java之DocumentBuilderFactory解析xml

1、About documentBuilderFactory API description

1）、 javax.xml.parsers 包DocumentBuilderFactory创建DOM模式的解析器对象, DocumentBuilderFactory是抽象工厂类，不能直接实例化，但是有newInstance方法


2）、DocumentBuilderFactory.newInstance() 得到创建 DOM 解析器的工厂

DocumentBuilderFactory documentBuilderFactory = DocumentBuilderFactory.newInstance()

3）、newDocumentBuilder方法得到 DOM 解析器对象

DocumentBuilder documentBuilder = documentBuilderFactory.newDocumentBuilder();

4)、DOM解析器解析输入流，这里可以是XML，文档转化为输入流，或者字符串转为ByteArrayInputStream,DOM 解析器对象的 parse() 方法解析 XML 文档，得到代表整个文档的 Document 对象

InputStream is = new FileInputStream("xxx.xml");
documentBuilder.parse(is);
documentBuilder.parse(new ByteArrayInputStream(str.getBytes())); 

 
5)、得到 XML 文档的根节点

Element rootElement = document.getDocumentElement();

6)、得到节点的子节点

NodeList studentInfo = appElement.getChildNodes();

2、Test Demo

Student.java文件

package com.parse.doc;

public class Student {

public String name;
public String age;
public String sex;
public Student() {}

public String getName() {
return name;
}
public void setName(String name) {
this.name = name;
}
public String getAge() {
return age;
}
public void setAge(String age) {
this.age = age;
}
public String getSex() {
return sex;
}
public void setSex(String sex) {
this.sex = sex;
}
@Override
public String toString() {
return "name=" + name + ", age=" + age + ", sex=" + sex;
}
}

ParseXml.java文件

package com.parse.doc;

import java.io.ByteArrayInputStream;
import java.util.ArrayList;
import java.util.List;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;

import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.NodeList;


public class ParseXml {

public static String xml = "<Students><student><name><![CDATA[陈喻]]></name><age><![CDATA[26]]></age><sex><![CDATA[男]]></sex></student><student><name><![CDATA[陈彩凤]]></name><age><![CDATA[25]]></age><sex><![CDATA[女]]></sex></student><student><name><![CDATA[陈紫宣]]></name><age><![CDATA[2]]></age><sex><![CDATA[女]]></sex></student><student><name><![CDATA[陈紫曦]]></name><age><![CDATA[7个月]]></age><sex><![CDATA[女]]></sex></student></Students>";
public static final String STUDENT = "student";
public static final String NAME = "name";
public static final String AGE = "age";
public static final String SEX = "sex";

public static void main(String args[]) {
List<Student> students = parseXmlByDoc(xml);
if (students != null && students.size() > 0) {
for (Student student : students) {
System.out.println(student);
}
} else {
System.out.println("students size is 0");
}

}

public static List<Student> parseXmlByDoc(String str) {
if (str == null || "".equals(str)) {
System.out.println("str is null or ''");
return null;
}
DocumentBuilderFactory documentBuilderFactory = DocumentBuilderFactory.newInstance();
List<Student> students = new ArrayList<Student>();
DocumentBuilder documentBuilder;
try {
documentBuilder = documentBuilderFactory.newDocumentBuilder();
Document document = documentBuilder.parse(new ByteArrayInputStream(str.getBytes()));
Element rootElement = document.getDocumentElement();
NodeList studentNodeList = rootElement.getElementsByTagName(STUDENT);
for (int i = 0; i < studentNodeList.getLength(); i++) {
Element appElement = (Element) studentNodeList.item(i);
NodeList studentInfo = appElement.getChildNodes();
Student student = new Student();
for(int j = 0; j < studentInfo.getLength(); j++) { 
Element element = (Element) studentInfo.item(j);
String appAttr = element.getTagName();
switch (appAttr) {
case NAME:
student.setName(element.getTextContent());
break;
case AGE:
student.setAge(element.getTextContent());
break;
case SEX:
student.setSex(element.getTextContent());
break;
default:
break;
} 
}
students.add(student);
}
} catch (Exception e) {
e.printStackTrace();
return null;
}
return students;
}
}

3、Running results

name=陈喻, age=26, sex=男
name=陈彩凤, age=25, sex=女
name=陈紫宣, age=2, sex=女
name=陈紫曦, age=7个月, sex=女