http://lavasoft.blog.51cto.com/62575/66953
Dom4j遍历解析XML测试
近来老和XML打交道,不深挖不行了。。
这是一个Dom4j解析XML的例子,为做复杂递归处理前期所写的例子。涵盖了XML的解析方面大部分核心API。
环境:
Dom4j-1.6.1
Dom4j解析需要XML需要的最小类库为:
dom4j-1.6.1.jar
jaxen-1.1-beta-6.jar
目标:
解析一个xml,输出所有的属性和元素值。
测试代码:
XML文件:
<?
xml
version
="1.0"
encoding
="GBK"
?>
< doc >
< person id ="1" sex ="m" >
< name >zhangsan </ name >
< age >32 </ age >
< adds >
< add code ="home" >home add </ add >
< add code ="com" >com add </ add >
</ adds >
</ person >
< person id ="2" sex ="w" >
< name >lisi </ name >
< age >22 </ age >
< adds >
< add ID ="22" id ="23" code ="home" >home add </ add >
< add ID ="23" id ="22" code ="com" >com add </ add >
< add id ="24" code ="com" >com add </ add >
</ adds >
</ person >
</ doc >
< doc >
< person id ="1" sex ="m" >
< name >zhangsan </ name >
< age >32 </ age >
< adds >
< add code ="home" >home add </ add >
< add code ="com" >com add </ add >
</ adds >
</ person >
< person id ="2" sex ="w" >
< name >lisi </ name >
< age >22 </ age >
< adds >
< add ID ="22" id ="23" code ="home" >home add </ add >
< add ID ="23" id ="22" code ="com" >com add </ add >
< add id ="24" code ="com" >com add </ add >
</ adds >
</ person >
</ doc >
解析代码:
package com.topsoft.test;
import org.dom4j.io.SAXReader;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.Element;
import org.dom4j.Node;
import java.util.Iterator;
import java.util.List;
import java.io.InputStream;
/**
* Created by IntelliJ IDEA.<br>
* <b>User</b>: leizhimin<br>
* <b>Date</b>: 2008-3-26 15:53:51<br>
* <b>Note</b>: Dom4j遍历解析XML测试
*/
public class TestDom4j {
/**
* 获取指定xml文档的Document对象,xml文件必须在classpath中可以找到
*
* @param xmlFilePath xml文件路径
* @return Document对象
*/
public static Document parse2Document(String xmlFilePath) {
SAXReader reader = new SAXReader();
Document document = null;
try {
InputStream in = TestDom4j. class.getResourceAsStream(xmlFilePath);
document = reader.read(in);
} catch (DocumentException e) {
System.out.println(e.getMessage());
System.out.println( "读取classpath下xmlFileName文件发生异常,请检查CLASSPATH和文件名是否存在!");
e.printStackTrace();
}
return document;
}
public static void testParseXMLData(String xmlFileName) {
//产生一个解析器对象
SAXReader reader = new SAXReader();
//将xml文档转换为Document的对象
Document document = parse2Document(xmlFileName);
//获取文档的根元素
Element root = document.getRootElement();
//定义个保存输出xml数据的缓冲字符串对象
StringBuffer sb = new StringBuffer();
sb.append( "通过Dom4j解析XML,并输出数据:\n");
sb.append(xmlFileName + "\n");
sb.append( "----------------遍历start----------------\n");
//遍历当前元素(在此是根元素)的子元素
for (Iterator i_pe = root.elementIterator(); i_pe.hasNext();) {
Element e_pe = (Element) i_pe.next();
//获取当前元素的名字
String person = e_pe.getName();
//获取当前元素的id和sex属性的值并分别赋给id,sex变量
String id = e_pe.attributeValue( "id");
String sex = e_pe.attributeValue( "sex");
String name = e_pe.element( "name").getText();
String age = e_pe.element( "age").getText();
//将数据存放到缓冲区字符串对象中
sb.append(person + ":\n");
sb.append( "\tid=" + id + " sex=" + sex + "\n");
sb.append( "\t" + "name=" + name + " age=" + age + "\n");
//获取当前元素e_pe(在此是person元素)下的子元素adds
Element e_adds = e_pe.element( "adds");
sb.append( "\t" + e_adds.getName() + "\n");
//遍历当前元素e_adds(在此是adds元素)的子元素
for (Iterator i_adds = e_adds.elementIterator(); i_adds.hasNext();) {
Element e_add = (Element) i_adds.next();
String code = e_add.attributeValue( "code");
String add = e_add.getTextTrim();
sb.append( "\t\t" + e_add.getName() + ":" + " code=" + code + " value=\"" + add + "\"\n");
}
sb.append( "\n");
