java解析xml

1.DOM方式解析XML
Dom解析是将xml文件全部载入到内存，组装成一颗dom树，然后通过节点以及节点之间的关系来解析xml文件,与平台无关,java提供的一种基础的解析XML文件的API,理解较简单，但是由于整个文档都需要载入内存,不适用于文档较大时。

2.SAX方式解析XML
基于事件驱动,逐条解析,适用于只处理xml数据，不易编码,而且很难同时访问同一个文档中的多处不同数据

3.JDOM方式解析XML
简化与XML的交互并且比使用DOM实现更快,仅使用具体类而不使用接口因此简化了API,并且易于使用

4.DOM4j方式解析XML
JDOM的一种智能分支,功能较强大，建议熟练使用

下面贴出第四种方式DOM4j的具体使用：
需要解析的xml：

<?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>
        <author>安徒生</author>
        <year>2004</year>
        <price>77</price>
    </book>
    <book id="3">
        <name>think think think</name>
        <author>aaa</author>
        <year>1997</year>
        <price>100</price>
    </book>
</bookstore>

工程中引入以下依赖：

        <dependency>
            <groupId>dom4j</groupId>
            <artifactId>dom4j</artifactId>
            <version>1.6.1</version>
        </dependency>

        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>1.2.62</version>
        </dependency>

创建几个bean对象用于存储数据：

package com.qs.bean;
public class Book {
    private Integer id;
    private String name;
    private String author;
    private Integer year;
    private double price;

    public Integer getId() {
        return id;
    }

    public void setId(Integer id) {
        this.id = id;
    }

    public String getName() {
        return name;
    }

    public void setName(String name) {
        this.name = name;
    }

    public String getAuthor() {
        return author;
    }

    public void setAuthor(String author) {
        this.author = author;
    }

    public Integer getYear() {
        return year;
    }

    public void setYear(Integer year) {
        this.year = year;
    }

    public double getPrice() {
        return price;
    }

    public void setPrice(double price) {
        this.price = price;
    }
}

package com.qs.beanxml;

import com.qs.bean.Book;

import java.util.List;

public class BookStore {
    private List<Book> bookstore;

    public List<Book> getBookstore() {
        return bookstore;
    }
    
    public void setBookstore(List<Book> bookstore) {
        this.bookstore = bookstore;
    }
}

package com.qs.parsexml;

import com.alibaba.fastjson.JSON;
import com.alibaba.fastjson.JSONArray;
import com.qs.bean.Book;
import com.qs.beanxml.BookStore;
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.ArrayList;
import java.util.Iterator;
import java.util.List;

/**
 * 用DOM4J方法解析xml文件
 *
 */
public class ParseXmlByDom4j {
    public static BookStore parseBookStoreXML(File file) {
        SAXReader reader = new SAXReader();
        BookStore bookStore = new BookStore();
        try {
            //获取操作文档对象
            Document document = reader.read(file);
            Element rootElement = document.getRootElement();
            //获取这个元素直接子节点的迭代器
            Iterator it = rootElement.elementIterator();
            //开始解析rootElement下的内容
            List<Book> bookList = new ArrayList<>();
            Book book = null;
            while (it.hasNext()) {
                book = new Book();
                Element bookElement = (Element) it.next();
                //遍历bookElement的所有属性
                List<Attribute> attributes = bookElement.attributes();
                for (Attribute attribute : attributes) {
                    if (attribute.getName().equals("id")) {
                        String id = attribute.getValue();
                        book.setId(Integer.parseInt(id));
                    }
                }
                Iterator bookit = bookElement.elementIterator();
                while (bookit.hasNext()) {
                    Element next = (Element) bookit.next();
                    String nodeName = next.getName();
                    String value = next.getStringValue();
                    if ("name".equals(nodeName)) {
                        book.setName(value);
                    } else if ("author".equals(nodeName)) {
                        book.setAuthor(value);
                    } else if ("year".equals(nodeName)) {
                        book.setYear(Integer.parseInt(value));
                    } else if ("price".equals(nodeName)) {
                        book.setPrice(Double.parseDouble(value));
                    }
                }
                bookList.add(book);
            }
            bookStore.setBookstore(bookList);
        } catch (DocumentException e) {
            e.printStackTrace();
            return null;
        }
        return bookStore;
    }

    public static void main(String[] args) {
        //注意此处是实际文件的路径
        BookStore bookStore = parseBookStoreXML(new File("E:/IDEWorkSpace/IdeaWorkSpace/MyWorkSpace/java_xml/doc/books.xml"));
        System.out.println(JSON.toJSONString(bookStore));
    }
}

