基于HttpClient、Jsoup的爬虫获取指定网页内容

import org.apache.http.HttpEntity;
import org.apache.http.HttpResponse;
import org.apache.http.client.HttpClient;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.HttpClients;
import org.apache.http.util.EntityUtils;

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

public class Main {

    public static void main(String[] args) throws IOException{
        try {
            //创建client实例
            HttpClient client= HttpClients.createDefault();
            //创建httpget实例
            HttpGet httpGet=new HttpGet("http://www.btba.com.cn");
            //执行 get请求
            HttpResponse response=client.execute(httpGet);
            //返回获取实体
            HttpEntity entity=response.getEntity();
            //获取网页内容，指定编码
            String web= EntityUtils.toString(entity,"UTF-8");
            //输出网页
            System.out.println(web);
            Document doc= Jsoup.parse(web);
            Elements links=doc.select("a[href~=http://www.btba.com.cn/type/*]");//选择器，选取特征信息
            String webs=null;
            for (Element link:links) {
                webs=link.attr("abs:href").toString();
                System.out.println(webs+"\t\t"+link.text());//输出特征信息
            }

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


    }
}