四种解析方式:
DOM解析、SAX解析、DOM4J解析、JDOM解析(其中DOM解析和SAX解析时java官方提供给我们解析xml文档的方式,所以我们不需要额外引入一些jar包;但是DOM4J和JDOM解析是其他组织利用他们的方式去解析xml文件的,所以我们在运用这两种解析方式的时候,需要额外下载一些jar包,导入到我们的工程中)
示例:解析写好的book.xml文件,并存入JAVA对象。book.xml文件如下:
<?xml version="1.0" encoding="UTF-8"?>
<bookstore>
<book id="1">
<name>冰与火之歌</name>
<author>乔治马丁</author>
<year>2014</year>
<price>89</price>
</book>
<book id="2">
<name>安徒生童话</name>
<year>2004</year>
<price>77</price>
<language>英文</language>
</book>
</bookstore>
根据book.xml创建Book对象如下:
package day13;
/**
* @ClassName: Book
* @Description TODO
* @Author:
* @Created: 2018/8/13 18:35
* @Version: 1.0
*/
public class Book {
private String id;
private String name;
private String author;
private String price;
private String year;
private String language;
public Book() {
}
public String getId() {
return id;
}
public String getName() {
return name;
}
public String getAuthor() {
return author;
}
public String getPrice() {
return price;
}
public String getYear() {
return year;
}
public String getLanguage() {
return language;
}
public void setId(String id) {
this.id = id;
}
public void setName(String name) {
this.name = name;
}
public void setAuthor(String author) {
this.author = author;
}
public void setPrice(String price) {
this.price = price;
}
public void setYear(String year) {
this.year = year;
}
public void setLanguage(String language) {
this.language = language;
}
@Override
public String toString() {
return "Book [id=" + id + ", name=" + name + ", author=" + author + ", price=" + price + ", year=" + year
+", language=" + language + "]";
}
}
一、DOM方式解析xml步骤:
package day13;
import org.w3c.dom.*;
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import java.util.ArrayList;
/**
* @ClassName: DomParse
* @Description TODO
* @Author:
* @Created: 2018/8/13 18:46
* @Version: 1.0
*/
public class DomParse {
public static void main(String[] args) {
//arrayList用于存放解析出来的BOOK对象
ArrayList<Book> arrayList = new ArrayList<>();
//1、创建一个DocumentBuilderFactory的对象
DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
try{
//2、创建一个DocumentBuilder的对象
DocumentBuilder db = dbf.newDocumentBuilder();
//3、通过DocumentBuilder对象的parse(String fileName)方法加载book.xml文件到当前项目下
Document document = db.parse("src/day13/book.xml");
//开始解析
//4、通过标签名获取节点集合(获取所有book节点的集合)
NodeList bookList = document.getElementsByTagName("book");
System.out.println("book节点的个数:"+bookList.getLength());
//遍历每一个Book节点
for(int i=0; i<bookList.getLength();i++){
//new一个Book对象
Book bookNode = new Book();
//通过item(i)方法获取一个book节点
Node book = bookList.item(i);
//前提,已知book节点有且只能有1个id属性
//可以直接获取id属性值
Element element=(Element) bookList.item(i);
String attrValue = element.getAttribute("id");
System.out.println("id属性的属性值:"+attrValue);
//获取的id属性set到Book对象
bookNode.setId(attrValue);
//解析book节点的子节点
NodeList childNodes = book.getChildNodes();
System.out.println("第"+(i+1)+"本书共有"+childNodes.getLength()+"个子节点");
//遍历childNodes获取每个节点的节点名以及节点值
for(int j=0; j<childNodes.getLength(); j++){
//判断当前节点是否为元素节点
if(childNodes.item(j).getNodeType() == Node.ELEMENT_NODE){
//获取节点属性名
String name = childNodes.item(j).getNodeName();
//根据节点属性名将获取的属性值set到Book对象中
switch (name) {
case "name":
bookNode.setName(childNodes.item(j).getTextContent());
break;
case "author":
bookNode.setAuthor(childNodes.item(j).getTextContent());
break;
case "year":
bookNode.setYear(childNodes.item(j).getTextContent());
break;
case "price":
bookNode.setPrice(childNodes.item(j).getTextContent());
break;
case "language":
bookNode.setLanguage(childNodes.item(j).getTextContent());
break;
default:
break;
}
}
}
arrayList.add(bookNode);
}
}catch (Exception e){
e.printStackTrace();
}
System.out.println(arrayList);
}
}
二、SAX解析
package day13;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;
import java.util.ArrayList;
import java.util.List;
/**
* @ClassName: SAXParserHandler
* @Description SAX处理程序(如何解析xml文档)
* @Author:
* @Created: 2018/8/13 19:45
* @Version: 1.0
*/
public class SAXParserHandler extends DefaultHandler {
private String value = null;
private List<Book> bookList = new ArrayList<>();
private Book book = null;
/**
* 用来标识解析开始
*/
@Override
public void startDocument() throws SAXException {
super.startDocument();
}
/**
* 用来标识解析结束
*/
@Override
public void endDocument() throws SAXException {
super.endDocument();
}
/**
* 开始标签时调用
*
* @param qName: 表示开始标签的标签名
* @param attributes: 表示开始标签内包含的(属性)【列表】
*/
@Override
public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
//调用DefaultHandler中的startElement方法
super.startElement(uri, localName, qName, attributes);
