java里面4种关于xml的解析方法

以下资料来源于 imooc

imooc学习资料：http://www.imooc.com/learn/171

推荐大家使用第四种方法；；；

4中关于解析xml的方法：

DOM，SAX ( java 里面提供包 )

JDOM,DOM4J ( 需要自己导入包文件 )

1：DOM

package com.sdingba.xmlparser;
import org.w3c.dom.*;
import org.xml.sax.SAXException;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import java.io.IOException;
import java.util.List;
/**
* Created by su on 16-4-30.
*
* DOM解析  xml文件
*
* 一次性加载内存
* 优点：
*      形成树的结构，直观好理解，代码更容易编写
*      解析过程中树结构保留在内存中，方便修改
*
* 缺点：
*      当xml文件较大时，对内存的消耗不比较大，
*      容易影响解析性能，并赵成内存溢出
*/
public class DOM {

public static void main(String[] args) {
//创建一个DocumentBuilderFactory对象
DocumentBuilderFactory dbf =
DocumentBuilderFactory.newInstance();

//创建一个DocumentBuilder对象
try {
DocumentBuilder db = dbf.newDocumentBuilder();

//通过DocumentBuilder对象的parse解析，加载xml文件
Document document = db.parse("new.xml");

//获取所有book的集合
NodeList bookList = document.getElementsByTagName("book");

for (int i=0;i<bookList.getLength();i++) {
//                通过  获取一个book的数据
Node books = (Node) bookList.item(i);
//获取book节点的所有属性的集合
NamedNodeMap attrs = books.getAttributes();
//遍历book的属性,
for (int j = 0; j < attrs.getLength(); j++) {
//通过item获取某一个属性
attrs.item(j).getNodeName();
//获取属性值  getNodeValue();
System.out.println("id == "+attrs.item(j).getNodeValue());
}

//                //前提book节点 有且只有一个：
//                Element book = (Element) bookList.item(i);
//                 //sttrValue 为 book里面的id值
//                String attrValue = book.getAttribute("id");
//                System.out.println(attrValue);

NodeList chileNodes = books.getChildNodes();
//遍历chileNode的节点和节点名
for (int k = 0; k < chileNodes.getLength(); k++) {
//区分text类型的node以及element的类型
if (chileNodes.item(k).getNodeType() == Node.ELEMENT_NODE) {
//获取的element类型的节点的节点名
String aa = chileNodes.item(k).getNodeName();
System.out.print(aa+"   =====    :      ");
//bb2   为空；
String bb2 = chileNodes.item(k).getNodeValue();

String bb = chileNodes.item(k).getFirstChild().getNodeValue();
//                        String bb = chileNodes.item(k).getTextContent();
System.out.println(bb);
}
}
}
} catch (ParserConfigurationException e) {
e.printStackTrace();
} catch (SAXException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
}

2,SAX

package com.sdingba.xmlparser;

import com.sdingba.javabean.Book;
import com.sun.org.apache.bcel.internal.generic.IF_ACMPEQ;
import com.sun.xml.internal.bind.v2.model.core.ID;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;

import javax.xml.parsers.ParserConfigurationException;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import java.io.IOException;
import java.util.ArrayList;

/**
* Created by su on 16-4-30.
* Handler  解析原理
*
* 基于事件的解析，一条一条的解析
*
* 优点：
*      采用事件驱动模式，对内存的消耗比较小
*      适合于只需要处理xml数据时
* 缺点，不易编码
*      很难同时访问一个xml中的多个不同的数据
*/
public class SAX {
public static void main(String[] args) {

//1.通过SAXparserFactory 的实例
SAXParserFactory factory = SAXParserFactory.newInstance();

try {
//通过factory获取SAXParser的实例
SAXParser parser = factory.newSAXParser();

SAXParserHandler handler = new SAXParserHandler();
parser.parse("new.xml", handler);

int a = handler.getBookList().size();
for (Book book : handler.getBookList()) {
System.out.println("id = "+book.getId());
System.out.println(book.getName());
System.out.println(book.getAuthor());
System.out.println(book.getYear());
System.out.println(book.getPrice());
System.out.println(book.getLanguage());
System.out.println("-------finish-------");
}

} catch (ParserConfigurationException e) {
e.printStackTrace();
} catch (SAXException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}

static class SAXParserHandler extends DefaultHandler {
Book book;

public ArrayList<Book> getBookList() {
return bookList;
}

public void setBookList(ArrayList<Book> bookList) {
this.bookList = bookList;
}

private  ArrayList<Book> bookList = new ArrayList<Book>();
String value = null;
private int bookIndex = 0;

/**
* 解析开始
*
* @throws SAXException
*/
@Override
public void startDocument() throws SAXException {
super.startDocument();
System.out.println("解析开始");
}

/**
* 解析结束
*
* @throws SAXException
*/
@Override
public void endDocument() throws SAXException {
super.endDocument();
System.out.println("解析结束");
}

