登录
当前位置： 首页 > 工具软件 > DOM Treemap > 使用案例 >

使用dom4j的xPath解析XML

戈曾琪
2023-12-01
books.xml: 
<?xml version="1.0" encoding="UTF-8"?>
<books>
    <!--This is a test for dom4j, jakoes, 2007.7.19-->
    <book show="yes" url="lucene.net">
        <title id="456">Lucene Studing</title>
    </book>
    <book show="yes" url="dom4j.com">
        <title id="123">Dom4j Tutorials</title>
    </book>
    <book show="no" url="spring.org">
        <title id="789">Spring in Action</title>
    </book>
    <owner>O'Reilly</owner>
</books>


下面我们使用dom4j的xPath来解析：

segment of ParseXML.java: 

public void parseBooks(){

        SAXReader reader = new SAXReader();
        try {
            Document doc = reader.read("books.xml");
            Node root = doc.selectSingleNode("/books");
            List list = root.selectNodes("book[@url='dom4j.com']");

            for(Object o:list){

                Element e = (Element) o;
                String show=e.attributeValue("show");
                System.out.println("show = " + show);
            }

        } catch (Exception e) {
            e.printStackTrace();
        }
    }


Document doc = reader.read("books.xml");的意思是加载XML文档，此是可以用doc.asXML()来查看，它将打印整个xml文档。

Node root = doc.selectSingleNode("/books");是读取刚才加载的xml文档内的books节点下的所有内容，对于本例也是整个xml文档。
当然我们也可以加载/books下的某一个节点，如：book节点
Node root = doc.selectSingleNode("/books/book");
或：Node root = doc.selectSingleNode("/books/*");
注意：如果有多个book节点，它只会读取第一个
root.asXML()将打印：
<book show="yes" url="lucene.net">
<title id="456">Lucene Studing</title>
</book>

既然加载了这么多，那我怎么精确的得到我想要的节点呢，别急，看下面：
List list = root.selectNodes("book[@url='dom4j.com']");
它的意思就是读取books节点下的book节点，且book的节点的url属性为dom4j.com
为什么使用list来接收呢，如果有两个book节点，且它们的url属性都为dom4j.com，此时就封闭到list里了。

[color=red]如果想读取books下的所有book节点，可以这样：
List list = root.selectNodes("book");

如果想读取books节点下的book节点下的title节点，可以这样：
List list2 = root.selectNodes("book[@url='dom4j.com']/title[@id='123']");[/color]

注意：selectNodes()参数的格式：
节点名[@属性名='属性值']，如：book[@url='dom4j.com']
如果有多个节点，用“/”分开，如：book[@url='dom4j.com']/title[@id='123']

最后就是读取封闭在List里的内容了，可以用Node来读取，也可以用Element来转换。
attributeValue("属性")是读取该节点的属性值
getText()是读取节点的的内容。

可参考：
[url]http://newbutton.blog.163.com/blog/static/440539462007919115928634/[/url]

下面介绍一个复杂一点的例子，通过请求，从服务器传回一串xml格式的字符串，然后再parse方法中解析，就得到了TermInfo对象实例。
服务器传回的字符串如下：
<?xml version=\"1.0\" encoding=\"utf-8\"?><message><head><messageId>20100707163000062</messageId><result>0000</result><encryptionType>0</encryptionType><md>a4820454be3b0bcc42cb62884a8ef44e</md></head><body><termInfo winTermNo=\"10077\" preTermNo=\"\"><lotteryResult>0607091724|0212</lotteryResult><missCount >10,29,3,4,5,0,0,12,0,2,4,1,12,7,11,1,0,8,1,3,11,11,2,0,5,6,2,7,8,4,14,3,17,9,1|4,0,5,28,2,9,2,8,8,5,4,0</missCount ><limitNumber ></limitNumber ><salesVolume >51385724</salesVolume ><jackpot >68192388.87</jackpot ><winResult><win id=\"1\"><winCount>0</winCount><winMoney>0</winMoney><winAddCount>0</winAddCount><winAddMoney>0</winAddMoney></win><win id=\"2\"><winCount>3</winCount><winMoney>1018831</winMoney><winAddCount>1</winAddCount><winAddMoney>611298</winAddMoney></win><win id=\"3\"><winCount>38</winCount><winMoney>22364</winMoney><winAddCount>5</winAddCount><winAddMoney>13418</winAddMoney></win><win id=\"4\"><winCount>40</winCount><winMoney>3000</winMoney><winAddCount>9</winAddCount><winAddMoney>1500</winAddMoney></win><win id=\"5\"><winCount>1473</winCount><winMoney>600</winMoney><winAddCount>464</winAddCount><winAddMoney>300</winAddMoney></win><win id=\"6\"><winCount>6540</winCount><winMoney>100</winMoney><winAddCount>1573</winAddCount><winAddMoney>50</winAddMoney></win><win id=\"7\"><winCount>69490</winCount><winMoney>10</winMoney><winAddCount>18273</winAddCount><winAddMoney>5</winAddMoney></win><win id=\"8\"><winCount>832924</winCount><winMoney>5</winMoney></win></winResult><term termNo=\"10078\"><termStatus>1</termStatus><winStatus>1</winStatus><saleStatus>1</saleStatus><startTime></startTime><deadLine>20100707193000</deadLine><deadLine2>20100707190000</deadLine2><winLine>20100707220000</winLine><startTime2></startTime2><deadLine3>20100707200000</deadLine3><winLine2>20100707220000</winLine2><changeLine>20100905220000</changeLine><reserve></reserve></term></termInfo></body></message>

