下面本文示例中，读取的XML内容
<?xml version="1.0" encoding="UTF-8"?>
<bookstore>
<book category="COOKING" aaaaaa="111111">
<title lang="en">Everyday Italian</title>
<author>Giada De Laurentiis</author>
<year>2005</year>
<price>30.00</price>
</book>
<book category="CHILDREN">
<title lang="en">Harry Potter</title>
<author>J K. Rowling</author>
<year>2005</year>
<price>29.99</price>
</book>
<book category="WEB">
<title lang="en">XQuery Kick Start</title>
<author>James McGovern</author>
<author>Per Bothner</author>
<author>Kurt Cagle</author>
<author>James Linn</author>
<author>Vaidyanathan Nagarajan</author>
<year>2003</year>
<price>49.99</price>
</book>
<book category="WEB">
<title lang="en">Learning XML</title>
<author>Erik T. Ray</author>
<year>2003</year>
<price>39.95</price>
</book>
</bookstore>
基于Filter的方式解析XML
package com.jadyer.demo.xml;
import org.apache.commons.io.IOUtils;
import javax.xml.stream.EventFilter;
import javax.xml.stream.XMLEventReader;
import javax.xml.stream.XMLInputFactory;
import javax.xml.stream.events.XMLEvent;
import java.io.InputStream;
import java.nio.charset.StandardCharsets;
/**
* StAX(Streaming API for XML)的方式解析XML
* Created by 玄玉<https://jadyer.cn/> on 2013/03/19 15:03.
*/
public class StaxXMLDemo {
public static void main(String[] args) throws Exception {
String xmlStr = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n" +
"<bookstore>\n" +
" <book category=\"COOKING\" aaaaaa=\"111111\">\n" +
" <title lang=\"en\">Everyday Italian</title>\n" +
" <author>Giada De Laurentiis</author>\n" +
" <year>2005</year>\n" +
" <price>30.00</price>\n" +
" </book>\n" +
" <book category=\"CHILDREN\">\n" +
" <title lang=\"en\">Harry Potter</title>\n" +
" <author>J K. Rowling</author>\n" +
" <year>2005</year>\n" +
" <price>29.99</price>\n" +
" </book>\n" +
" <book category=\"WEB\">\n" +
" <title lang=\"en\">XQuery Kick Start</title>\n" +
" <author>James McGovern</author>\n" +
" <author>Per Bothner</author>\n" +
" <author>Kurt Cagle</author>\n" +
" <author>James Linn</author>\n" +
" <author>Vaidyanathan Nagarajan</author>\n" +
" <year>2003</year>\n" +
" <price>49.99</price>\n" +
" </book>\n" +
" <book category=\"WEB\">\n" +
" <title lang=\"en\">Learning XML</title>\n" +
" <author>Erik T. Ray</author>\n" +
" <year>2003</year>\n" +
" <price>39.95</price>\n" +
" </book>\n" +
"</bookstore>";
new StaxXMLDemo().filterParseXML(xmlStr);
}
/**
* 基于Filter的方式解析XML
* 可以有效的过滤掉不用进行操作的节点，效率会高一些
*/
private void filterParseXML(String xmlStr) throws Exception {
XMLInputFactory factory = XMLInputFactory.newInstance();
//InputStream is = StaxXMLDemo.class.getClassLoader().getResourceAsStream("books.xml")
InputStream is = IOUtils.toInputStream(xmlStr, StandardCharsets.UTF_8);
XMLEventReader reader = factory.createFilteredReader(factory.createXMLEventReader(is),
new EventFilter() {
@Override
public boolean accept(XMLEvent event) {
if(event.isStartElement()) {
String name = event.asStartElement().getName().toString();
if(name.equals("title") || name.equals("price")){
//返回true表示会显示，false表示不显示
return true;
}
}
return false;
}
});
//统计遍历的次数
int iteratorNum = 0;
while(reader.hasNext()){
XMLEvent event = reader.nextEvent();
if(event.isStartElement()){
String name = event.asStartElement().getName().toString();
if(name.equals("title")){
System.out.print("书籍[" + reader.getElementText() + "]");
}
if(name.equals("price")){
System.out.println("的价格为[" + reader.getElementText() + "]");
}
}
iteratorNum++;
}
is.close();
System.out.println("本次操作遍历XML的次数合计为[" + iteratorNum + "]次");
}
}
基于Filter的方式解析XML，控制台输出如下
书籍[Everyday Italian]的价格为[30.00]
书籍[Harry Potter]的价格为[29.99]
书籍[XQuery Kick Start]的价格为[49.99]
书籍[Learning XML]的价格为[39.95]
本次操作遍历XML的次数合计为[8]次
基于XPath的方式解析XML
package com.jadyer.demo.xml;
import org.apache.commons.io.IOUtils;
import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.NodeList;
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.xpath.XPath;
import javax.xml.xpath.XPathConstants;
import javax.xml.xpath.XPathFactory;
import java.io.InputStream;
import java.nio.charset.StandardCharsets;
/**
* StAX(Streaming API for XML)的方式解析XML
* Created by 玄玉<https://jadyer.cn/> on 2013/03/19 15:03.
