| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388 | /* * HTML5 Parser By Sam Blowes * * Designed for HTML5 documents * * Original code by John Resig (ejohn.org) * http://ejohn.org/blog/pure-javascript-html-parser/ * Original code by Erik Arvidsson, Mozilla Public License * http://erik.eae.net/simplehtmlparser/simplehtmlparser.js * * ---------------------------------------------------------------------------- * License * ---------------------------------------------------------------------------- * * This code is triple licensed using Apache Software License 2.0, * Mozilla Public License or GNU Public License * * //////////////////////////////////////////////////////////////////////////// * * Licensed under the Apache License, Version 2.0 (the "License"); you may not * use this file except in compliance with the License.  You may obtain a copy * of the License at http://www.apache.org/licenses/LICENSE-2.0 * * //////////////////////////////////////////////////////////////////////////// * * The contents of this file are subject to the Mozilla Public License * Version 1.1 (the "License"); you may not use this file except in * compliance with the License. You may obtain a copy of the License at * http://www.mozilla.org/MPL/ * * Software distributed under the License is distributed on an "AS IS" * basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See the * License for the specific language governing rights and limitations * under the License. * * The Original Code is Simple HTML Parser. * * The Initial Developer of the Original Code is Erik Arvidsson. * Portions created by Erik Arvidssson are Copyright (C) 2004. All Rights * Reserved. * * //////////////////////////////////////////////////////////////////////////// * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version 2 * of the License, or (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA. * * ---------------------------------------------------------------------------- * Usage * ---------------------------------------------------------------------------- * * // 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); * */// Regular Expressions for parsing tags and attributesvar 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 5var 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 5var 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('<!--') == 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('([\\s\\S]*?)<\/' + stack.last() + '[^>]*>'), function (all, text) {        text = text.replace(/<!--([\s\S]*?)-->|<!\[CDATA\[([\s\S]*?)]]>/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(/<!doctype.*>\n/, '').replace(/<!DOCTYPE.*>\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 convertStyleStringToJSON(styleString) {  var styles = styleString.split(";"); // 通过分号将样式字符串分割为多个样式声明  var result = {};  styles.forEach(function(style) {    var styleParts = style.split(":"); // 通过冒号将样式声明分割为属性和值    var property = styleParts[0].trim();    var value = styleParts[1] && styleParts[1].trim();    if (property && value) {      result[property] = value; // 将属性和值添加到结果对象中    }  });  return result;}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);		node.styles = node.attrs.style ? convertStyleStringToJSON(node.attrs.style) : {}      }		if(!node.type) {	  if(inline[node.name] && node.name !== 'img' ) {		node.type = 'text';		if(node.name == 'br') {			node.text = '\n'		} else if(node.name == 'strong'){			node.styles.fontWeight = 'bold'		}	  } else if(node.name == 'img'){		 node.type = 'image' 		 node.src =  node.attrs.src	  } else {		   node.type = 'view' 		   if(['h1','h2','h3','h4','h5','h6'].includes(node.name)) {			   node.styles.fontWeight = 'bold'		   }	  }	}		      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);      }	  const isTextBox = node.children && node.children.length > 1 && node.children.every(child => {		  return ['text','image'].includes(child.type)	  })	  if(isTextBox) {		  node.type = 'textBox'	  }    },    chars: function chars(text) {      var node = {        type: 'text',        text: text      };      if (stacks.length === 0) {        results.children.push(node);      } else {        var parent = stacks[0];        if (!parent.children) {          parent.children = [];        }        parent.children.push(node);      }    },    comment: function comment(text) {      var node = {        node: 'comment',        text: text      };      var parent = stacks[0];      if (!parent.children) {        parent.children = [];      }      parent.children.push(node);    }  });  return results.children;}export default parseHtml;
 |