解析如下： 

import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import java.util.Map;
import java.util.TreeMap;

import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.DocumentHelper;
import org.dom4j.Element;
import com.tlt.app.util.Constants;
/**
 * 当前在售期彩期信息
 * @author Administrator
 *
 */
public class TermInfo extends BaseModel{

	private Head head;
	/*选填，最近一期开奖期号*/
	private String winTermNo;
	/*选填，最近一期预售期号*/
	private String preTermNo;
	/*最近开奖结果*/
	private String lotteryResult;
	/*遗漏信息*/
	private String missCount;
	/*限号信息*/
	private String limitNumber;
	/*上期销量*/
	private String salesVolume;
	/*奖池滚存*/
	private String jackpot;
	/*最近开奖奖级结果*/
	private WinResult winResult;
	/*正在销售彩期信息*/
	private Term term;
	/*保留*/
	private String reserve;
	/*出错信息*/
	private String errorMsg;
	/*球队*/
	private List<GameInfo> gameInfo;
	public List<GameInfo> getGameInfo() {
		return gameInfo;
	}
	public void setGameInfo(List<GameInfo> gameInfo) {
		this.gameInfo = gameInfo;
	}
	public String getWinTermNo() {
		return winTermNo;
	}
	public void setWinTermNo(String winTermNo) {
		this.winTermNo = winTermNo;
	}
	public String getPreTermNo() {
		return preTermNo;
	}
	public void setPreTermNo(String preTermNo) {
		this.preTermNo = preTermNo;
	}
	public String getErrorMsg() {
		return errorMsg;
	}
	public void setErrorMsg(String errorMsg) {
		this.errorMsg = errorMsg;
	}
	public Head getHead() {
		return head;
	}
	public void setHead(Head head) {
		this.head = head;
	}
	public String getLotteryResult() {
		return lotteryResult;
	}
	public void setLotteryResult(String lotteryResult) {
		this.lotteryResult = lotteryResult;
	}
	public String getMissCount() {
		return missCount;
	}
	public void setMissCount(String missCount) {
		this.missCount = missCount;
	}
	public String getLimitNumber() {
		return limitNumber;
	}
	public void setLimitNumber(String limitNumber) {
		this.limitNumber = limitNumber;
	}
	public String getSalesVolume() {
		return salesVolume;
	}
	public void setSalesVolume(String salesVolume) {
		this.salesVolume = salesVolume;
	}
	public String getJackpot() {
		return jackpot;
	}
	public void setJackpot(String jackpot) {
		this.jackpot = jackpot;
	}
	public WinResult getWinResult() {
		return winResult;
	}
	public void setWinResult(WinResult winResult) {
		this.winResult = winResult;
	}
	public Term getTerm() {
		return term;
	}
	public void setTerm(Term term) {
		this.term = term;
	}
	public String getReserve() {
		return reserve;
	}
	public void setReserve(String reserve) {
		this.reserve = reserve;
	}
	@Override
	public boolean parse(String xmlString) {
		// TODO Auto-generated method stub
		try {
			Document document = DocumentHelper.parseText(xmlString);
			Head head=new Head();
			head.setMessageId(document.selectSingleNode("//message/head/messageId").getText());
			head.setResult(document.selectSingleNode("//message/head/result").getText());
			head.setEncryptionType(document.selectSingleNode("//message/head/encryptionType").getText());
			head.setMd(document.selectSingleNode("//message/head/md").getText());
			setHead(head);
			//如果返回失败信息，就没必要继续解析了
			if(!head.getResult().equals(Constants.SUCCESS)){
				setErrorMsg(document.selectSingleNode("//message/head/result").getText()+":"+document.selectSingleNode("//message/body/errorMsg").getText());
				return false;
			}
			setWinTermNo(document.selectSingleNode("//message/body/termInfo/@winTermNo").getText());
			setPreTermNo(document.selectSingleNode("//message/body/termInfo/@preTermNo").getText());
			setLotteryResult(document.selectSingleNode("//message/body/termInfo/lotteryResult").getText());
			setMissCount(document.selectSingleNode("//message/body/termInfo/missCount").getText());
			setLimitNumber(document.selectSingleNode("//message/body/termInfo/limitNumber").getText());
			setSalesVolume(document.selectSingleNode("//message/body/termInfo/salesVolume").getText());
			setJackpot(document.selectSingleNode("//message/body/termInfo/jackpot").getText());
			winResult=new WinResult();
			Map<String,Win> winMap=new TreeMap<String,Win>();//需要排序
			List list = document.selectNodes("//message/body/termInfo/winResult/win");
			for (Iterator iter = list.iterator(); iter.hasNext();) {
				Win win=new Win();
				Element winEle=(Element)iter.next();
				win.setWinCount(winEle.element("winCount").getText());
				win.setWinMoney(winEle.element("winMoney").getText());
				if(winEle.element("winAddCount")!=null){//8等奖没有追加
					win.setWinAddCount(winEle.element("winAddCount").getText());
					win.setWinAddMoney(winEle.element("winAddMoney").getText());
				}else{
					win.setWinAddCount("");
					win.setWinAddMoney("");
				}
				String id=winEle.attribute("id").getValue();
				win.setId(id);
				winMap.put(id,win);
			}
			winResult.setWin(winMap);
			setWinResult(winResult);