*/
public class StaxXMLDemo {
public static void main(String[] args) throws Exception {
String xmlStr = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n" +
"<bookstore>\n" +
" <book category=\"COOKING\" aaaaaa=\"111111\">\n" +
" <title lang=\"en\">Everyday Italian</title>\n" +
" <author>Giada De Laurentiis</author>\n" +
" <year>2005</year>\n" +
" <price>30.00</price>\n" +
" </book>\n" +
" <book category=\"CHILDREN\">\n" +
" <title lang=\"en\">Harry Potter</title>\n" +
" <author>J K. Rowling</author>\n" +
" <year>2005</year>\n" +
" <price>29.99</price>\n" +
" </book>\n" +
" <book category=\"WEB\">\n" +
" <title lang=\"en\">XQuery Kick Start</title>\n" +
" <author>James McGovern</author>\n" +
" <author>Per Bothner</author>\n" +
" <author>Kurt Cagle</author>\n" +
" <author>James Linn</author>\n" +
" <author>Vaidyanathan Nagarajan</author>\n" +
" <year>2003</year>\n" +
" <price>49.99</price>\n" +
" </book>\n" +
" <book category=\"WEB\">\n" +
" <title lang=\"en\">Learning XML</title>\n" +
" <author>Erik T. Ray</author>\n" +
" <year>2003</year>\n" +
" <price>39.95</price>\n" +
" </book>\n" +
"</bookstore>";
new StaxXMLDemo().xpathParseXML(xmlStr);
}
/**
* 基于XPath的方式解析XML
*/
private void xpathParseXML(String xmlStr) throws Exception {
//InputStream is = StaxXMLDemo.class.getClassLoader().getResourceAsStream("books.xml")
InputStream is = IOUtils.toInputStream(xmlStr, StandardCharsets.UTF_8);
//创建文档处理对象
DocumentBuilder documentBuilder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
//通过DocumentBuilder创建文档对象
Document doc = documentBuilder.parse(is);
//创建XPath
XPath xpath = XPathFactory.newInstance().newXPath();
//第一个参数就是XPath表达式，第二参数就是文档
//这里是查找所有属性为category="WEB"的<book>节点
NodeList nodeList = (NodeList)xpath.evaluate("//book[@category='WEB']", doc, XPathConstants.NODESET);
for(int i=0; i<nodeList.getLength(); i++) {
Element e = (Element)nodeList.item(i);
//由于<book>节点下只会有一个<title>节点，所有这里是item(0)
System.out.println(e.getElementsByTagName("title").item(0).getTextContent());
System.out.println(e.getElementsByTagName("price").item(0).getTextContent());
}
is.close();
}
}
基于XPath的方式解析XML，控制台输出如下
XQuery Kick Start
49.99
Learning XML
39.95
基于光标的方式解析XML
package com.jadyer.demo.xml;
import org.apache.commons.io.IOUtils;
import javax.xml.stream.XMLInputFactory;
import javax.xml.stream.XMLStreamConstants;
import javax.xml.stream.XMLStreamReader;
import java.io.InputStream;
import java.nio.charset.StandardCharsets;
/**
* StAX(Streaming API for XML)的方式解析XML
* Created by 玄玉<https://jadyer.cn/> on 2013/03/19 15:03.
