美文网首页
04-XML解析和生成

04-XML解析和生成

作者: XAbo | 来源:发表于2020-11-29 09:45 被阅读0次

    XML基本的解析方式有两种,一种叫SAX,另一种叫DOM。SAX是基于事件流的解析,DOM是基于XML文档树结构的解析。

    1.DOM生成和解析XML文档

    为 XML 文档的已解析版本定义了一组接口。解析器读入整个文档,然后构建一个驻留内存的树结构,然后代码就可以使用 DOM 接口来操作这个树结构。
    优点:整个文档树在内存中,便于操作;支持删除、修改、重新排列等多种功能;
    缺点:将整个文档调入内存(包括无用的节点),浪费时间和空间;
    使用场合:一旦解析了文档还需多次访问这些数据;硬件资源充足(内存、CPU)。

    /** 
    * 
    * @author hongliang.dinghl 
    * DOM生成与解析XML文档 
    */ 
    public class DomDemo implements XmlDocument { 
    private Document document; 
    private String fileName; 
    public void init() { 
    try { 
    DocumentBuilderFactory factory = DocumentBuilderFactory 
    .newInstance(); 
    DocumentBuilder builder = factory.newDocumentBuilder(); 
    this.document = builder.newDocument(); 
    } catch (ParserConfigurationException e) { 
    System.out.println(e.getMessage()); 
    } 
    } 
    public void createXml(String fileName) { 
    Element root = this.document.createElement("employees"); 
    this.document.appendChild(root); 
    Element employee = this.document.createElement("employee"); 
    Element name = this.document.createElement("name"); 
    name.appendChild(this.document.createTextNode("丁宏亮")); 
    employee.appendChild(name); 
    Element sex = this.document.createElement("sex"); 
    sex.appendChild(this.document.createTextNode("m")); 
    employee.appendChild(sex); 
    Element age = this.document.createElement("age"); 
    age.appendChild(this.document.createTextNode("30")); 
    employee.appendChild(age); 
    root.appendChild(employee); 
    TransformerFactory tf = TransformerFactory.newInstance(); 
    try { 
    Transformer transformer = tf.newTransformer(); 
    DOMSource source = new DOMSource(document); 
    transformer.setOutputProperty(OutputKeys.ENCODING, "gb2312"); 
    transformer.setOutputProperty(OutputKeys.INDENT, "yes"); 
    PrintWriter pw = new PrintWriter(new FileOutputStream(fileName)); 
    StreamResult result = new StreamResult(pw); 
    transformer.transform(source, result); 
    System.out.println("生成XML文件成功!"); 
    } catch (TransformerConfigurationException e) { 
    System.out.println(e.getMessage()); 
    } catch (IllegalArgumentException e) { 
    System.out.println(e.getMessage()); 
    } catch (FileNotFoundException e) { 
    System.out.println(e.getMessage()); 
    } catch (TransformerException e) { 
    System.out.println(e.getMessage()); 
    } 
    } 
    public void parserXml(String fileName) { 
    try { 
    DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance(); 
    DocumentBuilder db = dbf.newDocumentBuilder(); 
    Document document = db.parse(fileName); 
    NodeList employees = document.getChildNodes(); 
    for (int i = 0; i < employees.getLength(); i++) { 
    Node employee = employees.item(i); 
    NodeList employeeInfo = employee.getChildNodes(); 
    for (int j = 0; j < employeeInfo.getLength(); j++) { 
    Node node = employeeInfo.item(j); 
    NodeList employeeMeta = node.getChildNodes(); 
    for (int k = 0; k < employeeMeta.getLength(); k++) { 
    System.out.println(employeeMeta.item(k).getNodeName() 
    + ":" + employeeMeta.item(k).getTextContent()); 
    } 
    } 
    } 
    System.out.println("解析完毕"); 
    } catch (FileNotFoundException e) { 
    System.out.println(e.getMessage()); 
    } catch (ParserConfigurationException e) { 
    System.out.println(e.getMessage()); 
    } catch (SAXException e) { 
    System.out.println(e.getMessage()); 
    } catch (IOException e) { 
    System.out.println(e.getMessage()); 
    } 
    } 
    }
    

