/** HTML Parser By John Resig (ejohn.org)* Original code by Erik Arvidsson, Mozilla Public License* http://erik.eae.net/simplehtmlparser/simplehtmlparser.js** // Use like so:* HTMLParser(htmlString, {*     start: function(tag, attrs, unary) {},*     end: function(tag) {},*     chars: function(text) {},*     comment: function(text) {}* });** // or to get an XML string:* HTMLtoXML(htmlString);** // or to get an XML DOM Document* HTMLtoDOM(htmlString);** // or to inject into an existing document/DOM node* HTMLtoDOM(htmlString, document);* HTMLtoDOM(htmlString, document.body);**/(function(){// Regular Expressions for parsing tags and attributesvar startTag = /^<([-A-Za-z0-9_]+)((?:\s+[-:A-Za-z0-9_]+(?:\s*=\s*(?:(?:"[^"]*")|(?:'[^']*')|[^>\s]+))?)*)\s*(\/?)>/,endTag = /^<\/([-A-Za-z0-9_]+)[^>]*>/,attr = /([-:A-Za-z0-9_]+)(?:\s*=\s*(?:(?:"((?:\\.|[^"])*)")|(?:'((?:\\.|[^'])*)')|([^>\s]+)))?/g;// Empty Elements - HTML 4.01var empty = makeMap("area,base,basefont,br,col,frame,hr,img,input,isindex,link,meta,param,embed");// Block Elements - HTML 4.01var block = makeMap("address,applet,blockquote,button,center,dd,del,dir,div,dl,dt,fieldset,form,frameset,hr,iframe,isindex,li,map,menu,noframes,noscript,object,ol,p,pre,script,table,tbody,td,tfoot,th,thead,tr,ul");// Inline Elements - HTML 4.01var inline = makeMap("a,abbr,acronym,applet,b,basefont,bdo,big,br,button,cite,code,del,dfn,em,font,i,iframe,img,input,ins,kbd,label,map,object,q,s,samp,script,select,small,span,strike,strong,sub,sup,textarea,tt,u,var");// Elements that you can, intentionally, leave open// (and which close themselves)var closeSelf = makeMap("colgroup,dd,dt,li,options,p,td,tfoot,th,thead,tr");// Attributes that have their values filled in disabled="disabled"var fillAttrs = makeMap("checked,compact,declare,defer,disabled,ismap,multiple,nohref,noresize,noshade,nowrap,readonly,selected");// Special Elements (can contain anything)var special = makeMap("script,style");var HTMLParser = this.HTMLParser = function( html, handler ) {var index, chars, match, stack = [], last = html;stack.last = function(){return this[ this.length - 1 ];};while ( html ) {chars = true;// Make sure we're not in a script or style elementif ( !stack.last() || !special[ stack.last() ] ) {// Commentif ( html.indexOf("<!--") == 0 ) {index = html.indexOf("-->");if ( index >= 0 ) {if ( handler.comment )handler.comment( html.substring( 4, index ) );html = html.substring( index + 3 );chars = false;}// end tag} else if ( html.indexOf("</") == 0 ) {match = html.match( endTag );if ( match ) {html = html.substring( match[0].length );match[0].replace( endTag, parseEndTag );chars = false;}// start tag} else if ( html.indexOf("<") == 0 ) {match = html.match( startTag );if ( match ) {html = html.substring( match[0].length );match[0].replace( startTag, parseStartTag );chars = false;}}if ( chars ) {index = html.indexOf("<");var text = index < 0 ? html : html.substring( 0, index );html = index < 0 ? "" : html.substring( index );if ( handler.chars )handler.chars( text );}} else {html = html.replace(new RegExp("(.*)<\/" + stack.last() + "[^>]*>"), function(all, text){text = text.replace(/<!--(.*?)-->/g, "$1").replace(/<!\[CDATA\[(.*?)]]>/g, "$1");if ( handler.chars )handler.chars( text );return "";});parseEndTag( "", stack.last() );}if ( html == last )throw "Parse Error: " + html;last = html;}// Clean up any remaining tagsparseEndTag();function parseStartTag( tag, tagName, rest, unary ) {tagName = tagName.toLowerCase();if ( block[ tagName ] ) {while ( stack.last() && inline[ stack.last() ] ) {parseEndTag( "", stack.last() );}}if ( closeSelf[ tagName ] && stack.last() == tagName ) {parseEndTag( "", tagName );}unary = empty[ tagName ] || !!unary;if ( !unary )stack.push( tagName );if ( handler.start ) {var attrs = [];rest.replace(attr, function(match, name) {var value = arguments[2] ? arguments[2] :arguments[3] ? arguments[3] :arguments[4] ? arguments[4] :fillAttrs[name] ? name : "";attrs.push({name: name,value: value,escaped: value.replace(/(^|[^\\])"/g, '$1\\\"') //"});});if ( handler.start )handler.start( tagName, attrs, unary );}}function parseEndTag( tag, tagName ) {// If no tag name is provided, clean shopif ( !tagName )var pos = 0;// Find the closest opened tag of the same typeelse{tagName = tagName.toLowerCase();for ( var pos = stack.length - 1; pos >= 0; pos-- )if ( stack[ pos ] == tagName )break;}if ( pos >= 0 ) {// Close all the open elements, up the stackfor ( var i = stack.length - 1; i >= pos; i-- )if ( handler.end )handler.end( stack[ i ] );// Remove the open elements from the stackstack.length = pos;}}};this.HTMLtoXML = function( html ) {var r###lts = "";HTMLParser(html, {start: function( tag, attrs, unary ) {r###lts += "<" + tag;for ( var i = 0; i < attrs.length; i++ )r###lts += " " + attrs[i].name + '="' + attrs[i].escaped + '"';r###lts += (unary ? "/" : "") + ">";},end: function( tag ) {r###lts += "</" + tag + ">";},chars: function( text ) {r###lts += text;},comment: function( text ) {r###lts += "<!--" + text + "-->";}});return r###lts;};this.HTMLtoDOM = function( html, doc ) {// There can be only one of these elementsvar one = makeMap("html,head,body,title");// Enforce a structure for the documentvar structure = {link: "head",base: "head"};if ( !doc ) {if ( typeof DOMDocument != "undefined" )doc = new DOMDocument();else if ( typeof document != "undefined" && document.implementation && document.implementation.createDocument )doc = document.implementation.createDocument("", "", null);else if ( typeof ActiveX != "undefined" )doc = new ActiveXObject("Msxml.DOMDocument");} elsedoc = doc.ownerDocument ||doc.getOwnerDocument && doc.getOwnerDocument() ||doc;var elems = [],documentElement = doc.documentElement ||doc.getDocumentElement && doc.getDocumentElement();// If we're dealing with an empty document then we// need to pre-populate it with the HTML document structureif ( !documentElement && doc.createElement ) (function(){var html = doc.createElement("html");var head = doc.createElement("head");head.appendChild( doc.createElement("title") );html.appendChild( head );html.appendChild( doc.createElement("body") );doc.appendChild( html );})();// Find all the unique elementsif ( doc.getElementsByTagName )for ( var i in one )one[ i ] = doc.getElementsByTagName( i )[0];// If we're working with a document, inject contents into// the body elementvar curParentNode = one.body;HTMLParser( html, {start: function( tagName, attrs, unary ) {// If it's a pre-built element, then we can ignore// its constructionif ( one[ tagName ] ) {curParentNode = one[ tagName ];if ( !unary ) {elems.push( curParentNode );}return;}var elem = doc.createElement( tagName );for ( var attr in attrs )elem.setAttribute( attrs[ attr ].name, attrs[ attr ].value );if ( structure[ tagName ] && typeof one[ structure[ tagName ] ] != "boolean" )one[ structure[ tagName ] ].appendChild( elem );else if ( curParentNode && curParentNode.appendChild )curParentNode.appendChild( elem );if ( !unary ) {elems.push( elem );curParentNode = elem;}},end: function( tag ) {elems.length -= 1;// Init the new parentNodecurParentNode = elems[ elems.length - 1 ];},chars: function( text ) {curParentNode.appendChild( doc.createTextNode( text ) );},comment: function( text ) {// create comment node}});return doc;};function makeMap(str){var obj = {}, items = str.split(",");for ( var i = 0; i < items.length; i++ )obj[ items[i] ] = true;return obj;}})();