java爬虫入门教程

java爬虫之爬基金增长情况
先上pom文件

 <dependencies>

        <dependency>
            <groupId>org.jsoup</groupId>
            <artifactId>jsoup</artifactId>
            <version>1.12.1</version>
        </dependency>

        <dependency>
            <groupId>org.fusesource</groupId>
            <artifactId>sigar</artifactId>
            <version>1.6.4</version>
        </dependency>

        <dependency>
            <groupId>org.apache.httpcomponents</groupId>
            <artifactId>httpclient</artifactId>
            <version>4.5.2</version>
        </dependency>

        <dependency>
            <groupId>net.sourceforge.htmlunit</groupId>
            <artifactId>htmlunit</artifactId>
            <version>2.23</version>
            <exclusions>
                <exclusion>
                    <artifactId>httpclient</artifactId>
                    <groupId>org.apache.httpcomponents</groupId>
                </exclusion>
            </exclusions>
        </dependency>
    </dependencies>

代码

package com.test;

import java.util.ArrayList;
import java.util.List;
import org.apache.http.Consts;
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.select.Elements;



public class HelloWorld {
	
	public static void main(String[] args) throws Exception {
		
        // 需要爬取的基金编号
		List<String> codes = new ArrayList<String>();
		
		codes.add("003834");
		codes.add("002251");
		codes.add("161725");
		codes.add("003095");
		
		List<String>  result = new ArrayList<String>();
		
		for (int i = 0; i < codes.size(); i++) {
			
			String url = "http://fundgz.1234567.com.cn/js/"+codes.get(i)+".js?rt="+System.currentTimeMillis();
			
			HttpGet httpGet = new HttpGet(url);
			CloseableHttpClient httpclient = HttpClients.createDefault();
			
			httpGet.setHeader("user-agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36");
			CloseableHttpResponse response = httpclient.execute(httpGet);
			int statusCode = response.getStatusLine().getStatusCode();
			try {
				HttpEntity entity = response.getEntity();
				if (statusCode == 200) {
					String html = EntityUtils.toString(entity, Consts.UTF_8);
					
					Document doc = null;
					
					doc = Jsoup.parse(html);
					
					Elements ulList = doc.select("body");
					
					String now = ulList.toString();
					
					now = now.substring(now.indexOf("{"), now.indexOf("}")+1);

					
					result.add(now);
					
					
					EntityUtils.consume(response.getEntity());
				}else {
					EntityUtils.consume(response.getEntity());
				}
			} finally {
				response.close();
			}
		}
		System.out.println(result);
		for (int i = 0; i < result.size(); i++) {
			
			System.out.println(result.get(i));
		}
	}
	
}

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值