    2.SAX生成和解析XML文档

    为解决DOM的问题,出现了SAX。SAX ,事件驱动。当解析器发现元素开始、元素结束、文本、文档的开始或结束等时,发送事件,程序员编写响应这些事件的代码,保存数据。
    优点:不用事先调入整个文档,占用资源少;SAX解析器代码比DOM解析器代码小,适于Applet,下载。
    缺点:不是持久的;事件过后,若没保存数据,那么数据就丢了;无状态性;从事件中只能得到文本,但不知该文本属于哪个元素;不能增删改
    使用场合:Applet;只需XML文档的少量内容,很少回头访问;机器内存少;

    public class SaxDemo implements XmlDocument { 
    public void createXml(String fileName) { 
    System.out.println("<<"+filename+">>"); 
    } 
    public void parserXml(String fileName) { 
    SAXParserFactory saxfac = SAXParserFactory.newInstance(); 
    try { 
    SAXParser saxparser = saxfac.newSAXParser(); 
    InputStream is = new FileInputStream(fileName); 
    saxparser.parse(is, new MySAXHandler()); 
    } catch (ParserConfigurationException e) { 
    e.printStackTrace(); 
    } catch (SAXException e) { 
    e.printStackTrace(); 
    } catch (FileNotFoundException e) { 
    e.printStackTrace(); 
    } catch (IOException e) { 
    e.printStackTrace(); 
    } 
    } 
    } 
    class MySAXHandler extends DefaultHandler { 
    boolean hasAttribute = false; 
    Attributes attributes = null; 
    public void startDocument() throws SAXException { 
    System.out.println("文档开始打印了"); 
    } 
    public void endDocument() throws SAXException { 
    System.out.println("文档打印结束了"); 
    } 
    public void startElement(String uri, String localName, String qName, 
    Attributes attributes) throws SAXException { 
    if (qName.equals("employees")) { 
    return; 
    } 
    if (qName.equals("employee")) { 
    System.out.println(qName); 
    } 
    if (attributes.getLength() > 0) { 
    this.attributes = attributes; 
    this.hasAttribute = true; 
    } 
    } 
    public void endElement(String uri, String localName, String qName) 
    throws SAXException { 
    if (hasAttribute && (attributes != null)) { 
    for (int i = 0; i < attributes.getLength(); i++) { 
    System.out.println(attributes.getQName(0) 
    + attributes.getValue(0)); 
    } 
    } 
    } 
    public void characters(char[] ch, int start, int length) 
    throws SAXException { 
    System.out.println(new String(ch, start, length)); 
    } 
    } 
    

    3.DOM4J生成和解析XML文档

    DOM4J 是一个非常非常优秀的JAVA XML API,具有性能优异、功能强大和极端易用使用的特点,同时它也是一个开放源代码的软件。如今你可以看到越来越多的 Java 软件都在使用 DOM4J 来读写 XML,特别值得一提的是连 Sun 的 JAXM 也在用 DOM4J。DOM4J是在SAX基础之上,又生成一个DOM树,所以DOM4J可以很容易的操作节点。

    /**  
    *   
    * @author hongliang.dinghl  
    * Dom4j 生成XML文档与解析XML文档  
    */  
    public class Dom4jDemo implements XmlDocument {   
    
    public void createXml(String fileName) {   
    Document document = DocumentHelper.createDocument();   
    Element employees=document.addElement("employees");   
    Element employee=employees.addElement("employee");   
    Element name= employee.addElement("name");   
    name.setText("ddvip");   
    Element sex=employee.addElement("sex");   
    sex.setText("m");   
    Element age=employee.addElement("age");   
    age.setText("29");   
    try {   
    Writer fileWriter=new FileWriter(fileName);   
    XMLWriter xmlWriter=new XMLWriter(fileWriter);   
    xmlWriter.write(document);   
    xmlWriter.close();   
    } catch (IOException e) {   
    
    System.out.println(e.getMessage());   
    }   
    
    
    }   
    
    
    public void parserXml(String fileName) {   
    File inputXml=new File(fileName);   
    SAXReader saxReader = new SAXReader();   
    try {   
    Document document = saxReader.read(inputXml);   
    Element employees=document.getRootElement();   
    for(Iterator i = employees.elementIterator(); i.hasNext();){   //这里建议使用employees.elements()替代迭代的方法,此方法返回一个元素List更易于操纵。
    Element employee = (Element) i.next();   
    for(Iterator j = employee.elementIterator(); j.hasNext();){   
    Element node=(Element) j.next();   
    System.out.println(node.getName()+":"+node.getText());   
    }   
    
