xml解析

JDK

使用最原始的javax.xml.parsers，标准的jdk api

// 字符串转XML
String xmlStr = "......";
StringReader sr = new StringReader(xmlStr); 
InputSource is = new InputSource(sr); 
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance(); 
DocumentBuilder builder=factory.newDocumentBuilder(); 
Document doc = builder.parse(is);
NodeList list = root.getChildNodes();
//XML转字符串
TransformerFactory  tf  =  TransformerFactory.newInstance();
Transformer t = tf.newTransformer();
t.setOutputProperty("encoding","GB23121");//解决中文问题，试过用GBK不行
ByteArrayOutputStream  bos  =  new  ByteArrayOutputStream();
t.transform(new DOMSource(doc), new StreamResult(bos));
String xmlStr = bos.toString();
这里的XML DOCUMENT为org.w3c.dom.Document

dom4j

使用dom4j解析xml

https://www.dom4j.org/dom4j-1.6.1/

从文件中读取xml

File file = new File("resource/outputdom4j.xml");
SAXReader reader = new SAXReader();
// 读取文件作为文档
Document doc = reader.read(file);
// 获取文档的根元素
Element root = doc.getRootElement();
// 根据跟元素找到全部的子节点
Iterator<Element> iter = root.elementIterator();
while(iter.hasNext()){
    Element name = iter.next();
    System.out.println("value = " + name.getText());
}

创建xml并写入文件

// 使用 DocumentHelper 来创建 Document 对象  
Document document = DocumentHelper.createDocument();  
// 创建元素并设置关系  
Element person = document.addElement("person");  
Element name = person.addElement("name");   
Element age = person.addElement("age");  
// 设置文本  name.setText("lebyte");  
age.setText("10"); 
// 创建格式化输出器  
OutputFormat of = OutputFormat.createPrettyPrint();  
of.setEncoding("utf-8");  
// 输出到文件  
File file = new File("resource/outputdom4j.xml");  
XMLWriter writer = new XMLWriter(new FileOutputStream(new  File(file.getAbsolutePath())),of);
//写出
writer.write(document);
writer.flush();
writer.close();

解析字符串

//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 {

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

            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

            // 遍历head节点
            while (iter.hasNext()) {

                Element recordEle = (Element) iter.next();
                String title = recordEle.elementTextTrim("title"); // 拿到head节点下的子节点title值
                System.out.println("title:" + title);

                Iterator iters = recordEle.elementIterator("script"); // 获取子节点head下的子节点script

                // 遍历Header节点下的Response节点
                while (iters.hasNext()) {

                    Element itemEle = (Element) iters.next();

                    String username = itemEle.elementTextTrim("username"); // 拿到head下的子节点script下的字节点username的值
                    String password = itemEle.elementTextTrim("password");

                    System.out.println("username:" + username);
                    System.out.println("password:" + password);
                }
            }
            Iterator iterss = rootElt.elementIterator("body"); ///获取根节点下的子节点body
            // 遍历body节点
            while (iterss.hasNext()) {

                Element recordEless = (Element) iterss.next();
                String result = recordEless.elementTextTrim("result"); // 拿到body节点下的子节点result值
                System.out.println("result:" + result);

                Iterator itersElIterator = recordEless.elementIterator("form"); // 获取子节点body下的子节点form
                // 遍历Header节点下的Response节点
                while (itersElIterator.hasNext()) {

                    Element itemEle = (Element) itersElIterator.next();

                    String banlce = itemEle.elementTextTrim("banlce"); // 拿到body下的子节点form下的字节点banlce的值
                    String subID = itemEle.elementTextTrim("subID");

                    System.out.println("banlce:" + banlce);
                    System.out.println("subID:" + subID);
                }
            }
        } catch (DocumentException e) {
            e.printStackTrace();

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

        }
    }

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

            // 获取根节点下的子节点head
            Iterator iter = rootElt.elementIterator("head");
            // 遍历head节点
            while (iter.hasNext()) {

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

                    System.out.println("username:" + username);
                    System.out.println("password:" + password);
                    map.put("username", username);
                    map.put("password", password);
                }
            }

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

                    System.out.println("banlce:" + banlce);
                    System.out.println("subID:" + subID);
                    map.put("result", result);
                    map.put("banlce", banlce);
                    map.put("subID", subID);
                }
            }
        } catch (DocumentException e) {
            e.printStackTrace();
        } catch (Exception e) {
            e.printStackTrace();
        }
        return map;
    }

    public static void main(String[] args) {

        // 下面是需要解析的xml字符串例子
        String xmlString = "<html>"  
            + "<head>" 
              + "<title>dom4j解析一个例子</title>"
              + "<script>" 
                + "<username>用户名</username>"
                + "<password>123456</password>" 
              + "</script>" 
            + "</head>"
            + "<body>" 
              + "<result>0</result>" 
              + "<form>"
                + "<banlce>1000</banlce>" 
                + "<subID>1111</subID>"
              + "</form>" 
            + "</body>" 
         + "</html>";

        /*
         * Test2 test = new Test2(); test.readStringXml(xmlString);
         */
        Map map = readStringXmlOut(xmlString);
        Iterator iters = map.keySet().iterator();
        while (iters.hasNext()) {
            String key = iters.next().toString(); // 拿到键
            String val = map.get(key).toString(); // 拿到值
            System.out.println(key + "=" + val);
        }
    }

}

解析单个对象xml

            Document doc = DocumentHelper.parseText(r_xml);
            Element rootElt = doc.getRootElement(); // 获取根节点
            System.out.println("根节点：" + rootElt.getName()); //获取根节点的名称
            //获取根结点下各个结点的值
            String ToUserName = rootElt.elementTextTrim("ToUserName");
            System.out.println("ToUserName:" + ToUserName);
            String FromUserName = rootElt.elementTextTrim("FromUserName");
            System.out.println("FromUserName:" + FromUserName);
            String CreateTime = rootElt.elementTextTrim("CreateTime");
            System.out.println("CreateTime:" + CreateTime);
            String MsgType = rootElt.elementTextTrim("MsgType");
            System.out.println("MsgType:" + MsgType);
            String Content = rootElt.elementTextTrim("Content");
            System.out.println("Content:" + Content);
            String MsgId = rootElt.elementTextTrim("MsgId");
            System.out.println("MsgId:" + MsgId);
            String AgentID = rootElt.elementTextTrim("AgentID");
            System.out.println("AgentID:" + AgentID);
            //将节点转换为xml格式的对象
            String xmlString = doc.getRootElement().asXML();
            System.out.println("xmlString :" + xmlString );