*/
public class StaxXMLDemo {
public static void main(String[] args) throws Exception {
String xmlStr = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n" +
"<bookstore>\n" +
" <book category=\"COOKING\" aaaaaa=\"111111\">\n" +
" <title lang=\"en\">Everyday Italian</title>\n" +
" <author>Giada De Laurentiis</author>\n" +
" <year>2005</year>\n" +
" <price>30.00</price>\n" +
" </book>\n" +
" <book category=\"CHILDREN\">\n" +
" <title lang=\"en\">Harry Potter</title>\n" +
" <author>J K. Rowling</author>\n" +
" <year>2005</year>\n" +
" <price>29.99</price>\n" +
" </book>\n" +
" <book category=\"WEB\">\n" +
" <title lang=\"en\">XQuery Kick Start</title>\n" +
" <author>James McGovern</author>\n" +
" <author>Per Bothner</author>\n" +
" <author>Kurt Cagle</author>\n" +
" <author>James Linn</author>\n" +
" <author>Vaidyanathan Nagarajan</author>\n" +
" <year>2003</year>\n" +
" <price>49.99</price>\n" +
" </book>\n" +
" <book category=\"WEB\">\n" +
" <title lang=\"en\">Learning XML</title>\n" +
" <author>Erik T. Ray</author>\n" +
" <year>2003</year>\n" +
" <price>39.95</price>\n" +
" </book>\n" +
"</bookstore>";
new StaxXMLDemo().cursorParseXML(xmlStr);
}
/**
* 基于光标的方式解析XML
*/
private void cursorParseXML(String xmlStr) throws Exception {
XMLInputFactory factory = XMLInputFactory.newInstance();
//InputStream is = StaxXMLDemo.class.getClassLoader().getResourceAsStream("books.xml")
InputStream is = IOUtils.toInputStream(xmlStr, StandardCharsets.UTF_8);
XMLStreamReader reader = factory.createXMLStreamReader(is);
while(reader.hasNext()){
int type = reader.next();
//处理不同的节点类型
//处理开始节点，如<bookstore>，<book>
if(type == XMLStreamConstants.START_ELEMENT){
String name = reader.getName().toString();
System.out.println("<" + name + ">");
//打印<book category="COOKING" aaaaaa="111111">节点中的第二个属性值aaaaaa
if(name.equals("book")){
System.out.println("节点属性值为" + reader.getAttributeName(1) + "=" + reader.getAttributeValue(1));
}
if(name.equals("title")){
System.out.println("书籍[" + reader.getElementText() + "]");
}
if(name.equals("price")){
System.out.println("的价格为[" + reader.getElementText() + "]");
}
//打印文本节点的内容
//注意各xml标签中的空白部分也属于文本节点，并且文本节点是没有name的，所以不能getName
}else if(type == XMLStreamConstants.CHARACTERS){
System.out.println("文本节点值=[" + reader.getText().trim() + "]");
//处理结束节点，如</book>，</title>
}else if(type == XMLStreamConstants.END_ELEMENT){
System.out.println("</" + reader.getName() + ">");
}
}
//处理完XML记得关闭流，但不能提前关闭，因为Stax是读一点流就解析一点的
is.close();
}
}
基于光标的方式解析XML，控制台输出如下
<bookstore>
文本节点值=[]
<book>
节点属性值为aaaaaa=111111
文本节点值=[]
<title>
书籍[Everyday Italian]
文本节点值=[]
<author>
文本节点值=[Giada De Laurentiis]
</author>
文本节点值=[]
<year>
文本节点值=[2005]
</year>
文本节点值=[]
<price>
的价格为[30.00]
文本节点值=[]
</book>
文本节点值=[]
<book>
节点属性值为null=null
文本节点值=[]
<title>
书籍[Harry Potter]
文本节点值=[]
<author>
文本节点值=[J K. Rowling]
</author>
文本节点值=[]
<year>
文本节点值=[2005]
</year>
文本节点值=[]
<price>
的价格为[29.99]
文本节点值=[]
</book>
文本节点值=[]
<book>
节点属性值为null=null
文本节点值=[]
<title>
书籍[XQuery Kick Start]
文本节点值=[]
