[Java] java利用Jsoup爬取糗事百科数据

一、首先，引入依赖jar包


org.jsoup
jsoup
1.11.3

二、编写方法
import java.io.IOException;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

/*

• 爬虫
  /
  public class MainActivity {
  /
  * Jsoup爬取糗事百科数据
  */
  public static List<Map<String,String>> spider(String url,int pages){

            List<Map<String,String>> list = new ArrayList<Map<String,String>>();
    try {
        Document mozilla = Jsoup.connect(url+"/page/"+pages)
                .userAgent("Mozilla")
                .timeout(3000)
                .get();
        Elements select1 = mozilla.select("div.article.block");
        for (Element element : select1) {
            Document parse = Jsoup.parse(element.toString());
            Elements select = parse.select("a h2");//作者
            Elements select2 = parse.select("a img");//作者头像
            Elements select3 = parse.select("a.contentHerf");//内容
            Elements select4 = parse.select("div.thumb img");//内容图片
            Elements select5 = parse.select("span.stats-vote i");//赞数量
            Map<String,String> map = new HashMap<String, String>();
                        map.put("author", select.text());//作者
                        map.put("author_img", select2.size()>0?"http:"+select2.attr("src"):"");//作者头像
                        map.put("content", select3.text());//内容
                        map.put("content_img",  select4.size()>0?"http:"+select4.attr("src"):"");//内容图片
                        map.put("number",  select5.text());//赞数量
                        list.add(map);
        }
        
    } catch (IOException e) {
            list = null;
    }
    return list;
    }
  

}

三，测试
String url = “https://www.qiushibaike.com/8hr/page/”;
List<Map<String, String>> list = MainActivity.spider(url, 1);