java 代码从网站提取数据

Posted 2021-05-08

import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.URL;
import java.net.URLConnection;


public class Scraping {

    public static void main(String[] args) throws IOException {

        URL url = new URL("http://www.ase.com.jo/ar/bulletins/daily");

        URLConnection con = url.openConnection();
        InputStream is =con.getInputStream();
        BufferedReader br = new BufferedReader(new InputStreamReader(is));

        String line = null;

        while ((line = br.readLine()) != null) {
            System.out.println(line);
        }
    }
}

import java.io.IOException;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

public class Extracting {
   public static void main(String[] args) {
      String html = "http://www.ase.com.jo/ar/bulletins/daily";
      try {
         Document doc = Jsoup.connect(html).get();
         Elements tableElements = doc.select("table");

         Elements tableHeaderEles = tableElements.select("thead tr th");
         System.out.println("headers");
         for (int i = 0; i < tableHeaderEles.size(); i++) {
            System.out.println(tableHeaderEles.get(i).text());
         }
         System.out.println();

         Elements tableRowElements = tableElements.select(":not(thead) tr");

         for (int i = 0; i < tableRowElements.size(); i++) {
            Element row = tableRowElements.get(i);
            System.out.println("row");
            Elements rowItems = row.select("td");
            for (int j = 0; j < rowItems.size(); j++) {
               System.out.print("	"+rowItems.get(j).text());
            }
            System.out.println();
         }

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