    }   
    } catch (DocumentException e) {   
    System.out.println(e.getMessage());   
    }   
    System.out.println("dom4j parserXml");   
    }   
    }
    

    4.JDOM生成和解析XML

    为减少DOM、SAX的编码量,出现了JDOM;优点:20-80原则,极大减少了代码量。使用场合:要实现的功能简单,如解析、创建等,但在底层,JDOM还是使用SAX(最常用)、DOM、Xanan文档。

    /**  
    *   
    * @author hongliang.dinghl  
    * JDOM 生成与解析XML文档  
    *   
    */  
    public class JDomDemo implements XmlDocument {   
    
    public void createXml(String fileName) {   
    Document document;   
    Element  root;   
    root=new Element("employees");   
    document=new Document(root);   
    Element employee=new Element("employee");   
    root.addContent(employee);   
    Element name=new Element("name");   
    name.setText("ddvip");   
    employee.addContent(name);   
    Element sex=new Element("sex");   
    sex.setText("m");   
    employee.addContent(sex);   
    Element age=new Element("age");   
    age.setText("23");   
    employee.addContent(age);   
    XMLOutputter XMLOut = new XMLOutputter();   
    try {   
    XMLOut.output(document, new FileOutputStream(fileName));   
    } catch (FileNotFoundException e) {   
    e.printStackTrace();   
    } catch (IOException e) {   
    e.printStackTrace();   
    }   
    
    }   
    
    public void parserXml(String fileName) {   
    SAXBuilder builder=new SAXBuilder(false);    
    try {   
    Document document=builder.build(fileName);   
    Element employees=document.getRootElement();    
    List employeeList=employees.getChildren("employee");   
    for(int i=0;iElement employee=(Element)employeeList.get(i);   
    List employeeInfo=employee.getChildren();   
    for(int j=0;jSystem.out.println(((Element)employeeInfo.get(j)).getName()+":"+((Element)employeeInfo.get(j)).getValue());   
    
    }   
    }   
    } catch (JDOMException e) {   
    
    e.printStackTrace();   
    } catch (IOException e) {   
    
    e.printStackTrace();   
    }    
    
    }   
    }
    

    以上摘自:解析XML的几种方式_yuan16423276的专栏-CSDN博客

    5.Jsoup解析器入门

    jsoup 是一款Java 的HTML解析器,可直接解析某个URL地址、HTML文本内容。它提供了一套非常省力的API,可通过DOM,CSS以及类似于jQuery的操作方法来取出和操作数据。jsoup开发指南

    实例:

    <?xml version="1.0" encoding="UTF-8" standalone="no"?>
     
    <students>
        <student number="0001">
            <name id="itcast">tom</name>
            <age>18</age>
            <sex>male</sex>
        </student>
        <student number="0002">
            <name>jack</name>
            <age>18</age>
            <sex>female</sex>
        </student>
    </students>
    

    解析:

    package jsoup;
     
    import org.jsoup.Jsoup;
    import org.jsoup.nodes.Document;
    import org.jsoup.nodes.Element;
    import org.jsoup.select.Elements;
     
    import java.io.File;
    import java.io.IOException;
     
    /**
     * xml_解析_Jsoup_快速入门
     * <p>
     * 步骤:
     * 1,导入JAR
     * 2,解析XML文件
     *      A,得到解析文件的路径:类加载器加载文件的路径
     *      B,构建一个FILE对象
     *      C,调用JSOUP的PARSE方法解析XML文件得到一个DOCUMENT对象
     *      D,调用Document的相关方法得到相关的标签对象(Element)
     *          Elements:就是一个存了Element对象的ArrayList集合
     *      E ,调用Element的相关方法得到想要的数据
     */
    public class JsoupDemo1 {
        public static void main(String[] args) throws IOException {
            //1.获取xml解析文件的路径
            String path = JsoupDemo1.class.getClassLoader().getResource( "xml/student.xml" ).getPath();
            //2.解析xml文档,加载文档进内存,获取document对象
            Document document = Jsoup.parse(new File( path ),"UTF-8");
            //3.获取元素对象Element,返回值是存了Element对象的ArrayList集合
            Elements name = document.getElementsByTag( "name" );
            //4.获取第一个name的Element对象
            Element element = name.get( 0 );
            //5.获取数据
            String text = element.text();
            System.out.println(text);
        }
    }
    

    相关文章

      网友评论

          本文标题:04-XML解析和生成

          本文链接:https://www.haomeiwen.com/subject/arnuiktx.html