赞
踩
- package com.example.demo.controller;
-
- import org.apache.http.HttpEntity;
- import org.apache.http.client.methods.CloseableHttpResponse;
- import org.apache.http.client.methods.HttpGet;
- import org.apache.http.impl.client.CloseableHttpClient;
- 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;
-
- import java.io.IOException;
-
- /**
- * Created with IntelliJ IDEA.
- *
- * @Auther: ljt
- * @Version 1.0
- * @Date: 2020/08/04/15:49
- * @Description:
- */
- public class JsoupTest {
-
- public static void main(String[] args) throws IOException {
- String url = "http://ivi.bupt.edu.cn";
- CloseableHttpClient httpClient = HttpClients.createDefault();//创建httpClient
- HttpGet httpGet = new HttpGet(url);//创建httpget实例
-
- CloseableHttpResponse response = httpClient.execute(httpGet);//执行get请求
- HttpEntity entity = response.getEntity();//获取返回实体
- String content = EntityUtils.toString(entity,"utf-8");//网页内容
- response.close();//关闭流和释放系统资源
-
- Jsoup.parse(content);
- Document doc = Jsoup.parse(content);//解析网页得到文档对象
- Elements elements = doc.getElementsByTag("title");//获取tag是title的所有dom文档
- Element element = elements.get(0);//获取第一个元素
- String title = element.text(); //.html是返回html
- System.out.println("网页标题:"+title);
-
- Elements div = doc.getElementsByClass("2u");
- for(int i=0 ; i < div.size() ; i++){
- String nameStr = div.get(i).getElementsByTag("p").text();
-
- System.out.println("------------------------------------------");
- System.out.println("电视台:"+ nameStr);
- Elements a = div.get(i).getElementsByTag("a");
- for(int j=0; j<a.size(); j++){
- String path = a.get(j).attr("href");
- String name = a.get(j).text();
- System.out.println(name+","+url+path);
- }
-
- }
-
-
-
-
- }
-
-
-
- }
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。