<author>
文本节点值=[James McGovern]
</author>
文本节点值=[]
<author>
文本节点值=[Per Bothner]
</author>
文本节点值=[]
<author>
文本节点值=[Kurt Cagle]
</author>
文本节点值=[]
<author>
文本节点值=[James Linn]
</author>
文本节点值=[]
<author>
文本节点值=[Vaidyanathan Nagarajan]
</author>
文本节点值=[]
<year>
文本节点值=[2003]
</year>
文本节点值=[]
<price>
的价格为[49.99]
文本节点值=[]
</book>
文本节点值=[]
<book>
节点属性值为null=null
文本节点值=[]
<title>
书籍[Learning XML]
文本节点值=[]
<author>
文本节点值=[Erik T. Ray]
</author>
文本节点值=[]
<year>
文本节点值=[2003]
</year>
文本节点值=[]
<price>
的价格为[39.95]
文本节点值=[]
</book>
文本节点值=[]
</bookstore>
基于迭代模型的方式解析XML
package com.jadyer.demo.xml;
import org.apache.commons.io.IOUtils;
import javax.xml.stream.XMLEventReader;
import javax.xml.stream.XMLInputFactory;
import javax.xml.stream.events.XMLEvent;
import java.io.InputStream;
import java.nio.charset.StandardCharsets;
/**
* StAX(Streaming API for XML)的方式解析XML
* Created by 玄玉<https://jadyer.cn/> on 2013/03/19 15:03.
*/
public class StaxXMLDemo {
public static void main(String[] args) throws Exception {
String xmlStr = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n" +
"<bookstore>\n" +
" <book category=\"COOKING\" aaaaaa=\"111111\">\n" +
" <title lang=\"en\">Everyday Italian</title>\n" +
" <author>Giada De Laurentiis</author>\n" +
" <year>2005</year>\n" +
" <price>30.00</price>\n" +
" </book>\n" +
" <book category=\"CHILDREN\">\n" +
" <title lang=\"en\">Harry Potter</title>\n" +
" <author>J K. Rowling</author>\n" +
" <year>2005</year>\n" +
" <price>29.99</price>\n" +
" </book>\n" +
" <book category=\"WEB\">\n" +
" <title lang=\"en\">XQuery Kick Start</title>\n" +
" <author>James McGovern</author>\n" +
" <author>Per Bothner</author>\n" +
" <author>Kurt Cagle</author>\n" +
" <author>James Linn</author>\n" +
" <author>Vaidyanathan Nagarajan</author>\n" +
" <year>2003</year>\n" +
" <price>49.99</price>\n" +
" </book>\n" +
" <book category=\"WEB\">\n" +
" <title lang=\"en\">Learning XML</title>\n" +
" <author>Erik T. Ray</author>\n" +
" <year>2003</year>\n" +
" <price>39.95</price>\n" +
" </book>\n" +
"</bookstore>";
new StaxXMLDemo().iteratorParseXML(xmlStr);
}
/**
* 基于迭代模型的方式解析XML
*/
private void iteratorParseXML(String xmlStr) throws Exception {
XMLInputFactory factory = XMLInputFactory.newInstance();
//InputStream is = StaxXMLDemo.class.getClassLoader().getResourceAsStream("books.xml")
InputStream is = IOUtils.toInputStream(xmlStr, StandardCharsets.UTF_8);
XMLEventReader reader = factory.createXMLEventReader(is);
//统计遍历的次数
int iteratorNum = 0;
while(reader.hasNext()){
XMLEvent event = reader.nextEvent();
//通过XMLEvent判断节点类型
if(event.isStartElement()){
//通过event.asxxx转换节点
String name = event.asStartElement().getName().toString();
if(name.equals("title")){
System.out.print("书籍[" + reader.getElementText() + "]");
}
if(name.equals("price")){
System.out.println("的价格为[" + reader.getElementText() + "]");
}
}
iteratorNum++;
}
is.close();
System.out.println("本次操作遍历XML的次数合计为[" + iteratorNum + "]次");
}
}
基于迭代模型的方式解析XML，控制台输出如下
书籍[Everyday Italian]的价格为[30.00]
