dom4j解析xml字符串实例

DOM4J

    与利用DOM、SAX、JAXP机制来解析xml相比，DOM4J 表现更优秀，具有性能优异、功能强大和极端易用使用的特点，只要懂得DOM基本概念，就可以通过dom4j的api文档来解析xml。dom4j是一套开源的api。实际项目中，往往选择dom4j来作为解析xml的利器。

先来看看dom4j中对应XML的DOM树建立的继承关系

  

针对于XML标准定义，对应于图2-1列出的内容，dom4j提供了以下实现：

  

同时，dom4j的NodeType枚举实现了XML规范中定义的node类型。如此可以在遍历xml文档的时候通过常量来判断节点类型了。

 

常用API

class org.dom4j.io.SAXReader

• read  提供多种读取xml文件的方式，返回一个Domcument对象

interface org.dom4j.Document

• iterator  使用此法获取node
• getRootElement  获取根节点

interface org.dom4j.Node

• getName  获取node名字，例如获取根节点名称为bookstore
• getNodeType  获取node类型常量值，例如获取到bookstore类型为1——Element
• getNodeTypeName  获取node类型名称，例如获取到的bookstore类型名称为Element

interface org.dom4j.Element

• attributes  返回该元素的属性列表
• attributeValue  根据传入的属性名获取属性值
• elementIterator  返回包含子元素的迭代器
• elements  返回包含子元素的列表

interface org.dom4j.Attribute

• getName  获取属性名
• getValue  获取属性值

interface org.dom4j.Text

• getText  获取Text节点值

interface org.dom4j.CDATA

• getText  获取CDATA Section值

interface org.dom4j.Comment

• getText  获取注释 

 

实例一：

//先加入dom4j.jar包 
import java.util.HashMap;
import java.util.Iterator;
import java.util.Map;
import org.dom4j.Document;

import org.dom4j.DocumentException;

import org.dom4j.DocumentHelper;

import org.dom4j.Element;
/**


@Title: TestDom4j.java


@Package


@Description: 解析xml字符串


@author 无处不在


@date 2012-11-20 下午05:14:05


@version V1.0

*/

public class TestDom4j {
public void readStringXml(String xml) {

Document doc = null;

try {
      </span><span style="color: #008000;">//</span><span style="color: #008000;"> 读取并解析XML文档
      </span><span style="color: #008000;">//</span><span style="color: #008000;"> SAXReader就是一个管道，用一个流的方式，把xml文件读出来
      </span><span style="color: #008000;">//</span> 
      <span style="color: #008000;">//</span><span style="color: #008000;"> SAXReader reader = new SAXReader(); </span><span style="color: #008000;">//</span><span style="color: #008000;">User.hbm.xml表示你要解析的xml文档
      </span><span style="color: #008000;">//</span><span style="color: #008000;"> Document document = reader.read(new File("User.hbm.xml"));
      </span><span style="color: #008000;">//</span><span style="color: #008000;"> 下面的是通过解析xml字符串的</span>
      doc = DocumentHelper.parseText(xml); <span style="color: #008000;">//</span><span style="color: #008000;"> 将字符串转为XML</span>




            Element rootElt = doc.getRootElement(); // 获取根节点
            System.out.println("根节点：" + rootElt.getName()); // 拿到根节点的名称

            Iterator iter = rootElt.elementIterator("head"); // 获取根节点下的子节点head
        </span><span style="color: #008000;">//</span><span style="color: #008000;"> 遍历head节点</span>
        <span style="color: #0000ff;">while</span><span style="color: #000000;"> (iter.hasNext()) {

            Element recordEle </span>=<span style="color: #000000;"> (Element) iter.next();
            String title </span>= recordEle.elementTextTrim("title"); <span style="color: #008000;">//</span><span style="color: #008000;"> 拿到head节点下的子节点title值</span>
            System.out.println("title:" +<span style="color: #000000;"> title);

            Iterator iters </span>= recordEle.elementIterator("script"); <span style="color: #008000;">//</span><span style="color: #008000;"> 获取子节点head下的子节点script

            </span><span style="color: #008000;">//</span><span style="color: #008000;"> 遍历Header节点下的Response节点</span>
            <span style="color: #0000ff;">while</span><span style="color: #000000;"> (iters.hasNext()) {

                Element itemEle </span>=<span style="color: #000000;"> (Element) iters.next();

