var startTag = /^<([-A-Za-z0-9_]+)((?:\s+[a-zA-Z_:][-a-zA-Z0-9_:.]*(?:\s*=\s*(?:(?:"[^"]*")|(?:'[^']*')|[^>\s]+))?)*)\s*(\/?)>/; var endTag = /^<\/([-A-Za-z0-9_]+)[^>]*>/; var 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 // fixed by xxx 将 ins 标签从块级名单中移除 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,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'); function HTMLParser(html, handler) { var index; var chars; var match; var stack = []; var 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; } } } function makeMap(str) { var obj = {}; var items = str.split(','); for (var i = 0; i < items.length; i++) { obj[items[i]] = true; } return obj; } function removeDOCTYPE(html) { return html.replace(/<\?xml.*\?>\n/, '').replace(/\n/, '').replace(/\n/, ''); } function parseAttrs(attrs) { return attrs.reduce(function (pre, attr) { var value = attr.value; var name = attr.name; if (pre[name]) { pre[name] = pre[name] + " " + value; } else { pre[name] = value; } return pre; }, {}); } function parseHtml(html) { html = removeDOCTYPE(html); var stacks = []; var results = { node: 'root', children: [] }; HTMLParser(html, { start: function start(tag, attrs, unary) { var node = { name: tag }; if (attrs.length !== 0) { node.attrs = parseAttrs(attrs); } if (unary) { var parent = stacks[0] || results; if (!parent.children) { parent.children = []; } parent.children.push(node); } else { stacks.unshift(node); } }, end: function end(tag) { var node = stacks.shift(); if (node.name !== tag) console.error('invalid state: mismatch end tag'); if (stacks.length === 0) { results.children.push(node); } else { var parent = stacks[0]; if (!parent.children) { parent.children = []; } parent.children.push(node); } }, chars: function chars(text) { var str = text var textArray = [] for(let i=0;i