书籍[Harry Potter]的价格为[29.99]
书籍[XQuery Kick Start]的价格为[49.99]
书籍[Learning XML]的价格为[39.95]
本次操作遍历XML的次数合计为[85]次
修改XML
package com.jadyer.demo.xml;
import org.apache.commons.io.IOUtils;
import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.NodeList;
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.TransformerFactoryConfigurationError;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import javax.xml.xpath.XPath;
import javax.xml.xpath.XPathConstants;
import javax.xml.xpath.XPathFactory;
import java.io.InputStream;
import java.nio.charset.StandardCharsets;
/**
* StAX(Streaming API for XML)的方式解析XML
* Created by 玄玉<https://jadyer.cn/> on 2013/03/19 15:03.
*/
public class StaxXMLDemo {
public static void main(String[] args) throws Exception {
String xmlStr = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n" +
"<bookstore>\n" +
" <book category=\"COOKING\" aaaaaa=\"111111\">\n" +
" <title lang=\"en\">Everyday Italian</title>\n" +
" <author>Giada De Laurentiis</author>\n" +
" <year>2005</year>\n" +
" <price>30.00</price>\n" +
" </book>\n" +
" <book category=\"CHILDREN\">\n" +
" <title lang=\"en\">Harry Potter</title>\n" +
" <author>J K. Rowling</author>\n" +
" <year>2005</year>\n" +
" <price>29.99</price>\n" +
" </book>\n" +
" <book category=\"WEB\">\n" +
" <title lang=\"en\">XQuery Kick Start</title>\n" +
" <author>James McGovern</author>\n" +
" <author>Per Bothner</author>\n" +
" <author>Kurt Cagle</author>\n" +
" <author>James Linn</author>\n" +
" <author>Vaidyanathan Nagarajan</author>\n" +
" <year>2003</year>\n" +
" <price>49.99</price>\n" +
" </book>\n" +
" <book category=\"WEB\">\n" +
" <title lang=\"en\">Learning XML</title>\n" +
" <author>Erik T. Ray</author>\n" +
" <year>2003</year>\n" +
" <price>39.95</price>\n" +
" </book>\n" +
"</bookstore>";
new StaxXMLDemo().transformerModifyXML(xmlStr);
}
/**
* 使用Transformer修改XML
*/
private void transformerModifyXML(String xmlStr) throws Exception, TransformerFactoryConfigurationError {
//InputStream is = StaxXMLDemo.class.getClassLoader().getResourceAsStream("books.xml")
InputStream is = IOUtils.toInputStream(xmlStr, StandardCharsets.UTF_8);
DocumentBuilder documentBuilder = DocumentBuilderFactory.newInstance().newDocumentBuilder();
Document doc = documentBuilder.parse(is);
XPath xpath = XPathFactory.newInstance().newXPath();
//查找内容含title="Learning XML"的<book>节点
NodeList list = (NodeList)xpath.evaluate("//book[title='Learning XML']", doc, XPathConstants.NODESET);
//获取<price>节点，这里只有一个符合条件的<book>节点，所以写成了list.item(0)
Element e = (Element)(((Element)list.item(0)).getElementsByTagName("price").item(0));
e.setTextContent("333.9");
Transformer tran = TransformerFactory.newInstance().newTransformer();
tran.setOutputProperty(OutputKeys.ENCODING, "UTF-8");
//让<?xml version=...?>与<bookestore>节点之间换行（默认不换行）
tran.setOutputProperty(OutputKeys.INDENT, "yes");
//修改节点
tran.transform(new DOMSource(doc), new StreamResult(System.out));
is.close();
}
}
使用Transformer修改XML，控制台输出如下