                String username </span>= itemEle.elementTextTrim("username"); <span style="color: #008000;">//</span><span style="color: #008000;"> 拿到head下的子节点script下的字节点username的值</span>
                String password = itemEle.elementTextTrim("password"<span style="color: #000000;">);

                System.out.println(</span>"username:" +<span style="color: #000000;"> username);
                System.out.println(</span>"password:" +<span style="color: #000000;"> password);
            }
        }
        Iterator iterss </span>= rootElt.elementIterator("body"); <span style="color: #008000;">//</span><span style="color: #008000;">/获取根节点下的子节点body
        </span><span style="color: #008000;">//</span><span style="color: #008000;"> 遍历body节点</span>
        <span style="color: #0000ff;">while</span><span style="color: #000000;"> (iterss.hasNext()) {

            Element recordEless </span>=<span style="color: #000000;"> (Element) iterss.next();
            String result </span>= recordEless.elementTextTrim("result"); <span style="color: #008000;">//</span><span style="color: #008000;"> 拿到body节点下的子节点result值</span>
            System.out.println("result:" +<span style="color: #000000;"> result);

            Iterator itersElIterator </span>= recordEless.elementIterator("form"); <span style="color: #008000;">//</span><span style="color: #008000;"> 获取子节点body下的子节点form
            </span><span style="color: #008000;">//</span><span style="color: #008000;"> 遍历Header节点下的Response节点</span>
            <span style="color: #0000ff;">while</span><span style="color: #000000;"> (itersElIterator.hasNext()) {

                Element itemEle </span>=<span style="color: #000000;"> (Element) itersElIterator.next();

                String banlce </span>= itemEle.elementTextTrim("banlce"); <span style="color: #008000;">//</span><span style="color: #008000;"> 拿到body下的子节点form下的字节点banlce的值</span>
                String subID = itemEle.elementTextTrim("subID"<span style="color: #000000;">);

                System.out.println(</span>"banlce:" +<span style="color: #000000;"> banlce);
                System.out.println(</span>"subID:" +<span style="color: #000000;"> subID);
            }
        }
    } </span><span style="color: #0000ff;">catch</span><span style="color: #000000;"> (DocumentException e) {
        e.printStackTrace();

    } </span><span style="color: #0000ff;">catch</span><span style="color: #000000;"> (Exception e) {
        e.printStackTrace();

    }
}

</span><span style="color: #008000;">/**</span><span style="color: #008000;">
 * @description 将xml字符串转换成map
 * </span><span style="color: #808080;">@param</span><span style="color: #008000;"> xml
 * </span><span style="color: #808080;">@return</span><span style="color: #008000;"> Map
 </span><span style="color: #008000;">*/</span>
<span style="color: #0000ff;">public</span> <span style="color: #0000ff;">static</span><span style="color: #000000;"> Map readStringXmlOut(String xml) {
    Map map </span>= <span style="color: #0000ff;">new</span><span style="color: #000000;"> HashMap();
    Document doc </span>= <span style="color: #0000ff;">null</span><span style="color: #000000;">;
    </span><span style="color: #0000ff;">try</span><span style="color: #000000;"> {
        </span><span style="color: #008000;">//</span><span style="color: #008000;"> 将字符串转为XML</span>
        doc =<span style="color: #000000;"> DocumentHelper.parseText(xml); 
        </span><span style="color: #008000;">//</span><span style="color: #008000;"> 获取根节点</span>
        Element rootElt =<span style="color: #000000;"> doc.getRootElement(); 
        </span><span style="color: #008000;">//</span><span style="color: #008000;"> 拿到根节点的名称</span>
        System.out.println("根节点：" +<span style="color: #000000;"> rootElt.getName()); 

        </span><span style="color: #008000;">//</span><span style="color: #008000;"> 获取根节点下的子节点head</span>
        Iterator iter = rootElt.elementIterator("head"<span style="color: #000000;">); 
        </span><span style="color: #008000;">//</span><span style="color: #008000;"> 遍历head节点</span>
        <span style="color: #0000ff;">while</span><span style="color: #000000;"> (iter.hasNext()) {

