如何在Java中提取字符串格式XML中的特定值？

先整理你需要处理的核心XML内容（先剥离外层的<p><code>标签）：

<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<ns2:services xmlns:ns2="http://www.3ds.com/enovia/e6wv2">
    <ns2:serviceData>
        <ns2:statusCode>200</ns2:statusCode>
        <ns2:success>true</ns2:success>
        <ns2:csrf name="ENO_CSRF_TOKEN" value="JYOF-K5LS-INZM-15O3-4O00-VTBJ-R28O-YY2P"/>
    </ns2:serviceData>
</ns2:services>

下面提供两种实用的提取方式：

方法一：使用原生DOM+XPath（无额外依赖） #

直接用JDK自带API，无需引入第三方库。

代码示例 #

import org.w3c.dom.Document;
import org.xml.sax.InputSource;

import javax.xml.xpath.XPath;
import javax.xml.xpath.XPathFactory;
import java.io.StringReader;

public class XmlExtractor {
    public static void main(String[] args) {
        // 原始输入字符串
        String xmlStr = "<p><code><?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"yes\"?><ns2:services xmlns:ns2=\"http://www.3ds.com/enovia/e6wv2\"><ns2:serviceData><ns2:statusCode>200</ns2:statusCode><ns2:success>true</ns2:success><ns2:csrf name=\"ENO_CSRF_TOKEN\" value=\"JYOF-K5LS-INZM-15O3-4O00-VTBJ-R28O-YY2P\"/></ns2:serviceData></ns2:services></code></p>";
        
        // 提取核心XML部分，剥离外层标签
        String coreXml = xmlStr.substring(xmlStr.indexOf("<?xml"), xmlStr.indexOf("</ns2:services>") + "</ns2:services>".length());

        try {
            // 初始化XPath并注册命名空间
            XPath xpath = XPathFactory.newInstance().newXPath();
            xpath.setNamespaceContext(new javax.xml.namespace.NamespaceContext() {
                @Override
                public String getNamespaceURI(String prefix) {
                    return "ns2".equals(prefix) ? "http://www.3ds.com/enovia/e6wv2" : javax.xml.XMLConstants.NULL_NS_URI;
                }

                @Override
                public String getPrefix(String namespaceURI) { return null; }
                @Override
                public java.util.Iterator<String> getPrefixes(String namespaceURI) { return null; }
            });

            // 解析XML为Document对象
            Document doc = javax.xml.parsers.DocumentBuilderFactory.newInstance().newDocumentBuilder()
                    .parse(new InputSource(new StringReader(coreXml)));

            // 提取目标值
            String statusCode = xpath.evaluate("/ns2:services/ns2:serviceData/ns2:statusCode", doc);
            String success = xpath.evaluate("/ns2:services/ns2:serviceData/ns2:success", doc);
            String csrfName = xpath.evaluate("/ns2:services/ns2:serviceData/ns2:csrf/@name", doc);
            String csrfValue = xpath.evaluate("/ns2:services/ns2:serviceData/ns2:csrf/@value", doc);

            // 输出结果
            System.out.println("statusCode: " + statusCode);
            System.out.println("success: " + success);
            System.out.println("csrf name: " + csrfName);
            System.out.println("csrf value: " + csrfValue);

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

关键说明 #

• 必须注册XML的命名空间，否则XPath无法识别带前缀的标签
• 先剥离外层的<p><code>标签，避免解析时出现非XML结构的错误

方法二：使用Jackson XML（简洁高效，需引入依赖） #

如果项目已使用Jackson，这种方式代码更简洁，无需手动操作DOM。

第一步：引入Maven依赖 #

<dependency>
    <groupId>com.fasterxml.jackson.dataformat</groupId>
    <artifactId>jackson-dataformat-xml</artifactId>
    <version>2.15.2</version> <!-- 使用最新稳定版 -->
</dependency>

第二步：编写实体类映射XML结构 #

import com.fasterxml.jackson.dataformat.xml.annotation.JacksonXmlProperty;
import com.fasterxml.jackson.dataformat.xml.annotation.JacksonXmlRootElement;

@JacksonXmlRootElement(localName = "services", namespace = "http://www.3ds.com/enovia/e6wv2")
public class Services {
    @JacksonXmlProperty(localName = "serviceData", namespace = "http://www.3ds.com/enovia/e6wv2")
    private ServiceData serviceData;

    // getter & setter
    public ServiceData getServiceData() { return serviceData; }
    public void setServiceData(ServiceData serviceData) { this.serviceData = serviceData; }

    public static class ServiceData {
        @JacksonXmlProperty(localName = "statusCode", namespace = "http://www.3ds.com/enovia/e6wv2")
        private String statusCode;
        @JacksonXmlProperty(localName = "success", namespace = "http://www.3ds.com/enovia/e6wv2")
        private String success;
        @JacksonXmlProperty(localName = "csrf", namespace = "http://www.3ds.com/enovia/e6wv2")
        private Csrf csrf;

        // getter & setter
        public String getStatusCode() { return statusCode; }
        public void setStatusCode(String statusCode) { this.statusCode = statusCode; }
        public String getSuccess() { return success; }
        public void setSuccess(String success) { this.success = success; }
        public Csrf getCsrf() { return csrf; }
        public void setCsrf(Csrf csrf) { this.csrf = csrf; }
    }

    public static class Csrf {
        @JacksonXmlProperty(isAttribute = true)
        private String name;
        @JacksonXmlProperty(isAttribute = true)
        private String value;

        // getter & setter
        public String getName() { return name; }
        public void setName(String name) { this.name = name; }
        public String getValue() { return value; }
        public void setValue(String value) { this.value = value; }
    }
}

第三步：解析XML并提取值 #

import com.fasterxml.jackson.dataformat.xml.XmlMapper;

public class JacksonXmlExtractor {
    public static void main(String[] args) {
        String xmlStr = "<p><code><?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"yes\"?><ns2:services xmlns:ns2=\"http://www.3ds.com/enovia/e6wv2\"><ns2:serviceData><ns2:statusCode>200</ns2:statusCode><ns2:success>true</ns2:success><ns2:csrf name=\"ENO_CSRF_TOKEN\" value=\"JYOF-K5LS-INZM-15O3-4O00-VTBJ-R28O-YY2P\"/></ns2:serviceData></ns2:services></code></p>";
        String coreXml = xmlStr.substring(xmlStr.indexOf("<?xml"), xmlStr.indexOf("</ns2:services>") + "</ns2:services>".length());

        try {
            XmlMapper xmlMapper = new XmlMapper();
            Services services = xmlMapper.readValue(coreXml, Services.class);

            // 提取目标值
            String statusCode = services.getServiceData().getStatusCode();
            String success = services.getServiceData().getSuccess();
            String csrfName = services.getServiceData().getCsrf().getName();
            String csrfValue = services.getServiceData().getCsrf().getValue();

            // 输出结果
            System.out.println("statusCode: " + statusCode);
            System.out.println("success: " + success);
            System.out.println("csrf name: " + csrfName);
            System.out.println("csrf value: " + csrfValue);

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

关键说明 #

• 实体类的命名空间、标签名必须和XML完全对应
• @JacksonXmlProperty(isAttribute = true)用于标记XML属性（如csrf的name和value）

内容的提问来源于stack exchange，提问作者Praveen s