JAVA解析XML文件(DOM,SAX,JDOM,DOM4j附代码实现)

1、解析XML主要有四种方式

1.DOM方式解析XML（与平台无关,JAVA提供,一次性加载XML文件内容,形成树结构,不适用于大文件）
2.SAX方式解析XML（基于事件驱动,逐条解析,适用于只处理XML数据,不易编码）
3.JDOM方式解析XML（使用具体类而不使用接口）
4.DOM4j方式解析XML（推荐）

2、代码实现

（1）XML文件

 <?xml version="1.0" encoding="UTF-8"?>
 <bookstore>
     <book id="1">
         <name>平凡的世界</name>
         <author>路遥</author>
         <year>2017</year>
         <price></price>
     </book>
     <book id="2">
         <name>百年孤独</name>
         <author>加西亚·马尔克斯</author>
         <year>1967</year>
         <price>80</price>
     </book>
     <book id="3">
         <name>程序员的修炼之道</name>
         <author>安德鲁·亨特、大卫·托马斯</author>
         <year>2011</year>
         <price>156</price>
     </book>
 </bookstore>

（2）XML对应的Bean类

 public class Book {   

     private int id;
     private String name;
     private String author;
     private int year;
     private double price;  

     /**
      * @return the id
      */
     public int getId() {
         return id;
     }
     /**
      * @param id the id to set
      */
     public void setId(int id) {
         this.id = id;
     }
     /**
      * @return the name
      */
     public String getName() {
         return name;
     }
     /**
      * @param name the name to set
      */
     public void setName(String name) {
         this.name = name;
     }
     /**
      * @return the author
      */
     public String getAuthor() {
         return author;
     }
     /**
      * @param author the author to set
      */
     public void setAuthor(String author) {
         this.author = author;
     }
     /**
      * @return the year
      */
     public int getYear() {
         return year;
     }
     /**
      * @param year the year to set
      */
     public void setYear(int year) {
         this.year = year;
     }
     /**
      * @return the price
      */
     public double getPrice() {
         return price;
     }
     /**
      * @param price the price to set
      */
     public void setPrice(double price) {
         this.price = price;
     }  

     @Override
     public String toString() {
         return "Book [id=" + id + ", name=" + name + ", author=" + author + ", year=" + year + ", price=" + price + "]";
     }  

 }  

3、XML解析

（1）DOM方式解析XML

 public class ReadxmlByDom {
     private static DocumentBuilderFactory dbFactory = ;
     private static DocumentBuilder db = ;
     private static Document document = ;
     private static List<Book> books = ;
     static{
         try {
             dbFactory = DocumentBuilderFactory.newInstance();
             db = dbFactory.newDocumentBuilder();
         } catch (ParserConfigurationException e) {
             e.printStackTrace();
         }
     }  

     public static List<Book> getBooks(String fileName) throws Exception{
         //将给定 URI 的内容解析为一个 XML 文档,并返回Document对象
         document = db.parse(fileName);
         //按文档顺序返回包含在文档中且具有给定标记名称的所有 Element 的 NodeList
         NodeList bookList = document.getElementsByTagName("book");
         books = new ArrayList<Book>();
         //遍历books
         for(int i=0;i<bookList.getLength();i++){
             Book book = new Book();
             //获取第i个book结点
             org.w3c.dom.Node node = bookList.item(i);
             //获取第i个book的所有属性
             NamedNodeMap namedNodeMap = node.getAttributes();
             //获取已知名为id的属性值
             String id = namedNodeMap.getNamedItem("id").getTextContent();//System.out.println(id);
             book.setId(Integer.parseInt(id));  

             //获取book结点的子节点,包含了Test类型的换行
             NodeList cList = node.getChildNodes();//System.out.println(cList.getLength());9  

             //将一个book里面的属性加入数组
             ArrayList<String> contents = new ArrayList<>();
             for(int j=1;j<cList.getLength();j+=2){  

                 org.w3c.dom.Node cNode = cList.item(j);
                 String content = cNode.getFirstChild().getTextContent();
                 contents.add(content);
                 //System.out.println(contents);
             }  

             book.setName(contents.get(0));
             book.setAuthor(contents.get(1));
             book.setYear(Integer.parseInt(contents.get(2)));
             book.setPrice(Double.parseDouble(contents.get(3)));
             books.add(book);
         }  

         return books;  

