XPath

javax.xml.xpath Interface XPath
XPath 是一门在 XML 文档中查找信息的语言。XPath 可用来在 XML 文档中对元素和属性进行遍历。
XPath 是 W3C XSLT 标准的主要元素，并且 XQuery 和 XPointer 都构建于 XPath 表达之上。
因此，对 XPath 的理解是很多高级 XML 应用的基础。
XPath 使用路径表达式来选取 XML 文档中的节点或者节点集。这些路径表达式和我们在常规的电脑文件系统中看到的表达式非常相似。

E.G

import java.io.File;
import java.io.FileInputStream;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.xpath.XPath;
import javax.xml.xpath.XPathConstants;
import javax.xml.xpath.XPathExpressionException;
import javax.xml.xpath.XPathFactory;

import org.w3c.dom.Document;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;

public class XPathDemo {
    private static Document doc;
    private static XPath xpath;

    public static void main(String[] args) throws Exception {
        init();
        getRootEle();
        getChildEles();
        getPartEles();
        haveChildsEles();
        getLevelEles();
        getAttrEles();

        // 打印根节点下的所有元素节点
        System.out
                .println(doc.getDocumentElement().getChildNodes().getLength());
        NodeList nodeList = doc.getDocumentElement().getChildNodes();
        for (int i = 0; i < nodeList.getLength(); i++) {
            if (nodeList.item(i).getNodeType() == Node.ELEMENT_NODE) {
                System.out.print(nodeList.item(i).getNodeName() + " ");
            }
        }
    }

    // 初始化Document、XPath对象
    public static void init() throws Exception {
        // 创建Document对象
        DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
        dbf.setValidating(false);
        DocumentBuilder db = dbf.newDocumentBuilder();
        doc = db.parse(new FileInputStream(new File("D:\\SVN111\\Xpath\\bin\\demo.xml")));

        // 创建XPath对象
        XPathFactory factory = XPathFactory.newInstance();
        xpath = factory.newXPath();
    }

    // 获取根元素
    // 表达式可以更换为/*,/rss
    public static void getRootEle() throws XPathExpressionException {
        Node node = (Node) xpath.evaluate("/rss", doc, XPathConstants.NODE);
        System.out.println(node.getNodeName() + "--------"
                + node.getNodeValue());
    }

    // 获取子元素并打印
    public static void getChildEles() throws XPathExpressionException {
        NodeList nodeList = (NodeList) xpath.evaluate("/rss/channel/*", doc,
                XPathConstants.NODESET);
        for (int i = 0; i < nodeList.getLength(); i++) {
            System.out.print(nodeList.item(i).getNodeName() + " ");
        }
        System.out.println();
    }

    // 获取部分元素
    // 只获取元素名称为title的元素
    public static void getPartEles() throws XPathExpressionException {
        NodeList nodeList = (NodeList) xpath.evaluate("//*[name() = 'title']",
                doc, XPathConstants.NODESET);
        for (int i = 0; i < nodeList.getLength(); i++) {
            System.out.print(nodeList.item(i).getNodeName() + "-->"
                    + nodeList.item(i).getTextContent());
        }
        System.out.println();
    }

    // 获取包含子节点的元素
    public static void haveChildsEles() throws XPathExpressionException {
        NodeList nodeList = (NodeList) xpath.evaluate("//*[*]", doc,
                XPathConstants.NODESET);
        for (int i = 0; i < nodeList.getLength(); i++) {
            System.out.print(nodeList.item(i).getNodeName() + " ");
        }
        System.out.println();
    }

    // 获取指定层级的元素
    public static void getLevelEles() throws XPathExpressionException {
        NodeList nodeList = (NodeList) xpath.evaluate("/*/*/*/*", doc,
                XPathConstants.NODESET);
        for (int i = 0; i < nodeList.getLength(); i++) {
            System.out.print(nodeList.item(i).getNodeName() + "-->"
                    + nodeList.item(i).getTextContent() + " ");
        }
        System.out.println("-----------------------------");
    }

    // 获取指定属性的元素
    // 获取所有大于指定价格的书箱
    public static void getAttrEles() throws XPathExpressionException {
        NodeList nodeList = (NodeList) xpath.evaluate(
                "//bookstore/book[price>35.00]/title", doc,
                XPathConstants.NODESET);
        for (int i = 0; i < nodeList.getLength(); i++) {
            System.out.print(nodeList.item(i).getNodeName() + "-->"
                    + nodeList.item(i).getTextContent() + " ");
        }
        System.out.println();
    }
}

xml

<rss version="2.0">
    <channel>
        <title>Java Tutorials and Examples 2title>
        <language>en-uslanguage>
        <item>
            <title>title>
            <link>http://www.javacodegeeks.com/link>
        item>
        <item>
            <title>title>
            <link>http://examples.javacodegeeks.com/link>
        item>
    channel>
    <college name="c1">
        <class name="class1">
            <student name="stu1" sex='male' age="21" />
            <student name="stu2" sex='female' age="20" />
            <student name="stu3" sex='female' age="20" />
        class>
    college>
    <bookstore>
        <book>
            <title lang="eng">Harry Pottertitle>
            <price>29.99price>
        book>
        <book>
            <title lang="eng">Learning XMLtitle>
            <price>39.95price>
        book>
    bookstore>
rss>