Java读取网站XML数据并提取geoplugin_countryName字段方法

方法一：使用Java标准DOM解析器 #

先修改原有代码，将XML内容拼接为完整字符串，再通过DOM解析提取目标字段：

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 java.io.ByteArrayInputStream;
import java.io.InputStreamReader;
import java.net.URL;
import java.nio.charset.StandardCharsets;

public class GeoPluginParser {
    public static void main(String[] args) {
        try {
            URL url = new URL("http://www.geoplugin.net/xml.gp?ip=xx.xx.xx.xx");
            // 读取并拼接完整XML内容
            StringBuilder xmlContent = new StringBuilder();
            InputStreamReader reader = new InputStreamReader(url.openStream(), StandardCharsets.UTF_8);
            int c;
            while ((c = reader.read()) != -1) {
                xmlContent.append((char) c);
            }
            reader.close();

            // 初始化DOM解析器
            DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
            DocumentBuilder builder = factory.newDocumentBuilder();
            Document doc = builder.parse(new ByteArrayInputStream(xmlContent.toString().getBytes(StandardCharsets.UTF_8)));

            // 提取国家名称
            NodeList countryNameNodes = doc.getElementsByTagName("geoplugin_countryName");
            if (countryNameNodes.getLength() > 0) {
                Element countryElement = (Element) countryNameNodes.item(0);
                String countryName = countryElement.getTextContent().trim();
                System.out.println("国家名称：" + countryName);
            } else {
                System.out.println("未找到国家名称字段");
            }
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}

方法二：使用XPath简化解析 #

XPath可直接定位目标节点，代码更简洁：

import javax.xml.xpath.XPath;
import javax.xml.xpath.XPathFactory;
import org.w3c.dom.Document;
import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import java.io.InputStream;
import java.net.URL;

public class GeoPluginXPathParser {
    public static void main(String[] args) {
        try {
            URL url = new URL("http://www.geoplugin.net/xml.gp?ip=xx.xx.xx.xx");
            InputStream inputStream = url.openStream();

            DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
            DocumentBuilder builder = factory.newDocumentBuilder();
            Document doc = builder.parse(inputStream);

            XPath xpath = XPathFactory.newInstance().newXPath();
            String countryName = xpath.evaluate("/geoPlugin/geoplugin_countryName", doc).trim();
            System.out.println("国家名称：" + countryName);

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

注意事项 #

• 实际开发中务必处理网络、XML解析等异常，避免程序崩溃
• XML结构固定时，XPath方式代码更简洁易维护
• 不推荐用正则表达式解析XML（结构变动时易失效），若临时使用可参考匹配规则：<geoplugin_countryName>(.*?)</geoplugin_countryName>

内容的提问来源于stack exchange，提问作者Destroy