如何在 Java 中使用 XPath 读取 XML

你需要一些类似的东西：

DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
DocumentBuilder builder = factory.newDocumentBuilder();
Document doc = builder.parse(<uri_as_string>);
XPathFactory xPathfactory = XPathFactory.newInstance();
XPath xpath = xPathfactory.newXPath();
XPathExpression expr = xpath.compile(<xpath_expression>);

然后，调用传入该代码中定义的文档和预期的返回类型，并将结果强制转换为结果的对象类型。expr.evaluate()

如果你在特定的 XPath 表达式方面需要帮助，你可能应该把它作为单独的问题来问（除非这是你在这里首先提出的问题 - 我理解你的问题是如何在 Java 中使用 API）。

编辑：（对评论的回应）：此 XPath 表达式将为您提供 PowerBuilder 下第一个 URL 元素的文本：

/howto/topic[@name='PowerBuilder']/url/text()

这将为您提供第二个：

/howto/topic[@name='PowerBuilder']/url[2]/text()

你可以通过以下代码得到它：

expr.evaluate(doc, XPathConstants.STRING);

如果您不知道给定节点中有多少个 URL，那么您应该执行以下操作：

XPathExpression expr = xpath.compile("/howto/topic[@name='PowerBuilder']/url");
NodeList nl = (NodeList) expr.evaluate(doc, XPathConstants.NODESET);

然后遍历 NodeList。

入门示例：

XML 文件：

<inventory>
    <book year="2000">
        <title>Snow Crash</title>
        <author>Neal Stephenson</author>
        <publisher>Spectra</publisher>
        <isbn>0553380958</isbn>
        <price>14.95</price>
    </book>

    <book year="2005">
        <title>Burning Tower</title>
        <author>Larry Niven</author>
        <author>Jerry Pournelle</author>
        <publisher>Pocket</publisher>
        <isbn>0743416910</isbn>
        <price>5.99</price>
    </book>

    <book year="1995">
        <title>Zodiac</title>
        <author>Neal Stephenson</author>
        <publisher>Spectra</publisher>
        <isbn>0553573862</isbn>
        <price>7.50</price>
    </book>

    <!-- more books... -->

</inventory>

Java 代码：

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;

import org.testng.annotations.DataProvider;
import org.testng.annotations.Test;
import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.xml.sax.SAXException;
import org.xml.sax.SAXParseException;


try {

    DocumentBuilderFactory docBuilderFactory = DocumentBuilderFactory.newInstance();
    DocumentBuilder docBuilder = docBuilderFactory.newDocumentBuilder();
    Document doc = docBuilder.parse (new File("c:\\tmp\\my.xml"));

    // normalize text representation
    doc.getDocumentElement().normalize();
    System.out.println ("Root element of the doc is " + doc.getDocumentElement().getNodeName());

    NodeList listOfBooks = doc.getElementsByTagName("book");
    int totalBooks = listOfBooks.getLength();
    System.out.println("Total no of books : " + totalBooks);

    for(int i=0; i<listOfBooks.getLength() ; i++) {

        Node firstBookNode = listOfBooks.item(i);
        if(firstBookNode.getNodeType() == Node.ELEMENT_NODE) {

            Element firstElement = (Element)firstBookNode;                              
            System.out.println("Year :"+firstElement.getAttribute("year"));

            //-------
            NodeList firstNameList = firstElement.getElementsByTagName("title");
            Element firstNameElement = (Element)firstNameList.item(0);

            NodeList textFNList = firstNameElement.getChildNodes();
            System.out.println("title : " + ((Node)textFNList.item(0)).getNodeValue().trim());
        }
    }//end of for loop with s var
} catch (SAXParseException err) {
    System.out.println ("** Parsing error" + ", line " + err.getLineNumber () + ", uri " + err.getSystemId ());
    System.out.println(" " + err.getMessage ());
} catch (SAXException e) {
    Exception x = e.getException ();
    ((x == null) ? e : x).printStackTrace ();
} catch (Throwable t) {
    t.printStackTrace ();
}                

你可以试试这个。

XML 文档

另存为 .employees.xml

<?xml version="1.0" encoding="UTF-8"?>
<Employees>
    <Employee id="1">
        <age>29</age>
        <name>Pankaj</name>
        <gender>Male</gender>
        <role>Java Developer</role>
    </Employee>
    <Employee id="2">
        <age>35</age>
        <name>Lisa</name>
        <gender>Female</gender>
        <role>CEO</role>
    </Employee>
    <Employee id="3">
        <age>40</age>
        <name>Tom</name>
        <gender>Male</gender>
        <role>Manager</role>
    </Employee>
    <Employee id="4">
        <age>25</age>
        <name>Meghan</name>
        <gender>Female</gender>
        <role>Manager</role>
    </Employee>
</Employees>