			Term term=new Term();
			term.setTermNo(document.selectSingleNode("//message/body/termInfo/term/@termNo").getText());
			term.setTermStatus(document.selectSingleNode("//message/body/termInfo/term/termStatus").getText());
			term.setWinStatus(document.selectSingleNode("//message/body/termInfo/term/winStatus").getText());
			term.setSaleStatus(document.selectSingleNode("//message/body/termInfo/term/saleStatus").getText());
			term.setStartTime(document.selectSingleNode("//message/body/termInfo/term/startTime").getText());
			term.setDeadLine(document.selectSingleNode("//message/body/termInfo/term/deadLine").getText());
			term.setDeadLine2(document.selectSingleNode("//message/body/termInfo/term/deadLine2").getText());
			term.setWinLine(document.selectSingleNode("//message/body/termInfo/term/winLine").getText());
			term.setStartTime2(document.selectSingleNode("//message/body/termInfo/term/startTime2").getText());
			term.setDeadLine3(document.selectSingleNode("//message/body/termInfo/term/deadLine3").getText());
			term.setWinLine2(document.selectSingleNode("//message/body/termInfo/term/winLine2").getText());
			term.setChangeLine(document.selectSingleNode("//message/body/termInfo/term/changeLine").getText());
			term.setReserve(document.selectSingleNode("//message/body/termInfo/term/reserve").getText());
			setTerm(term);

			List list_gameInfo = document.selectNodes("//message/body/termInfo/term/gameInfo/game");
			gameInfo=new ArrayList<GameInfo>();
			for (Iterator iter = list_gameInfo.iterator(); iter.hasNext();) {
				GameInfo info=new GameInfo();
				Element gameInfoEle=(Element)iter.next();
				info.setId(gameInfoEle.attributeValue("id"));
				info.setHomeTeam(gameInfoEle.element("homeTeam").getText());
				info.setAwayTeam(gameInfoEle.element("awayTeam").getText());
				info.setGameDate(gameInfoEle.element("gameDate").getText());
				info.setLeagueMatch(gameInfoEle.element("leagueMatch").getText());//巴甲
				info.setReserve(gameInfoEle.element("reserve").getText());
				gameInfo.add(info);
			}
			setGameInfo(gameInfo);
		} catch (DocumentException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
			return false;
		}
		return true;
	}

}



<![CDATA[你的有特殊字符的内容]]>，比如：
<message><![CDATA[salary<1000]]></message>
 类似资料：

相关阅读

通过XPath解析HTMLphp用xpath解析html的代码实例讲解在JAVA中使用XPath解析具有不同名称空间的xml在Java中使用XPath和Selenium解析HTML表数据关于python中的xpath解析定位

相关文章

Java XPath解析器 解析XML文档Java XPath解析器 介绍Java XPath解析器 查询XML文档Jsoup 使用DOM解析HTMLXpath Helper安装使用

相关问答

带有VTD XML解析器的XPath联合运算符JavaVTD-XML和XPath：在找到的部分使用XPath使用改型的Android XML解析使用Jackson解析XML时的MismatchedInputException使用过时的XSD解析XML

相关文档

深入解析 GoTornado 源码解析深度解析 ECMAScript 6百度分析云使用手册百度统计分析云使用手册
快捷导航： 新手教程 算法原理 架构设计 Java进阶 数据库进阶 大厂专栏 面试经验 编程笔记 编程问答 所有专题 文档资料 工具软件 电子书籍 小牛导航
在线工具： 房贷计算器 个税计算器 Linux命令查询 Json格式化 正则表达式 颜色转换 AES加解密 SHA1加密 MD5加密 毒鸡汤 字数统计 随机密码生成 进制转换 Base64编解码 励志句子
Copyright © 2019-2024 小牛知识库@xnip.cn. All Rights Reserved.