csdn 涨粉攻略 代码

csdn 涨粉攻略 代码,第1张

获取关注者数目 

package com.web;

import java.util.List;

import us.codecraft.webmagic.Page;
import us.codecraft.webmagic.Site;
import us.codecraft.webmagic.processor.PageProcessor;
import us.codecraft.webmagic.selector.JsonPathSelector;


public class FollowCountSpider implements PageProcessor {

    /*
https://blog.csdn.net/community/home-api/v1/get-follow-list?page=1&size=100&noMore=false&blogUsername= + username

     */

    private final String TAG = FollowCountSpider.class.getSimpleName();


    Integer count = 0;


    private Site site = Site
            .me()
            .setDomain("blog.csdn.net")
            .setSleepTime(1000)
            // 便于测试,休眠较长时间。
            .setUserAgent(
                    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_2) AppleWebKit/537.31 (KHTML, like Gecko) Chrome/26.0.1410.65 Safari/537.31");

    @Override
    public void process(Page page) {
        String rawText = page.getRawText();
        String data = new JsonPathSelector("$.data").select(rawText);
        String replace = data.replace("{list=", "{\"list\":");
        List selectList = new JsonPathSelector("$.list").selectList(replace);
        count = selectList.size();
    }

    @Override
    public Site getSite() {
        return site;
    }

}

测试类

/*
 * 

文件名称: T2.java

*

项目描述: ALIPAY 交易系统

*

公司名称: 杭州市阿里科技股份有限公司

*

版权所有: (C) 2022-2023

*/ package com.web; import us.codecraft.webmagic.Spider; /** * @author globalcoding * @since 2022/5/9 15:28 */ public class T2 { public static void main(String[] args) { String username = ""; String pageIndex = "1"; int followCount = 0; for (int i = 1; ; i++) { String fanUrl = "https://blog.csdn.net/community/home-api/v1/get-follow-list?page=" + i + "&size=20&noMore=false&blogUsername=" + username; FollowCountSpider followCountSpider = new FollowCountSpider(); Spider.create(followCountSpider).addUrl(fanUrl).thread(1).run(); if (followCountSpider.count < 20) { followCount = (i-1) * 20 + followCountSpider.count; break; } } System.out.println(followCount); } }

欢迎分享,转载请注明来源:内存溢出

原文地址: https://outofmemory.cn/langs/889895.html

(0)
打赏 微信扫一扫 微信扫一扫 支付宝扫一扫 支付宝扫一扫
上一篇 2022-05-14
下一篇 2022-05-14

发表评论

登录后才能评论

评论列表(0条)

保存