Parser 类

该类具有以下方法

• 列表项
• 一个方法，该方法将返回输入 ID 的 Employee Name。
• 一个方法，它将返回年龄大于输入年龄的雇员姓名列表。
• 将返回 Female Employees Name 列表的方法。

源代码

import java.io.IOException;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;

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

import org.w3c.dom.Document;
import org.w3c.dom.NodeList;
import org.xml.sax.SAXException;


public class Parser {

    public static void main(String[] args) {
        DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
        factory.setNamespaceAware(true);
        DocumentBuilder builder;
        Document doc = null;
        try {
            builder = factory.newDocumentBuilder();
            doc = builder.parse("employees.xml");

            // Create XPathFactory object
            XPathFactory xpathFactory = XPathFactory.newInstance();

            // Create XPath object
            XPath xpath = xpathFactory.newXPath();

            String name = getEmployeeNameById(doc, xpath, 4);
            System.out.println("Employee Name with ID 4: " + name);

            List<String> names = getEmployeeNameWithAge(doc, xpath, 30);
            System.out.println("Employees with 'age>30' are:" + Arrays.toString(names.toArray()));

            List<String> femaleEmps = getFemaleEmployeesName(doc, xpath);
            System.out.println("Female Employees names are:" +
                    Arrays.toString(femaleEmps.toArray()));

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

    }


    private static List<String> getFemaleEmployeesName(Document doc, XPath xpath) {
        List<String> list = new ArrayList<>();
        try {
            //create XPathExpression object
            XPathExpression expr =
                xpath.compile("/Employees/Employee[gender='Female']/name/text()");
            //evaluate expression result on XML document
            NodeList nodes = (NodeList) expr.evaluate(doc, XPathConstants.NODESET);
            for (int i = 0; i < nodes.getLength(); i++)
                list.add(nodes.item(i).getNodeValue());
        } catch (XPathExpressionException e) {
            e.printStackTrace();
        }
        return list;
    }


    private static List<String> getEmployeeNameWithAge(Document doc, XPath xpath, int age) {
        List<String> list = new ArrayList<>();
        try {
            XPathExpression expr =
                xpath.compile("/Employees/Employee[age>" + age + "]/name/text()");
            NodeList nodes = (NodeList) expr.evaluate(doc, XPathConstants.NODESET);
            for (int i = 0; i < nodes.getLength(); i++)
                list.add(nodes.item(i).getNodeValue());
        } catch (XPathExpressionException e) {
            e.printStackTrace();
        }
        return list;
    }


    private static String getEmployeeNameById(Document doc, XPath xpath, int id) {
        String name = null;
        try {
            XPathExpression expr =
                xpath.compile("/Employees/Employee[@id='" + id + "']/name/text()");
            name = (String) expr.evaluate(doc, XPathConstants.STRING);
        } catch (XPathExpressionException e) {
            e.printStackTrace();
        }

        return name;
    }

}

下面是使用 vtd-xml 处理 xpath 的示例...对于繁重的XML处理，它是首屈一指的。这是最近关于这个主题的论文 Processing XML with Java – A Performance Benchmark

import com.ximpleware.*;

public class changeAttrVal {
    public  static  void main(String s[]) throws VTDException,java.io.UnsupportedEncodingException,java.io.IOException{
        VTDGen vg = new VTDGen();
        if (!vg.parseFile("input.xml", false))
            return;
        VTDNav vn = vg.getNav();
        AutoPilot ap = new AutoPilot(vn);
        XMLModifier xm = new XMLModifier(vn);
        ap.selectXPath("/*/place[@id=\"p14\" and   @initialMarking=\"2\"]/@initialMarking");
        int i=0;
        while((i=ap.evalXPath())!=-1){
            xm.updateToken(i+1, "499");// change initial marking from 2 to 499
        }
        xm.output("new.xml");
    }

}

通过@bluish和@Yishai扩展了出色的答案，以下是如何使 NodeLists 和节点属性支持迭代器，即接口。for(Node n: nodelist)