}
sb.append( "-----------------遍历end-----------------\n");
System.out.println(sb.toString());
System.out.println( "---------通过XPath获取一个元素----------");
Node node1 = document.selectSingleNode( "/doc/person");
System.out.println( "输出节点:" +
"\t"+node1.asXML());
Node node2 = document.selectSingleNode( "/doc/person/@sex");
System.out.println( "输出节点:" +
"\t"+node2.asXML());
Node node3 = document.selectSingleNode( "/doc/person[name=\"zhangsan\"]/age");
System.out.println( "输出节点:" +
"\t"+node3.asXML());
System.out.println( "\n---------XPath获取List节点测试------------");
List list = document.selectNodes( "/doc/person[name=\"zhangsan\"]/adds/add");
for(Iterator it=list.iterator();it.hasNext();){
Node nodex=(Node)it.next();
System.out.println(nodex.asXML());
}
System.out.println( "\n---------通过ID获取元素的测试----------");
System.out.println( "陷阱:通过ID获取,元素ID属性名必须为“大写ID”,小写的“id”会认为是普通属性!");
String id22 = document.elementByID( "22").asXML();
String id23 = document.elementByID( "23").asXML();
String id24 = null;
if (document.elementByID( "24") != null) {
id24 = document.elementByID( "24").asXML();
} else {
id24 = "null";
}
System.out.println( "id22= " + id22);
System.out.println( "id23= " + id23);
System.out.println( "id24= " + id24);
}
public static void main(String args[]) {
testParseXMLData( "/person.xml");
}
}
import org.dom4j.io.SAXReader;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.Element;
import org.dom4j.Node;
import java.util.Iterator;
import java.util.List;
import java.io.InputStream;
/**
* Created by IntelliJ IDEA.<br>
* <b>User</b>: leizhimin<br>
* <b>Date</b>: 2008-3-26 15:53:51<br>
* <b>Note</b>: Dom4j遍历解析XML测试
*/
public class TestDom4j {
/**
* 获取指定xml文档的Document对象,xml文件必须在classpath中可以找到
*
* @param xmlFilePath xml文件路径
* @return Document对象
*/
public static Document parse2Document(String xmlFilePath) {
SAXReader reader = new SAXReader();
Document document = null;
try {
InputStream in = TestDom4j. class.getResourceAsStream(xmlFilePath);
document = reader.read(in);
} catch (DocumentException e) {
System.out.println(e.getMessage());
System.out.println( "读取classpath下xmlFileName文件发生异常,请检查CLASSPATH和文件名是否存在!");
e.printStackTrace();
}
return document;
}
public static void testParseXMLData(String xmlFileName) {
//产生一个解析器对象
SAXReader reader = new SAXReader();
//将xml文档转换为Document的对象
Document document = parse2Document(xmlFileName);
//获取文档的根元素
Element root = document.getRootElement();
//定义个保存输出xml数据的缓冲字符串对象
StringBuffer sb = new StringBuffer();
sb.append( "通过Dom4j解析XML,并输出数据:\n");
sb.append(xmlFileName + "\n");
sb.append( "----------------遍历start----------------\n");
//遍历当前元素(在此是根元素)的子元素
for (Iterator i_pe = root.elementIterator(); i_pe.hasNext();) {
Element e_pe = (Element) i_pe.next();
//获取当前元素的名字
String person = e_pe.getName();
//获取当前元素的id和sex属性的值并分别赋给id,sex变量
String id = e_pe.attributeValue( "id");
String sex = e_pe.attributeValue( "sex");
String name = e_pe.element( "name").getText();
String age = e_pe.element( "age").getText();
//将数据存放到缓冲区字符串对象中
sb.append(person + ":\n");
sb.append( "\tid=" + id + " sex=" + sex + "\n");
sb.append( "\t" + "name=" + name + " age=" + age + "\n");
//获取当前元素e_pe(在此是person元素)下的子元素adds
Element e_adds = e_pe.element( "adds");
sb.append( "\t" + e_adds.getName() + "\n");
//遍历当前元素e_adds(在此是adds元素)的子元素
for (Iterator i_adds = e_adds.elementIterator(); i_adds.hasNext();) {
Element e_add = (Element) i_adds.next();
String code = e_add.attributeValue( "code");
String add = e_add.getTextTrim();
