如果我从这个站点复制并粘贴 xml 到一个 xml 文件中，我可以用 java 解析它

http://api.indeed.com/ads/apisearch?publisher=8397709210207872&q=java&l=austin%2C+tx&sort&radius&st&jt&start&limit&fromage&filter&latlong=1&chnl&userip=1.2.3.4&v=2

但是，如果可能的话，我想直接从网页解析它!

这是我当前的代码:

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

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

import java.io.File;
import java.io.IOException;

  public class XMLParser {

public void readXML(String parse) {
    File xml = new File(parse);
    DocumentBuilderFactory dbFactory = DocumentBuilderFactory.newInstance();
    DocumentBuilder dBuilder;
    try {
        dBuilder = dbFactory.newDocumentBuilder();
        Document doc = dBuilder.parse(xml);
 //         System.out.println("Root element :"
 //                 + doc.getDocumentElement().getNodeName());

        NodeList nList = doc.getElementsByTagName("result");

        System.out.println("----------------------------");

        for (int temp = 0; temp < nList.getLength(); temp++) {

            Node nNode = nList.item(temp);

 //             System.out.println("\nCurrent Element :" + 
     nNode.getNodeName());

            if (nNode.getNodeType() == Node.ELEMENT_NODE) {

                Element eElement = (Element) nNode;

                System.out.println("job title : "
                        + 
 eElement.getElementsByTagName("jobtitle").item(0)
                        .getTextContent());;
                System.out.println("Company: "
                        + 
  eElement.getElementsByTagName("company")

 .item(0).getTextContent());
                System.out.println("City : "
                        + 
  eElement.getElementsByTagName("city").item(0)
                                .getTextContent());
                System.out.println("State : "
                        + 
eElement.getElementsByTagName("state").item(0)
                                .getTextContent());
                System.out.println("Country : "
                        + 
eElement.getElementsByTagName("country").item(0)
                                .getTextContent());
                System.out.println("Date posted : "
                        + 
     eElement.getElementsByTagName("date").item(0)
                                .getTextContent());
                System.out.println("Job summary : "
                        + 
    eElement.getElementsByTagName("snippet").item(0)
                                .getTextContent());
                System.out.println("Latitude : "
                        +      
 eElement.getElementsByTagName("latitude").item(0).getTextContent());
                System.out.println("longitude : "
                        +     
eElement.getElementsByTagName("longitude").item(0).getTextContent());

            }
        }

    } catch (ParserConfigurationException | SAXException | IOException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    }

}

public static void main(String[] args) {
    new XMLParser().readXML("test.xml");
}
 }

如有任何帮助，我们将不胜感激。

最佳答案

给它 URI 而不是 XML。它会为您下载。

文档 doc = dBuilder.parse(uriString)

关于java - 从网页解析 XML，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/15851700/