像这样使用它：

NodeList nl = ...
for(Node n : XmlUtil.asList(nl))
{...}

和

Node n = ...
for(Node attr : XmlUtil.asList(n.getAttributes())
{...}

代码：

/**
 * Converts NodeList to an iterable construct.
 * From: https://stackoverflow.com/a/19591302/779521
 */
public final class XmlUtil {
    private XmlUtil() {}

    public static List<Node> asList(NodeList n) {
        return n.getLength() == 0 ? Collections.<Node>emptyList() : new NodeListWrapper(n);
    }

    static final class NodeListWrapper extends AbstractList<Node> implements RandomAccess {
        private final NodeList list;

        NodeListWrapper(NodeList l) {
            this.list = l;
        }

        public Node get(int index) {
            return this.list.item(index);
        }

        public int size() {
            return this.list.getLength();
        }
    }

    public static List<Node> asList(NamedNodeMap n) {
        return n.getLength() == 0 ? Collections.<Node>emptyList() : new NodeMapWrapper(n);
    }

    static final class NodeMapWrapper extends AbstractList<Node> implements RandomAccess {
        private final NamedNodeMap list;

        NodeMapWrapper(NamedNodeMap l) {
            this.list = l;
        }

        public Node get(int index) {
            return this.list.item(index);
        }

        public int size() {
            return this.list.getLength();
        }
    }
}

使用 XPathFactory、SAXParserFactory 和 StAX （JSR-173） 读取 XML 文件。

使用 XPath 获取节点及其子数据。

public static void main(String[] args) {
    String xml = "<soapenv:Body xmlns:soapenv='http://schemas.xmlsoap.org/soap/envelope/'>"
            + "<Yash:Data xmlns:Yash='http://Yash.stackoverflow.com/Services/Yash'>"
            + "<Yash:Tags>Java</Yash:Tags><Yash:Tags>Javascript</Yash:Tags><Yash:Tags>Selenium</Yash:Tags>"
            + "<Yash:Top>javascript</Yash:Top><Yash:User>Yash-777</Yash:User>"
            + "</Yash:Data></soapenv:Body>";
    String jsonNameSpaces = "{'soapenv':'http://schemas.xmlsoap.org/soap/envelope/',"
            + "'Yash':'http://Yash.stackoverflow.com/Services/Yash'}";
    String xpathExpression = "//Yash:Data";

    Document doc1 = getDocument(false, "fileName", xml);
    getNodesFromXpath(doc1, xpathExpression, jsonNameSpaces);
    System.out.println("\n===== ***** =====");
    Document doc2 = getDocument(true, "./books.xml", xml);
    getNodesFromXpath(doc2, "//person", "{}");
}
static Document getDocument( boolean isFileName, String fileName, String xml ) {
    Document doc = null;
    try {

        DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
        factory.setValidating(false);
        factory.setNamespaceAware(true);
        factory.setIgnoringComments(true);
        factory.setIgnoringElementContentWhitespace(true);

        DocumentBuilder builder = factory.newDocumentBuilder();
        if( isFileName ) {
            File file = new File( fileName );
            FileInputStream stream = new FileInputStream( file );
            doc = builder.parse( stream );
        } else {
            doc = builder.parse( string2Source( xml ) );
        }
    } catch (SAXException | IOException e) {
        e.printStackTrace();
    } catch (ParserConfigurationException e) {
        e.printStackTrace();
    }
    return doc;
}

/**
 * ELEMENT_NODE[1],ATTRIBUTE_NODE[2],TEXT_NODE[3],CDATA_SECTION_NODE[4],
 * ENTITY_REFERENCE_NODE[5],ENTITY_NODE[6],PROCESSING_INSTRUCTION_NODE[7],
 * COMMENT_NODE[8],DOCUMENT_NODE[9],DOCUMENT_TYPE_NODE[10],DOCUMENT_FRAGMENT_NODE[11],NOTATION_NODE[12]
 */
public static void getNodesFromXpath( Document doc, String xpathExpression, String jsonNameSpaces ) {
    try {
        XPathFactory xpf = XPathFactory.newInstance();
        XPath xpath = xpf.newXPath();

        JSONObject namespaces = getJSONObjectNameSpaces(jsonNameSpaces);
        if ( namespaces.size() > 0 ) {
            NamespaceContextImpl nsContext = new NamespaceContextImpl();

            Iterator<?> key = namespaces.keySet().iterator();
            while (key.hasNext()) { // Apache WebServices Common Utilities
                String pPrefix = key.next().toString();
                String pURI = namespaces.get(pPrefix).toString();
                nsContext.startPrefixMapping(pPrefix, pURI);
            }
            xpath.setNamespaceContext(nsContext );
        }