            Element recordEle </span>=<span style="color: #000000;"> (Element) iter.next();
            </span><span style="color: #008000;">//</span><span style="color: #008000;"> 拿到head节点下的子节点title值</span>
            String title = recordEle.elementTextTrim("title"<span style="color: #000000;">); 
            System.out.println(</span>"title:" +<span style="color: #000000;"> title);
            map.put(</span>"title"<span style="color: #000000;">, title);
            </span><span style="color: #008000;">//</span><span style="color: #008000;"> 获取子节点head下的子节点script</span>
            Iterator iters = recordEle.elementIterator("script"<span style="color: #000000;">); 
            </span><span style="color: #008000;">//</span><span style="color: #008000;"> 遍历Header节点下的Response节点</span>
            <span style="color: #0000ff;">while</span><span style="color: #000000;"> (iters.hasNext()) {
                Element itemEle </span>=<span style="color: #000000;"> (Element) iters.next();
                </span><span style="color: #008000;">//</span><span style="color: #008000;"> 拿到head下的子节点script下的字节点username的值</span>
                String username = itemEle.elementTextTrim("username"<span style="color: #000000;">); 
                String password </span>= itemEle.elementTextTrim("password"<span style="color: #000000;">);

                System.out.println(</span>"username:" +<span style="color: #000000;"> username);
                System.out.println(</span>"password:" +<span style="color: #000000;"> password);
                map.put(</span>"username"<span style="color: #000000;">, username);
                map.put(</span>"password"<span style="color: #000000;">, password);
            }
        }

        </span><span style="color: #008000;">//</span><span style="color: #008000;">获取根节点下的子节点body</span>
        Iterator iterss = rootElt.elementIterator("body"<span style="color: #000000;">); 
        </span><span style="color: #008000;">//</span><span style="color: #008000;"> 遍历body节点</span>
        <span style="color: #0000ff;">while</span><span style="color: #000000;"> (iterss.hasNext()) {
            Element recordEless </span>=<span style="color: #000000;"> (Element) iterss.next();
            </span><span style="color: #008000;">//</span><span style="color: #008000;"> 拿到body节点下的子节点result值</span>
            String result = recordEless.elementTextTrim("result"<span style="color: #000000;">); 
            System.out.println(</span>"result:" +<span style="color: #000000;"> result);
            </span><span style="color: #008000;">//</span><span style="color: #008000;"> 获取子节点body下的子节点form</span>
            Iterator itersElIterator = recordEless.elementIterator("form"<span style="color: #000000;">); 
            </span><span style="color: #008000;">//</span><span style="color: #008000;"> 遍历Header节点下的Response节点</span>
            <span style="color: #0000ff;">while</span><span style="color: #000000;"> (itersElIterator.hasNext()) {
                Element itemEle </span>=<span style="color: #000000;"> (Element) itersElIterator.next();
                </span><span style="color: #008000;">//</span><span style="color: #008000;"> 拿到body下的子节点form下的字节点banlce的值</span>
                String banlce = itemEle.elementTextTrim("banlce"<span style="color: #000000;">); 
                String subID </span>= itemEle.elementTextTrim("subID"<span style="color: #000000;">);

                System.out.println(</span>"banlce:" +<span style="color: #000000;"> banlce);
                System.out.println(</span>"subID:" +<span style="color: #000000;"> subID);
                map.put(</span>"result"<span style="color: #000000;">, result);
                map.put(</span>"banlce"<span style="color: #000000;">, banlce);
                map.put(</span>"subID"<span style="color: #000000;">, subID);
            }
        }
    } </span><span style="color: #0000ff;">catch</span><span style="color: #000000;"> (DocumentException e) {
        e.printStackTrace();
    } </span><span style="color: #0000ff;">catch</span><span style="color: #000000;"> (Exception e) {
        e.printStackTrace();
    }
    </span><span style="color: #0000ff;">return</span><span style="color: #000000;"> map;
}

</span><span style="color: #0000ff;">public</span> <span style="color: #0000ff;">static</span> <span style="color: #0000ff;">void</span><span style="color: #000000;"> main(String[] args) {

    </span><span style="color: #008000;">//</span><span style="color: #008000;"> 下面是需要解析的xml字符串例子</span>
    String xmlString = "&lt;html&gt;" + "&lt;head&gt;" + "&lt;title&gt;dom4j解析一个例子&lt;/title&gt;"
            + "&lt;script&gt;" + "&lt;username&gt;yangrong&lt;/username&gt;"
            + "&lt;password&gt;123456&lt;/password&gt;" + "&lt;/script&gt;" + "&lt;/head&gt;"
            + "&lt;body&gt;" + "&lt;result&gt;0&lt;/result&gt;" + "&lt;form&gt;"
            + "&lt;banlce&gt;1000&lt;/banlce&gt;" + "&lt;subID&gt;36242519880716&lt;/subID&gt;"
            + "&lt;/form&gt;" + "&lt;/body&gt;" + "&lt;/html&gt;"<span style="color: #000000;">;