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<bookstore>
<book aaaaaa="111111" category="COOKING">
<title lang="en">Everyday Italian</title>
<author>Giada De Laurentiis</author>
<year>2005</year>
<price>30.00</price>
</book>
<book category="CHILDREN">
<title lang="en">Harry Potter</title>
<author>J K. Rowling</author>
<year>2005</year>
<price>29.99</price>
</book>
<book category="WEB">
<title lang="en">XQuery Kick Start</title>
<author>James McGovern</author>
<author>Per Bothner</author>
<author>Kurt Cagle</author>
<author>James Linn</author>
<author>Vaidyanathan Nagarajan</author>
<year>2003</year>
<price>49.99</price>
</book>
<book category="WEB">
<title lang="en">Learning XML</title>
<author>Erik T. Ray</author>
<year>2003</year>
<price>333.9</price>
</book>
</bookstore>
创建XML
package com.jadyer.demo.xml;
import javax.xml.stream.FactoryConfigurationError;
import javax.xml.stream.XMLOutputFactory;
import javax.xml.stream.XMLStreamException;
import javax.xml.stream.XMLStreamWriter;
/**
* StAX(Streaming API for XML)的方式解析XML
* Created by 玄玉<https://jadyer.cn/> on 2013/03/19 15:03.
*/
public class StaxXMLDemo {
public static void main(String[] args) throws Exception {
String xmlStr = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n" +
"<bookstore>\n" +
" <book category=\"COOKING\" aaaaaa=\"111111\">\n" +
" <title lang=\"en\">Everyday Italian</title>\n" +
" <author>Giada De Laurentiis</author>\n" +
" <year>2005</year>\n" +
" <price>30.00</price>\n" +
" </book>\n" +
" <book category=\"CHILDREN\">\n" +
" <title lang=\"en\">Harry Potter</title>\n" +
" <author>J K. Rowling</author>\n" +
" <year>2005</year>\n" +
" <price>29.99</price>\n" +
" </book>\n" +
" <book category=\"WEB\">\n" +
" <title lang=\"en\">XQuery Kick Start</title>\n" +
" <author>James McGovern</author>\n" +
" <author>Per Bothner</author>\n" +
" <author>Kurt Cagle</author>\n" +
" <author>James Linn</author>\n" +
" <author>Vaidyanathan Nagarajan</author>\n" +
" <year>2003</year>\n" +
" <price>49.99</price>\n" +
" </book>\n" +
" <book category=\"WEB\">\n" +
" <title lang=\"en\">Learning XML</title>\n" +
" <author>Erik T. Ray</author>\n" +
" <year>2003</year>\n" +
" <price>39.95</price>\n" +
" </book>\n" +
"</bookstore>";
new StaxXMLDemo().xmlStreamWriterXML(xmlStr);
}
/**
* 使用XMLStreamWriter创建XML
*/
private void xmlStreamWriterXML(String xmlStr) throws XMLStreamException, FactoryConfigurationError {
XMLStreamWriter xsw = XMLOutputFactory.newInstance().createXMLStreamWriter(System.out);
//先写<?xml version="1.0" encoding="UTF-8"?>
xsw.writeStartDocument("UTF-8", "1.0");
xsw.writeEndDocument();
String namespaceURI = "https://jadyer.cn/";
//再写<pre:uesr>
xsw.writeStartElement("pre", "uesr", namespaceURI);
//再写<pre:id>
xsw.writeStartElement(namespaceURI, "id");
//再写1
xsw.writeCharacters("1");
//再写</pre:id>
xsw.writeEndElement();
//再写</pre:uesr>
xsw.writeEndElement();
xsw.flush();
xsw.close();
}
}
使用XMLStreamWriter创建XML，控制台输出如下
<?xml version="1.0" encoding="UTF-8"?><pre:uesr><pre:id>1</pre:id></pre:uesr>