上个文件改进之后：

package com.qs.parsexml;

import com.alibaba.fastjson.JSON;
import com.qs.bean.Book;
import com.qs.beanxml.BookStore;
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.ArrayList;
import java.util.Iterator;
import java.util.List;

/**
 * 用DOM4J方法读取xml文件
 * (将上个文件重新封装改进了一下)
 */
public class ParseXmlByDom4j {
    public static BookStore parseBookStoreXML(File file) {
        SAXReader reader = new SAXReader();
        BookStore bookStore = new BookStore();
        try {
            //获取操作文档对象
            Document document = reader.read(file);
            Element rootElement = document.getRootElement();
            //获取这个元素直接子节点的迭代器
            Iterator it = rootElement.elementIterator();
            //开始解析rootElement下的内容
            List<Book> bookList = new ArrayList<>();
            Book book = null;
            while (it.hasNext()) {
                book = new Book();
                Element bookElement = (Element) it.next();
                //指定获取某个元素的属性值
                String bookId = getValueByAttribute(bookElement, "id");
                //设置bookId
                if (bookId != null) {
                    book.setId(Integer.parseInt(bookId));
                }
                //指定获取book标签下的子标签的内容
                String nameValue = getValueByElement(bookElement, "name");
                String authorValue = getValueByElement(bookElement, "author");
                String yearValue = getValueByElement(bookElement, "year");
                String priceValue = getValueByElement(bookElement, "price");
                //设置book的其他字段
                book.setName(nameValue);
                book.setAuthor(authorValue);
                book.setYear(Integer.parseInt(yearValue));
                book.setPrice(Double.parseDouble(priceValue));
                //添加到list中
                bookList.add(book);
            }
            bookStore.setBookstore(bookList);
        } catch (DocumentException e) {
            e.printStackTrace();
            return null;
        }
        return bookStore;
    }

    //指定获取某个元素的内容
    private static String getValueByElement(Element element, String needElement) {
        String value = null;
        Iterator it = element.elementIterator();
        while (it.hasNext()) {
            Element next = (Element) it.next();
            String nodeName = next.getName();
            if (needElement.equals(nodeName)) {
                value = next.getStringValue();
                break;
            }
        }
        return value;
    }

    //获取一个节点元素的某个属性值
    private static String getValueByAttribute(Element element, String attribute) {
        String value = null;
        //遍历bookElement的所有属性
        List<Attribute> attributes = element.attributes();
        for (Attribute attr : attributes) {
            if (attribute.equals(attr.getName())) {
                value = attr.getValue();
                break;
            }
        }
        return value;
    }


    public static void main(String[] args) {
       //注意此处是实际xml文件的存放路径
        BookStore bookStore = parseBookStoreXML(new File("E:/IDEWorkSpace/IdeaWorkSpace/MyWorkSpace/java_xml/doc/books.xml"));
        System.out.println(".................................");
        System.out.println(JSON.toJSONString(bookStore));
    }
}

输出结果：

{
	"bookstore": [
		{
			"author": "乔治马丁",
			"id": 1,
			"name": "冰与火之歌",
			"price": 89.0,
			"year": 2014
		},
		{
			"author": "安徒生",
			"id": 2,
			"name": "安徒生童话",
			"price": 77.0,
			"year": 2004
		},
		{
			"author": "aaa",
			"id": 3,
			"name": "think think think",
			"price": 100.0,
			"year": 1997
		}
	]
}