     }  

     public static void main(String args[]){
         String fileName = "src/res/books.xml";
         try {
             List<Book> list = ReadxmlByDom.getBooks(fileName);
             for(Book book :list){
                 System.out.println(book);
             }
         } catch (Exception e) {
             // TODO Auto-generated catch block
             e.printStackTrace();
         }
     }  

 }  

（2）SAX方式解析XML（比较麻烦，需要配置一个handler处理器）

DefaultHandler处理器

 /**
  * 用SAX解析xml文件时需要的handler
  */
 public class SAXParseHandler extends DefaultHandler {
     private List<Book> list;         //存放解析到的book数组
     private Book book;               //存放当前解析的book  

     private String content = ;   //存放当前节点值  

     /**
      * 开始解析xml文档时调用此方法
      */
     @Override
     public void startDocument() throws SAXException {  

         super.startDocument();
         System.out.println("开始解析xml文件");
         list = new ArrayList<Book>();
     }  

     /**
      * 文档解析完成后调用此方法
      */
     @Override
     public void endDocument() throws SAXException {  

         super.endDocument();
         System.out.println("xml文件解析完毕");
     }  

     /**
      * 开始解析节点时调用此方法
      */
     @Override
     public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {  

         super.startElement(uri, localName, qName, attributes);  

         //当节点名为book时,获取book的属性id
         if(qName.equals("book")){
             book = new Book();
             String id = attributes.getValue("id");//System.out.println("id值为"+id);
             book.setId(Integer.parseInt(id));
         }  

     }  

     /**
      *节点解析完毕时调用此方法
      *
      *@param qName 节点名
      */
     @Override
     public void endElement(String uri, String localName, String qName) throws SAXException {  

         super.endElement(uri, localName, qName);
         if(qName.equals("name")){
             book.setName(content);
             //System.out.println("书名"+content);
         }else if(qName.equals("author")){
             book.setAuthor(content);
         //  System.out.println("作者"+content);
         }else if(qName.equals("year")){
             book.setYear(Integer.parseInt(content));
         //  System.out.println("年份"+content);
         }else if(qName.equals("price")){
             book.setPrice(Double.parseDouble(content));
         //  System.out.println("价格"+content);
         }else if(qName.equals("book")){         //当结束当前book解析时,将该book添加到数组后置为空，方便下一次book赋值
             list.add(book);
             book = ;
         }     

     }  

     /**
      * 此方法用来获取节点的值
      */
     @Override
     public void characters(char[] ch, int start, int length) throws SAXException {  

         super.characters(ch, start, length);  

         content = new String(ch, start, length);
         //收集不为空白的节点值
 //      if(!content.trim().equals("")){
 //          System.out.println("节点值为："+content);
 //      }  

     }  

     public List<Book> getBooks(){
         return list;
     }  

 }  

用SAX方式读取xml文件

 /**
  * 用SAX方式读取xml文件
  */
 public class ReadXmlBySAX {  

     private static List<Book> books = ;  

     private  SAXParserFactory sParserFactory = ;
     private  SAXParser parser = ;  

     public List<Book> getBooks(String fileName) throws Exception{
         SAXParserFactory sParserFactory = SAXParserFactory.newInstance();
         SAXParser parser = sParserFactory.newSAXParser();  

         SAXParseHandler handler = new SAXParseHandler();
         parser.parse(fileName, handler);  

         return handler.getBooks();  

     }
     /**
      * @param args
      */
     public static void main(String[] args) {
         try {
             books = new ReadXmlBySAX().getBooks("src/res/books.xml");
             for(Book book:books){
                 System.out.println(book);
             }  