        XPathExpression compile = xpath.compile(xpathExpression);
        NodeList nodeList = (NodeList) compile.evaluate(doc, XPathConstants.NODESET);
        displayNodeList(nodeList);
    } catch (XPathExpressionException e) {
        e.printStackTrace();
    }
}

static void displayNodeList( NodeList nodeList ) {
    for (int i = 0; i < nodeList.getLength(); i++) {
        Node node = nodeList.item(i);
        String NodeName = node.getNodeName();

        NodeList childNodes = node.getChildNodes();
        if ( childNodes.getLength() > 1 ) {
            for (int j = 0; j < childNodes.getLength(); j++) {

                Node child = childNodes.item(j);
                short nodeType = child.getNodeType();
                if ( nodeType == 1 ) {
                    System.out.format( "\n\t Node Name:[%s], Text[%s] ", child.getNodeName(), child.getTextContent() );
                }
            }
        } else {
            System.out.format( "\n Node Name:[%s], Text[%s] ", NodeName, node.getTextContent() );
        }

    }
}
static InputSource string2Source( String str ) {
    InputSource inputSource = new InputSource( new StringReader( str ) );
    return inputSource;
}
static JSONObject getJSONObjectNameSpaces( String jsonNameSpaces ) {
    if(jsonNameSpaces.indexOf("'") > -1)    jsonNameSpaces = jsonNameSpaces.replace("'", "\"");
    JSONParser parser = new JSONParser();
    JSONObject namespaces = null;
    try {
        namespaces = (JSONObject) parser.parse(jsonNameSpaces);
    } catch (ParseException e) {
        e.printStackTrace();
    }
    return namespaces;
}

XML 文档

<?xml version="1.0" encoding="UTF-8"?>
<book>
<person>
  <first>Yash</first>
  <last>M</last>
  <age>22</age>
</person>
<person>
  <first>Bill</first>
  <last>Gates</last>
  <age>46</age>
</person>
<person>
  <first>Steve</first>
  <last>Jobs</last>
  <age>40</age>
</person>
</book>

给定 XPathExpression 的输出：

String xpathExpression = "//person/first";
/*OutPut:
 Node Name:[first], Text[Yash] 
 Node Name:[first], Text[Bill] 
 Node Name:[first], Text[Steve] */

String xpathExpression = "//person";
/*OutPut:
     Node Name:[first], Text[Yash] 
     Node Name:[last], Text[M] 
     Node Name:[age], Text[22] 
     Node Name:[first], Text[Bill] 
     Node Name:[last], Text[Gates] 
     Node Name:[age], Text[46] 
     Node Name:[first], Text[Steve] 
     Node Name:[last], Text[Jobs] 
     Node Name:[age], Text[40] */

String xpathExpression = "//Yash:Data";
/*OutPut:
     Node Name:[Yash:Tags], Text[Java] 
     Node Name:[Yash:Tags], Text[Javascript] 
     Node Name:[Yash:Tags], Text[Selenium] 
     Node Name:[Yash:Top], Text[javascript] 
     Node Name:[Yash:User], Text[Yash-777] */

请参阅此链接，了解我们自己的实现NamespaceContext

这演示了如何

1. 将 XML 文件读入DOM
2. 过滤掉一组NodesXPath
3. 对每个提取的 .Nodes

我们将使用以下语句调用代码

processFilteredXml(xmlIn, xpathExpr,(node) -> {/*Do something...*/;});

在我们的例子中，我们想从 using as xpath 打印一些内容，以在与 .creatorNamesbook.xml"//book/creators/creator/creatorName"printNodeXPath

完整代码

@Test
public void printXml() {
    try (InputStream in = readFile("book.xml")) {
        processFilteredXml(in, "//book/creators/creator/creatorName", (node) -> {
            printNode(node, System.out);
        });
    } catch (Exception e) {
        throw new RuntimeException(e);
    }
}

private InputStream readFile(String yourSampleFile) {
    return Thread.currentThread().getContextClassLoader().getResourceAsStream(yourSampleFile);
}

private void processFilteredXml(InputStream in, String xpath, Consumer<Node> process) {
    Document doc = readXml(in);
    NodeList list = filterNodesByXPath(doc, xpath);
    for (int i = 0; i < list.getLength(); i++) {
        Node node = list.item(i);
        process.accept(node);
    }
}

public Document readXml(InputStream xmlin) {
    try {
        DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
        DocumentBuilder db = dbf.newDocumentBuilder();
        return db.parse(xmlin);
    } catch (Exception e) {
        throw new RuntimeException(e);
    }
}

