Java爬取网页指定内容

• 爬取网页文字：

• import org.jsoup.Jsoup;
  import org.junit.Test;
  
  import java.io.IOException;
  
  public class Crawling {
  
  
      public static void Test() throws IOException {
          Jsoup.connect("https://soccer.hupu.com/").get().body().
                  getElementsByClass("list-item"). //class="list-item-title"
                  forEach(e->{
              System.out.println(e.text());
          });
  
      }
  
      public static void main(String[] args) {
          try {
              Test();
          } catch (IOException e) {
              e.printStackTrace();
          }
      }
  
  }

• 爬取网页图片地址：

• import org.jsoup.Jsoup;
  import org.junit.Test;
  
  import java.io.IOException;
  
  public class Crawling {
  
      public static void Test() throws IOException {
          Jsoup.connect("https://soccer.hupu.com/").get().body().
                  getElementsByClass("list-item-img").
                  forEach(e->{
              System.out.println(e.attr("src")); //src标签图片地址
          });
      }
  
      public static void main(String[] args) {
          try {
              Test();
          } catch (IOException e) {
              e.printStackTrace();
          }
      }
  
  }

标签：static,网页,爬取,Jsoup,IOException,import,Test,Java,public
来源： https://www.cnblogs.com/subtlman/p/15958233.html