    </span><span style="color: #008000;">/*</span><span style="color: #008000;">
     * Test2 test = new Test2(); test.readStringXml(xmlString);
     </span><span style="color: #008000;">*/</span><span style="color: #000000;">
    Map map </span>=<span style="color: #000000;"> readStringXmlOut(xmlString);
    Iterator iters </span>=<span style="color: #000000;"> map.keySet().iterator();
    </span><span style="color: #0000ff;">while</span><span style="color: #000000;"> (iters.hasNext()) {
        String key </span>= iters.next().toString(); <span style="color: #008000;">//</span><span style="color: #008000;"> 拿到键</span>
        String val = map.get(key).toString(); <span style="color: #008000;">//</span><span style="color: #008000;"> 拿到值</span>
        System.out.println(key + "=" +<span style="color: #000000;"> val);
    }
}

}

实例二：

/**
 * 解析包含有DB连接信息的XML文件
 * 格式必须符合如下规范：
 * 1. 最多三级，每级的node名称自定义；
 * 2. 二级节点支持节点属性，属性将被视作子节点；
 * 3. CDATA必须包含在节点中，不能单独出现。
 *
 * 示例1——三级显示：
 * <db-connections>
 *         <connection>
 *            <name>DBTest</name>
 *            <jndi></jndi>
 *            <url>
 *                <![CDATA[jdbc:mysql://localhost:3306/db_test?useUnicode=true&characterEncoding=UTF8]]>
 *             </url>
 *            <driver>org.gjt.mm.mysql.Driver</driver>
 *             <user>test</user>
 *            <password>test2012</password>
 *            <max-active>10</max-active>
 *            <max-idle>10</max-idle>
 *            <min-idle>2</min-idle>
 *            <max-wait>10</max-wait>
 *            <validation-query>SELECT 1+1</validation-query>
 *         </connection>
 * </db-connections>
 *
 * 示例2——节点属性：
 * <bookstore>
 *         <book category="cooking">
 *            <title lang="en">Everyday Italian</title>
 *            <author>Giada De Laurentiis</author>
 *            <year>2005</year>
 *            <price>30.00</price>
 *         </book>
 *
 *         <book category="children" title="Harry Potter" author="J K. Rowling" year="2005" price="$29.9"/>
 * </bookstore>

 *
 * @param configFile
 * @return
 * @throws Exception
 */
public static List<Map<String, String>> parseDBXML(String configFile) throws Exception {
    List<Map<String, String>> dbConnections = new ArrayList<Map<String, String>>();
    InputStream is = Parser.class.getResourceAsStream(configFile);
    SAXReader saxReader = new SAXReader();
    Document document = saxReader.read(is);
    Element connections = document.getRootElement();
Iterator</span>&lt;Element&gt; rootIter =<span style="color: #000000;"> connections.elementIterator();
</span><span style="color: #0000ff;">while</span><span style="color: #000000;"> (rootIter.hasNext()) {
    Element connection </span>=<span style="color: #000000;"> rootIter.next();
    Iterator</span>&lt;Element&gt; childIter =<span style="color: #000000;"> connection.elementIterator();
    Map</span>&lt;String, String&gt; connectionInfo = <span style="color: #0000ff;">new</span> HashMap&lt;String, String&gt;<span style="color: #000000;">();
    List</span>&lt;Attribute&gt; attributes =<span style="color: #000000;"> connection.attributes();
    </span><span style="color: #0000ff;">for</span> (<span style="color: #0000ff;">int</span> i = 0; i &lt; attributes.size(); ++i) { <span style="color: #008000;">//</span><span style="color: #008000;"> 添加节点属性</span>

            connectionInfo.put(attributes.get(i).getName(), attributes.get(i).getValue());

}

while (childIter.hasNext()) { // 添加子节点

Element attr = childIter.next();

connectionInfo.put(attr.getName().trim(), attr.getText().trim());

}

dbConnections.add(connectionInfo);

}
</span><span style="color: #0000ff;">return</span><span style="color: #000000;"> dbConnections;

}