//开始解析book元素属性
if (qName.equals("book")) {
//已知book元素下属性的属性名称,根据名称获取属性值
String id = attributes.getValue("id");
System.out.println("book的属性值:"+id);
//将id属性set到Book对象中
book = new Book();
book.setId(id);
//不知道book元素下属性的属性名称
int num = attributes.getLength();
//遍历属性
for (int i=0; i<num; i++){
System.out.println("book元素的第"+(i+1)+"个属性名是:"+attributes.getQName(i));
System.out.println("---属性值是:"+attributes.getValue(i));
}
}else if (!qName.equals("book") && !qName.equals("bookstore")){
System.out.println("节点名是:"+qName);
}
}
/**
* 结束标签时调用
*
* @param qName: 结束标签的标签名称
*/
@Override
public void endElement(String uri, String localName, String qName) throws SAXException {
super.endElement(uri, localName, qName);
switch (qName) {
case "book":
bookList.add(book);
book = null;
break;
case "name":
book.setName(value);
break;
case "author":
book.setAuthor(value);
case "year":
book.setYear(value);
break;
case "language":
book.setLanguage(value);
break;
case "price":
book.setPrice(value);
break;
}
}
/**
* 读到文本内容的时调用
*
* @param ch: 表示当前读完的所有文本内容
* @param start: 表示当前文本内容的开始位置
* @param length: 表示当前文本内容的长度
*/
@Override
public void characters(char[] ch, int start, int length) throws SAXException {
super.characters(ch, start, length);
value = new String(ch, start, length);
}
public List<Book> getBookList() {
return bookList;
}
public void setBookList(List<Book> bookList) {
this.bookList = bookList;
}
}
三、DOM4J解析--注意:使用Dom4解析,需下载dom4j相应的jar文件
Dom4j递归遍历所有节点方法如下:
package day13;
import org.dom4j.Attribute;
import org.dom4j.Element;
import java.util.List;
/**
* @ClassName: Dom4jParse
* @Description 通过element方法递归遍历所有节点
* @Author:
* @Created: 2018/8/14 7:39
* @Version: 1.0
*/
public class Dom4jParse {
/**
*@Description 递归遍历所有父节点、子节点
*@Author:
*@Date: 2018/8/14
*@param: [element]
*@return: void
*/
public void dom4jParse(Element element) {
System.out.println(element.getName() + ":" + element.getText().trim());
//从book根节点开始遍历,以【属性=值】的形式存为一个Attribute对象存储在list中
List<Attribute> attributeList = element.attributes();
for (Attribute attribute : attributeList) {
//每循环一次,解析次节点的一个【属性=值】,没有则输出空
String name = attribute.getName();
String value = attribute.getValue();
System.out.println(name + "=" + value);
}
List<Element> elementList = element.elements();
//递归遍历父节点下的所有子节点
for (Element e : elementList) {
dom4jParse(e);
}
}
}
DOM4J测试:
package day13;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.Element;
import org.dom4j.io.SAXReader;
/**
* @ClassName: Dom4jParseTest
* @Description TODO
* @Author: heyuan@iflytek.com
* @Created: 2018/8/13 20:22
* @Version: 1.0
*/
public class Dom4jParseTest {
public static void main(String[] args) throws Exception{
//构造SAXReader对象
SAXReader saxReader = new SAXReader();
try {
//通过read方法读取xml文件转换成Document对象
Document document = saxReader.read("src/day13/book.xml");
//获取根节点元素对象
Element element = document.getRootElement();
//创建Dom4jParse解析对象
Dom4jParse dom4jParse = new Dom4jParse();
//调用解析方法
dom4jParse.dom4jParse(element);
}catch (DocumentException e){
e.printStackTrace();
}
}
}
四、JDOM解析
package day13;
import org.dom4j.Element;
import org.jdom.Attribute;
import org.jdom.Document;
import org.jdom.input.SAXBuilder;
import java.io.FileInputStream;
import java.io.InputStream;
import java.util.List;
/**
* @ClassName: JDomParse
* @Description TODO
* @Author:
* @Created: 2018/8/14 9:07
* @Version: 1.0
*/
public class JDomParse {
public static void main(String[] args) {
//1、创建SAXBuilder对象
SAXBuilder saxBuilder = new SAXBuilder();
InputStream in;
try {
//2、创建输入流,并将xml文件加载到输入流中
in = new FileInputStream("src/day13/book.xml");
//3、将输入流加载到SAXBuilder对象中
Document document = saxBuilder.build(in);
//4、获取根元素
org.jdom.Element element = document.getRootElement();
//5、获取根元素所以的子元素
List<org.jdom.Element> childList = element.getChildren();
//6、遍历每一个子元素
for (org.jdom.Element child : childList){
System.out.println("=====开始读取第"+(childList.indexOf(child)+1)+"本书的信息");
//7-1、如果不知道属性有哪些,使用Element.getAttributes获取属性,并遍历属性
List<Attribute> attrList = child.getAttributes();
for(Attribute attr : attrList) {
System.out.println("属性名:" + attr.getName() + "-->属性值:" + attr.getValue());
}
//7-2、如果知道属性有哪些,可以直接调用Element.getAttributeValue(String name)获取对应的属性值
System.out.println("已知有id属性,id属性的值为" + child.getAttributeValue("id"));
//8、获取所有子节点,并调用Element.getName()方法获取节点名,调用Element.getVlaue()方法获取节点值
List<org.jdom.Element> list = child.getChildren();
for(org.jdom.Element ele : list) {
System.out.println("子节点:" + ele.getName() + "--->子节点的值:" + ele.getValue());
}
}
}catch (Exception e){
e.printStackTrace();
}
}
}