/**
* 用来遍历xml文件的开始标签
*
* @throws SAXException
*/
@Override
public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
super.startElement(uri, localName, qName, attributes);
//
if (qName.equals("book")) {
bookIndex++;
book = new Book();
System.out.println("开始第" + bookIndex + "本书的解析======");
//以知 book元素的属性
String value = attributes.getValue("id");
System.out.println("book+" + value);//book+2

//如果不知道book元素的属性值
int num = attributes.getLength();
for (int i = 0; i < num; i++) {
System.out.println(attributes.getQName(i));//属性名 id
System.out.println("属性值“===" + attributes.getValue(i));
if (attributes.getQName(i).equals("id")) {
book.setId(attributes.getValue(i));
}
}
} else if (!qName.equals("book") && !qName.equals("bookstore")) {
System.out.println("节点名”" + qName);

}
}

/**
* 用来遍历xml文件的结束标签
*
* @throws SAXException
*/
@Override
public void endElement(String uri, String localName, String qName) throws SAXException {
//调用DefaultHandler类的startElement方法；
super.endElement(uri, localName, qName);
//判断是否针对一本书进行遍历
if (qName.equals("book")) {
bookList.add(book);
book = null;
System.out.println("=====结束" + bookIndex + "的解析");
} else if (qName.equals("name")) {
book.setName(value);
} else if (qName.equals("author")) {
book.setAuthor(value);
} else if (qName.equals("year")) {
book.setYear(value);
} else if (qName.equals("price")) {
book.setPrice(value);
} else if (qName.equals("language")) {
book.setLanguage(value);
}

}

/**
* @param ch ,,整个共享xml文档的内容
*           start 开始节点
*           length 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);
if (!value.trim().equals("")) {
System.out.println("节点值是：：" + value);
}
}
}

}

3，JDOM

package com.sdingba.xmlparser;

import org.jdom2.Attribute;
import org.jdom2.Document;
import org.jdom2.Element;
import org.jdom2.JDOMException;
import org.jdom2.input.SAXBuilder;

import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStream;
import java.util.List;

/**
* Created by su on 16-5-1.
* 不是java官方提高的，。需要导入jar包
*
*
*
*/
public class JDOM {

public static void main(String[] args) {

//进行对new。xml文件的解析
//1，
SAXBuilder saxBuilder = new SAXBuilder();

try {
//2,创建一个输入流
InputStream in = new FileInputStream("new.xml");
//3,通过saxBuiler的build的方法，将输入流加载到sax里面
Document document = saxBuilder.build(in);
//通过decument对象，。获取xml文件的根节点
Element rootElement = document.getRootElement();
//获取根节点下的子节点,集合
List<Element> booklist = rootElement.getChildren();
//继续进行解析
for (Element book : booklist) {
System.out.println("开始解析第" +
booklist.indexOf(book) + 1 + "本书=====");

//解析book的属性，
List<Attribute> attrList = book.getAttributes();
/*
//如果知道属性值的时候，可以选择下面这行代码获取属性值
String aaaa = book.getAttributeValue("id");
System.out.println(aaaa);  //aaaa  = 1，和下面的for循环里面的一样效果
*/
//遍历属性名,针对不清楚book下的属性值
for (Attribute attribute : attrList) {
//获取属性名
String attrName = attribute.getName();
//获取属性值
String attrValue = attribute.getValue();
System.out.println(attrName + "---" + attrValue);

}
//对book节点的子节点的节点名以及节点值进行遍历
List<Element> bookChilds = book.getChildren();
for (Element chile : bookChilds) {
String name = chile.getName();
String value = chile.getValue();
System.out.print(name+"    ----   ");
System.out.println(value);
}
//对book节点的子节点的节点名和接地安置
System.out.println("结束解析第" +
booklist.indexOf(book) + 1 + "本书=====");
}

} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (JDOMException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
}

4,DOM4J

package com.sdingba.xmlparser;

import org.dom4j.Attribute;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.Element;
import org.dom4j.io.SAXReader;

import java.io.File;
import java.util.Iterator;
import java.util.List;

/**
* Created by su on 16-5-1.
* jdom的一种智能分支，
*
*/
public class Dom4J {
public static void main(String[] args) {
//创建SAXReader的duixaing
SAXReader reader = new SAXReader();
//通富哦reader对象read
try {
//          Document document = reader.read("new.xml");
Document document = reader.read(new File("new.xml"));

//通过document对象获取根节点
Element bookStore = document.getRootElement();

/* //如果你知道很多属性，只要求获取某些属性
String bookname = bookStore.element("book").element("name").getText();
System.out.println(bookname);//直接打印书名：你是我的女神
*/
//通过elementIterator方法获取迭代器
Iterator<Element> it = bookStore.elementIterator();
//遍历迭代器
while (it.hasNext()) {
System.out.println("======开始遍历莫一本书");
Element book = (Element) it.next();
//获取book的属性名和属性值
List<Attribute> bookAttrs = book.attributes();
for (Attribute attr : bookAttrs) {
String name = attr.getName();
String vale = attr.getValue();
System.out.println(name + "---" + vale);
}
Iterator iit = book.elementIterator();
while (iit.hasNext()) {
Element bookClild = (Element) iit.next();
String value = bookClild.getStringValue();
String name = bookClild.getName();
System.out.println(name + "=---=" + value);
}
System.out.println("======结束遍历某一本书");
}
} catch (DocumentException e) {
e.printStackTrace();
}
}
}