private NodeList filterNodesByXPath(Document doc, String xpathExpr) {
    try {
        XPathFactory xPathFactory = XPathFactory.newInstance();
        XPath xpath = xPathFactory.newXPath();
        XPathExpression expr = xpath.compile(xpathExpr);
        Object eval = expr.evaluate(doc, XPathConstants.NODESET);
        return (NodeList) eval;
    } catch (Exception e) {
        throw new RuntimeException(e);
    }
}

private void printNode(Node node, PrintStream out) {
    try {
        Transformer transformer = TransformerFactory.newInstance().newTransformer();
        transformer.setOutputProperty(OutputKeys.INDENT, "yes");
        transformer.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION, "yes");
        transformer.setOutputProperty("{http://xml.apache.org/xslt}indent-amount", "2");
        StreamResult result = new StreamResult(new StringWriter());
        DOMSource source = new DOMSource(node);
        transformer.transform(source, result);
        String xmlString = result.getWriter().toString();
        out.println(xmlString);
    } catch (Exception e) {
        throw new RuntimeException(e);
    }
}

指纹

<creatorName>Fosmire, Michael</creatorName>

<creatorName>Wertz, Ruth</creatorName>

<creatorName>Purzer, Senay</creatorName>

为book.xml

<book>
  <creators>
    <creator>
      <creatorName>Fosmire, Michael</creatorName>
      <givenName>Michael</givenName>
      <familyName>Fosmire</familyName>
    </creator>
    <creator>
      <creatorName>Wertz, Ruth</creatorName>
      <givenName>Ruth</givenName>
      <familyName>Wertz</familyName>
    </creator>
    <creator>
      <creatorName>Purzer, Senay</creatorName>
       <givenName>Senay</givenName>
       <familyName>Purzer</familyName>
    </creator>
  </creators>
  <titles>
    <title>Critical Engineering Literacy Test (CELT)</title>
  </titles>
</book>

如果您有如下所示的 xml

<e:Envelope
    xmlns:d = "http://www.w3.org/2001/XMLSchema"
    xmlns:e = "http://schemas.xmlsoap.org/soap/envelope/"
    xmlns:wn0 = "http://systinet.com/xsd/SchemaTypes/"
    xmlns:i = "http://www.w3.org/2001/XMLSchema-instance">
    <e:Header>
        <Friends>
            <friend>
                <Name>Testabc</Name>
                <Age>12121</Age>
                <Phone>Testpqr</Phone>
            </friend>
        </Friends>
    </e:Header>
    <e:Body>
        <n0:ForAnsiHeaderOperResponse xmlns:n0 = "http://systinet.com/wsdl/com/magicsoftware/ibolt/localhost/ForAnsiHeader/ForAnsiHeaderImpl#ForAnsiHeaderOper?KExqYXZhL2xhbmcvU3RyaW5nOylMamF2YS9sYW5nL1N0cmluZzs=">
            <response i:type = "d:string">12--abc--pqr</response>
        </n0:ForAnsiHeaderOperResponse>
    </e:Body>
</e:Envelope>

并想提取以下 XML

<e:Header>
   <Friends>
      <friend>
         <Name>Testabc</Name>
         <Age>12121</Age>
         <Phone>Testpqr</Phone>
      </friend>
   </Friends>
</e:Header>

下面的代码有助于实现相同的目的

public static void main(String[] args) {

    File fXmlFile = new File("C://Users//abhijitb//Desktop//Test.xml");
    DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
    Document document;
    Node result = null;
    try {
        document = dbf.newDocumentBuilder().parse(fXmlFile);
        XPath xPath = XPathFactory.newInstance().newXPath();
        String xpathStr = "//Envelope//Header";
        result = (Node) xPath.evaluate(xpathStr, document, XPathConstants.NODE);
        System.out.println(nodeToString(result));
    } catch (SAXException | IOException | ParserConfigurationException | XPathExpressionException
            | TransformerException e) {
        e.printStackTrace();
    }
}

private static String nodeToString(Node node) throws TransformerException {
    StringWriter buf = new StringWriter();
    Transformer xform = TransformerFactory.newInstance().newTransformer();
    xform.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION, "yes");
    xform.transform(new DOMSource(node), new StreamResult(buf));
    return (buf.toString());
}

现在，如果您只想要如下所示的 xml

<Friends>
   <friend>
      <Name>Testabc</Name>
      <Age>12121</Age>
      <Phone>Testpqr</Phone>
   </friend>
</Friends>

您需要更改

String xpathStr = "//Envelope//Header";自String xpathStr = "//Envelope//Header/*";