Php filters html tag attributes (with source code)

Php filters html tag attributes (with source code)

/** HTML Attribute Filter * Date: 2013-09-22 * Author: fdipzone * Ver: 1.0 * Edit: bbs.it-home.org * Func: * Public strip filter attributes * Public setAllow: Set the allowed attributes. * Special case for setting public setException * Public setIgnore: Set the ignored flag. * Private findElements: Search for elements to be processed * Private findAttributes search attributes * Private removeAttributes: remove attributes * Private isException: determines whether a special case exists. * Private createAttributes: create attributes * Private protect special character escape */ Class HtmlAttributeFilter {// class start Private $ _ str = ''; // source string Private $ _ allow = array (); // attributes that can be retained, for example, array ('id', 'class', 'title ') Private $ _ exception = array (); // special example: array ('a' => array ('href ', 'class '), 'span '=> array ('class ')) Private $ _ ignore = array (); // ignore filtered tags, for example, array ('span ', 'IMG ') /** Process HTML and filter attributes that are not retained * @ Param String $ str Source String * @ Return String */ Public function strip ($ str ){ $ This-> _ str = $ str; If (is_string ($ this-> _ str) & strlen ($ this-> _ str)> 0) {// judge a string $ This-> _ str = strtolower ($ this-> _ str); // Convert it to lowercase. $ Res = $ this-> findElements (); If (is_string ($ res )){ Return $ res; } $ Nodes = $ this-> findAttributes ($ res ); $ This-> removeAttributes ($ nodes ); } Return $ this-> _ str; } /** Set allowed attributes * @ Param Array $ param */ Public function setAllow ($ param = array ()){ $ This-> _ allow = $ param; } /** Set special cases * @ Param Array $ param */ Public function setException ($ param = array ()){ $ This-> _ exception = $ param; } /** Set the ignored flag * @ Param Array $ param */ Public function setIgnore ($ param = array ()){ $ This-> _ ignore = $ param; } /** Search for elements to be processed */ Private function findElements (){ $ Nodes = array (); Preg_match_all ("/<([^! \/\> \ N] +) ([^>] *)>/I ", $ this-> _ str, $ elements ); Foreach ($ elements [1] as $ el_key => $ element ){ If ($ elements [2] [$ el_key]) { $ Literal = $ elements [0] [$ el_key]; $ Element_name = $ elements [1] [$ el_key]; $ Attributes = $ elements [2] [$ el_key]; If (is_array ($ this-> _ ignore )&&! In_array ($ element_name, $ this-> _ ignore )){ $ Nodes [] = array ('literal' => $ literal, 'name' => $ element_name, 'bubuckets' => $ attributes ); } } } If (! $ Nodes [0]) { Return $ this-> _ str; } Else { Return $ nodes; } } /** Search for attributes * @ Param Array $ elements to be processed by nodes */ Private function findAttributes ($ nodes ){ Foreach ($ nodes as & $ node ){ Preg_match_all ("/([^ =] +) \ s * = \ s * [\" | '] {0, 1} ([^ \ "'] *) [\ "| '] {0, 1}/I", $ node ['bubuckets'], $ attributes ); If ($ attributes [1]) { Foreach ($ attributes [1] as $ att_key => $ att ){ $ Literal = $ attributes [0] [$ att_key]; $ Attribute_name = $ attributes [1] [$ att_key]; $ Value = $ attributes [2] [$ att_key]; $ Atts [] = array ('literal' => $ literal, 'name' => $ attribute_name, 'value' => $ value ); } } Else { $ Node ['bubuckets'] = null; } $ Node ['bubuckets'] = $ atts; Unset ($ atts ); } Return $ nodes; } /** Remove attributes * @ Param Array $ elements to be processed by nodes */ Private function removeAttributes ($ nodes ){ Foreach ($ nodes as $ node ){ $ Node_name = $ node ['name']; $ New_attributes = ''; If (is_array ($ node ['bubuckets']) { Foreach ($ node ['buckets'] as $ attribute ){ If (is_array ($ this-> _ allow) & in_array ($ attribute ['name'], $ this-> _ allow )) | $ this-> isException ($ node_name, $ attribute ['name'], $ this-> _ exception )){ $ New_attributes = $ this-> createAttributes ($ new_attributes, $ attribute ['name'], $ attribute ['value']); } } } $ Replacement = ($ new_attributes )? "<$ Node_name $ new_attributes>": "<$ node_name> "; $ This-> _ str = preg_replace ('/'. $ this-> protect ($ node ['literal']). '/', $ replacement, $ this-> _ str ); } } /** Determine whether a special case exists * @ Param String $ element_name element name * @ Param String $ attribute_name attribute name * @ Param Array $ special exceptions * @ Return boolean */ Private function isException ($ element_name, $ attribute_name, $ exceptions ){ If (array_key_exists ($ element_name, $ this-> _ exception )){ If (in_array ($ attribute_name, $ this-> _ exception [$ element_name]) { Return true; } } Return false; } /** Create attributes * @ Param String $ new_attributes * @ Param String $ name * @ Param String $ value * @ Return String */ Private function createAttributes ($ new_attributes, $ name, $ value ){ If ($ new_attributes ){ $ New_attributes. = ""; } $ New_attributes. = "$ name = \" $ value \""; Return $ new_attributes; } /** Escape special characters * @ Param String $ str Source String * @ Return String */ Private function protect ($ str ){ $ Conversions = array ( "^" => "\ ^ ", "[" => "\[", "." => "\.", "$" => "\ $ ", "{" => "\{", "*" => "\*", "(" => "\(", "\\" => "\\\\", "/" => "\/", "+" => "\ + ", ")" => "\)", "|" => "\ | ", "? "=> "\? ", "<" => "\ <", ">" => "\>" ); Return strtr ($ str, $ conversions ); } } // Class end ?> 2. Demo Require ('htmlattributefilter. class. php '); $ Str =' Yuna Love Want to knowYES '; $ Obj = new HtmlAttributeFilter (); // Allow the id attribute $ Obj-> setAllow (array ('id ')); $ Obj-> setException (array ( 'A' => array ('href '), // a tag allows special cases with the href attribute 'Ul '=> array ('class') // The ul tag allows special class attribute exceptions. )); // The img label is ignored and no attributes are filtered. $ Obj-> setIgnore (array ('IMG ')); Echo 'source str: '; Echo htmlspecialchars ($ str ).' '; Echo 'filter str: '; Echo htmlspecialchars ($ obj-> strip ($ str )); ?> Appendix: php source code used to filter html tag attribute classes