DOM4J 其他的方式：

//创建SAXReader的duixaing
SAXReader reader = new SAXReader();
//通富哦reader对象read
try {
//          Document document = reader.read("new.xml");
Document document = reader.read(new File("new.xml"));

//通过document对象获取根节点
Element bookStore = document.getRootElement();
List<Element> elementList = bookStore.elements();
for (Element ele : elementList) {
List<Element> elementss = ele.elements();
//                String value1 = ele.getText();
//                String value = ele.getStringValue();//
//                String name = ele.getName();
//                System.out.println(value);
System.out.println();
for (Element eles : elementss) {
String val = eles.getText();
String namenode = eles.getName();
System.out.println(namenode + " ==== " + val);
}
}

下面的xml文件是上面的四段代码解析的文件；

<?xml version="1.0" encoding="UTF-8" ?>
<bookstore>
<book id="1">
<name>你是我的女神</name>
<author>sdingba</author>
<year>2016</year>
<price>89</price>
</book>
<book id="2">
<name>你是我的女神2</name>
<author>sdingba2</author>
<year>2017</year>
<price>88</price>
</book>
</bookstore>

ssssssssssssssssssssssssssssssssssssssssssss

<?xml version="1.0" encoding="UTF-8"?>

<书架>
<书>
<书名>Java就业培训教程</书名>
<作者>张</作者>
<售价>39.00元</售价>
</书>
<书>
<书名>JavaScript网页开发</书名>
<作者>张</作者>
<售价>28.00元</售价>
</书>
</书架>

public static void main(String[] args) throws Exception {
//如果实在 web中
//      1,      InputStream aaInputStream =     request.getInputStream();
//      2,      SAXReader reader = new SAXReader();
//     3,       Document dom = reader.read(aaInputStream);
//1.获取解析器
SAXReader reader = new SAXReader();
//2.解析xml获取代表整个文档的dom对象
Document dom = reader.read("book.xml");

//3.获取根节点
Element root = dom.getRootElement();

//4.获取书名进行打印
String bookName = root.element("书").element("书名").getText();
System.out.println(bookName);
}

@Test
public void attr() throws Exception{
SAXReader reader = new SAXReader();
Document dom = reader.read("book.xml");
Element root = dom.getRootElement();

Element bookEle = root.element("书");
//bookEle.addAttribute("出版社", "传智出版社");
//      String str = bookEle.attributeValue("出版社");
//      System.out.println(str);
Attribute attr = bookEle.attribute("出版社");
attr.getParent().remove(attr);

XMLWriter writer = new XMLWriter(new FileOutputStream("book.xml"),OutputFormat.createPrettyPrint());
writer.write(dom);
writer.close();
}

@Test
public void del() throws Exception{
SAXReader reader = new SAXReader();
Document dom = reader.read("book.xml");
Element root = dom.getRootElement();

Element price2Ele = root.element("书").element("特价");
price2Ele.getParent().remove(price2Ele);

XMLWriter writer = new XMLWriter(new FileOutputStream("book.xml"),OutputFormat.createPrettyPrint());
writer.write(dom);
writer.close();
}

@Test
public void update()throws Exception{
SAXReader reader = new SAXReader();
Document dom = reader.read("book.xml");
Element root = dom.getRootElement();

root.element("书").element("特价").setText("4.0元");

XMLWriter writer = new XMLWriter(new FileOutputStream("book.xml"),OutputFormat.createPrettyPrint());
writer.write(dom);
writer.close();
}

@Test
public void add()throws Exception{
SAXReader reader = new SAXReader();
Document dom = reader.read("book.xml");
Element root = dom.getRootElement();
//凭空创建<特价>节点,设置标签体
Element price2Ele = DocumentHelper.createElement("特价");
price2Ele.setText("40.0元");
//获取父标签<书>将特价节点挂载上去
Element bookEle = root.element("书");
bookEle.add(price2Ele);

//将内存中的dom树会写到xml文件中,从而使xml中的数据进行更新
//      FileWriter writer = new FileWriter("book.xml");
//      dom.write(writer);
//      writer.flush();
//      writer.close();
XMLWriter writer = new XMLWriter(new FileOutputStream("book.xml"),OutputFormat.createPrettyPrint());
writer.write(dom);
writer.close();
}

@Test
public void find() throws Exception{
SAXReader reader = new SAXReader();
Document dom = reader.read("book.xml");
Element root = dom.getRootElement();

List<Element> list =  root.elements();
Element book2Ele = list.get(1);
System.out.println(book2Ele.element("书名").getText());

}