sb.append( "\t\t" + e_add.getName() + ":" + " code=" + code + " value=\"" + add + "\"\n");
}
sb.append( "\n");
}
sb.append( "-----------------遍历end-----------------\n");
System.out.println(sb.toString());
System.out.println( "---------通过XPath获取一个元素----------");
Node node1 = document.selectSingleNode( "/doc/person");
System.out.println( "输出节点:" +
"\t"+node1.asXML());
Node node2 = document.selectSingleNode( "/doc/person/@sex");
System.out.println( "输出节点:" +
"\t"+node2.asXML());
Node node3 = document.selectSingleNode( "/doc/person[name=\"zhangsan\"]/age");
System.out.println( "输出节点:" +
"\t"+node3.asXML());
System.out.println( "\n---------XPath获取List节点测试------------");
List list = document.selectNodes( "/doc/person[name=\"zhangsan\"]/adds/add");
for(Iterator it=list.iterator();it.hasNext();){
Node nodex=(Node)it.next();
System.out.println(nodex.asXML());
}
System.out.println( "\n---------通过ID获取元素的测试----------");
System.out.println( "陷阱:通过ID获取,元素ID属性名必须为“大写ID”,小写的“id”会认为是普通属性!");
String id22 = document.elementByID( "22").asXML();
String id23 = document.elementByID( "23").asXML();
String id24 = null;
if (document.elementByID( "24") != null) {
id24 = document.elementByID( "24").asXML();
} else {
id24 = "null";
}
System.out.println( "id22= " + id22);
System.out.println( "id23= " + id23);
System.out.println( "id24= " + id24);
}
public static void main(String args[]) {
testParseXMLData( "/person.xml");
}
}
运行结果:
通过Dom4j解析XML,并输出数据:
/person.xml
----------------遍历start----------------
person:
id=1 sex=m
name=zhangsan age=32
adds
add: code=home value="home add"
add: code=com value="com add"
person:
id=2 sex=w
name=lisi age=22
adds
add: code=home value="home add"
add: code=com value="com add"
add: code=com value="com add"
-----------------遍历end-----------------
---------通过XPath获取一个元素----------
输出节点: < person id ="1" sex ="m" >
< name >zhangsan </ name >
< age >32 </ age >
< adds >
< add code ="home" >home add </ add >
< add code ="com" >com add </ add >
</ adds >
</ person >
输出节点: sex="m"
输出节点: < age >32 </ age >
---------XPath获取List节点测试------------
< add code ="home" >home add </ add >
< add code ="com" >com add </ add >
---------通过ID获取元素的测试----------
陷阱:通过ID获取,元素ID属性名必须为“大写ID”,小写的“id”会认为是普通属性!
id22= < add ID ="22" id ="23" code ="home" >home add </ add >
id23= < add ID ="23" id ="22" code ="com" >com add </ add >
id24= null
Process finished with exit code 0
/person.xml
----------------遍历start----------------
person:
id=1 sex=m
name=zhangsan age=32
adds
add: code=home value="home add"
add: code=com value="com add"
person:
id=2 sex=w
name=lisi age=22
adds
add: code=home value="home add"
add: code=com value="com add"
add: code=com value="com add"
-----------------遍历end-----------------
---------通过XPath获取一个元素----------
输出节点: < person id ="1" sex ="m" >
< name >zhangsan </ name >
< age >32 </ age >
< adds >
< add code ="home" >home add </ add >
< add code ="com" >com add </ add >
</ adds >
</ person >
输出节点: sex="m"
输出节点: < age >32 </ age >
---------XPath获取List节点测试------------
< add code ="home" >home add </ add >
< add code ="com" >com add </ add >
---------通过ID获取元素的测试----------
陷阱:通过ID获取,元素ID属性名必须为“大写ID”,小写的“id”会认为是普通属性!
id22= < add ID ="22" id ="23" code ="home" >home add </ add >
id23= < add ID ="23" id ="22" code ="com" >com add </ add >
id24= null
Process finished with exit code 0
发个Idea7开发界面截图:
点击图片放大
![](https://i-blog.csdnimg.cn/blog_migrate/4edfc675f9c545f9adabd6082a38dd1b.png)
想从头了解dom4j的朋友可以看dom4j文档中的quick start,这个是E文版的,另外有热心的网友已经将自己翻译的中文版奉献出来了,可以看看: