!function(e){ if("object" == typeof exports && "undefined" != typeof module){ module.exports = e(); }else if ("function" == typeof define && define.amd){ define([], e); }else{ var r; r = "undefined" != typeof window ? window : "undefined" != typeof global ? global : "undefined" != typeof self ? self : this, r.html2json = e() }; }(function(){ // Regular Expressions for parsing tags and attributes var startTag = /^<([-A-Za-z0-9_]+)((?:\s+[a-zA-Z_:][-a-zA-Z0-9_:.]*(?:\s*=\s*(?:(?:"[^"]*")|(?:'[^']*')|[^>\s]+))?)*)\s*(\/?)>/, endTag = /^<\/([-A-Za-z0-9_]+)[^>]*>/, attr = /([a-zA-Z_:][-a-zA-Z0-9_:.]*)(?:\s*=\s*(?:(?:"((?:\\.|[^"])*)")|(?:'((?:\\.|[^'])*)')|([^>\s]+)))?/g; // Empty Elements - HTML 5 var empty = makeMap("area,base,basefont,br,col,frame,hr,img,input,link,meta,param,embed,command,keygen,source,track,wbr"); // Block Elements - HTML 5 var block = makeMap("a,address,article,applet,aside,audio,blockquote,button,canvas,center,dd,del,dir,div,dl,dt,fieldset,figcaption,figure,footer,form,frameset,h1,h2,h3,h4,h5,h6,header,hgroup,hr,iframe,ins,isindex,li,map,menu,noframes,noscript,object,ol,output,p,pre,section,script,table,tbody,td,tfoot,th,thead,tr,ul,video"); // Inline Elements - HTML 5 var inline = makeMap("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 = 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 element if (!stack.last() || !special[stack.last()]) { // Comment if (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("]*>"), function (all, text) { text = text.replace(/|/g, "$1$2"); if (handler.chars) handler.chars(text); return ""; }); parseEndTag("", stack.last()); } if (html == last) throw "Parse Error: " + html; last = html; } // Clean up any remaining tags parseEndTag(); 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 shop if (!tagName) var pos = 0; // Find the closest opened tag of the same type else for (var pos = stack.length - 1; pos >= 0; pos--) if (stack[pos] == tagName) break; if (pos >= 0) { // Close all the open elements, up the stack for (var i = stack.length - 1; i >= pos; i--) if (handler.end) handler.end(stack[i]); // Remove the open elements from the stack stack.length = pos; } } }; var HTMLtoXML = function (html) { var results = ""; HTMLParser(html, { start: function (tag, attrs, unary) { results += "<" + tag; for (var i = 0; i < attrs.length; i++) results += " " + attrs[i].name + '="' + attrs[i].escaped + '"'; results += ">"; }, end: function (tag) { results += ""; }, chars: function (text) { results += text; }, comment: function (text) { results += ""; } }); return results; }; var HTMLtoDOM = function (html, doc) { // There can be only one of these elements var one = makeMap("html,head,body,title"); // Enforce a structure for the document var 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"); } else doc = 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 structure if (!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 elements if (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 element var curParentNode = one.body; HTMLParser(html, { start: function (tagName, attrs, unary) { // If it's a pre-built element, then we can ignore // its construction if (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 parentNode curParentNode = 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; } function q(v) { return '"' + v + '"'; } function removeDOCTYPE(html) { return html .replace(/<\?xml.*\?>\n/, '') .replace(/\n/, '') .replace(/\n/, ''); } let html2json = function html2json(html) { html = removeDOCTYPE(html); var bufArray = []; var results = { node: 'root', child: [], }; HTMLParser(html, { start: function(tag, attrs, unary) { // node for this element var node = { node: 'element', tag: tag, }; if (attrs.length !== 0) { node.attr = attrs.reduce(function(pre, attr) { var name = attr.name; var value = attr.value; // has multi attibutes // make it array of attribute if (value.match(/ /)) { value = value.split(' '); } // if attr already exists // merge it if (pre[name]) { if (Array.isArray(pre[name])) { // already array, push to last pre[name].push(value); } else { // single value, make it array pre[name] = [pre[name], value]; } } else { // not exist, put it pre[name] = value; } return pre; }, {}); } if (unary) { // if this tag dosen't have end tag // like // add to parents var parent = bufArray[0] || results; if (parent.child === undefined) { parent.child = []; } parent.child.push(node); } else { bufArray.unshift(node); } }, end: function(tag) { // merge into parent tag var node = bufArray.shift(); if (node.tag !== tag) console.error('invalid state: mismatch end tag'); if (bufArray.length === 0) { results.child.push(node); } else { var parent = bufArray[0]; if (parent.child === undefined) { parent.child = []; } parent.child.push(node); } }, chars: function(text) { var node = { node: 'text', text: text, }; if (bufArray.length === 0) { results.child.push(node); } else { var parent = bufArray[0]; if (parent.child === undefined) { parent.child = []; } parent.child.push(node); } }, comment: function(text) { var node = { node: 'comment', text: text, }; var parent = bufArray[0]; if (parent.child === undefined) { parent.child = []; } parent.child.push(node); }, }); return results; }; return html2json; });