filter_var($var, $filter) !== false ? true : false;
}
}
当然，请记住，您也需要根据您使用的db类型进行sql查询转义(mysql_real_escape_string()对于sql server来说是无用的)。您可能希望在适当的应用程序层(如ORM)自动处理这个问题。另外，如上所述:对于输出到html使用其他php专用函数，如htmlspecialchars;)
真正允许HTML输入的类和/或标签依赖于一个专用的xss验证包。不要编写自己的正则表达式来解析html !
