java爬虫(Jsoup)爬取某新闻站点标题

​需要一个包：jsoup-1.7.3.jar​ 

​有一定的java和js基础​

package wang.test;

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 JsoupTestTitle {
  public static void main(String[] args) throws Exception {
    getWuMaoW();
  }

  // 获取http://www.ltaaa.com/
  public static void getWuMaoW() {
    String url = "http://www.ltaaa.com/";
    Document doc = null;
    try {
      doc = Jsoup.connect(url).get();
      Elements listDiv = doc.getElementsByAttributeValue("class", "show");
      for (Element element : listDiv) {
        Elements texts = element.getElementsByTag("a");
        for (Element text : texts) {

          // 取所有文本
          // String ptext = text.text();

          String ptext = text.attr("title");
          System.out.println("标题：" + ptext);

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

}