         } catch (Exception e) {
             e.printStackTrace();
         }  

     }  

 }  

（3）JDOM方式解析XML

 /**
  * 用JDOM方式读取xml文件
  */
 public class ReadXMLByJDom {  

     private List<Book> books = ;
     private Book book = ;  

     public List<Book> getBooks(String fileName){
         SAXBuilder saxBuilder = new SAXBuilder();
         try {
             Document document = saxBuilder.build(new FileInputStream(fileName));
             //获取根节点bookstore
             Element rootElement = document.getRootElement();
             //获取根节点的子节点，返回子节点的数组
             List<Element> bookList = rootElement.getChildren();
             books = new ArrayList<Book>();
             for(Element bookElement : bookList){
                 book = new Book();
                 //获取bookElement的属性
                 List<Attribute> bookAttributes = bookElement.getAttributes();
                 for(Attribute attribute : bookAttributes){
                     if(attribute.getName().equals("id")){
                         String id = attribute.getValue(); //System.out.println(id);
                         book.setId(Integer.parseInt(id));
                     }
                 }
                 //获取bookElement的子节点
                 List<Element> children = bookElement.getChildren();
                 for(Element child : children){
                     if(child.getName().equals("name")){
                         String name = child.getValue();//System.out.println(name);
                         book.setName(name);
                     }else if(child.getName().equals("author")){
                         String author = child.getValue();
                         book.setAuthor(author);//System.out.println(author);
                     }else if(child.getName().equals("year")){
                         String year = child.getValue();
                         book.setYear(Integer.parseInt(year));
                     }else if(child.getName().equals("price")){
                         String price = child.getValue();
                         book.setPrice(Double.parseDouble(price));
                     }  

                 }  

                 books.add(book);
                 book = ;  

             }  

         } catch (FileNotFoundException e) {  

             e.printStackTrace();
         } catch (JDOMException e) {  

             e.printStackTrace();
         } catch (IOException e) {  

             e.printStackTrace();
         }  

         return books;  

     }  

     public static void main(String[] args) {
         // TODO Auto-generated method stub
         String fileName = "src/res/books.xml";
         List<Book> books= new ReadXMLByJDom().getBooks(fileName);
         for(Book book : books){
             System.out.println(book);
         }
     }  

 }  

4、DOM4j方式解析XML

 /**
  * 用DOM4J方法读取xml文件
  */
 public class ReadXMLByDom4j {  

     private List<Book> bookList = ;
     private Book book = ;  

     public List<Book> getBooks(File file){  

         SAXReader reader = new SAXReader();
         try {
             Document document = reader.read(file);
             Element bookstore = document.getRootElement();
             Iterator storeit = bookstore.elementIterator();  

             bookList = new ArrayList<Book>();
             while(storeit.hasNext()){  

                 book = new Book();
                 Element bookElement = (Element) storeit.next();
                 //遍历bookElement的属性
                 List<Attribute> attributes = bookElement.attributes();
                 for(Attribute attribute : attributes){
                     if(attribute.getName().equals("id")){
                         String id = attribute.getValue();//System.out.println(id);
                         book.setId(Integer.parseInt(id));
                     }
                 }  

                 Iterator bookit = bookElement.elementIterator();
                 while(bookit.hasNext()){
                     Element child = (Element) bookit.next();
                     String nodeName = child.getName();
                     if(nodeName.equals("name")){
                         //System.out.println(child.getStringValue());
                         String name = child.getStringValue();
                         book.setName(name);
                     }else if(nodeName.equals("author")){
                         String author = child.getStringValue();
                         book.setAuthor(author);
                     }else if(nodeName.equals("year")){
                         String year = child.getStringValue();
                         book.setYear(Integer.parseInt(year));
                     }else if(nodeName.equals("price")){
                         String price = child.getStringValue();
                         book.setPrice(Double.parseDouble(price));
                     }
                 }
                 bookList.add(book);
                 book = ;  

             }
         } catch (DocumentException e) {  

             e.printStackTrace();
         }  

         return bookList;  

     }  

     /**
      * @param args
      */
     public static void main(String[] args) {
         // TODO Auto-generated method stub
         File file = new File("src/res/books.xml");
         List<Book> bookList = new ReadXMLByDom4j().getBooks(file);
         for(Book book : bookList){
             System.out.println(book);
         }
     }  

 }