csdn 涨粉攻略 代码(二)粉丝数 webmagic 爬虫

获取粉丝数目

package com.web;

import java.util.regex.Matcher;
import java.util.regex.Pattern;

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


public class FanCountSpider implements PageProcessor {

    

    private final String TAG = FanCountSpider.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();
        count = getCount(rawText);
    }

    public Integer getCount(String line) {
        String pattern = "(id="fan">\d+?<)";

        // 创建 Pattern 对象
        Pattern r = Pattern.compile(pattern);

        // 现在创建 matcher 对象
        Matcher m = r.matcher(line);
        if (m.find()) {
            String fanCount = m.group(0);
            String replace = fanCount.replace("id="fan">", "");
            String result = replace.replace("<", "");
            return Integer.parseInt(result);
        }

        return 0;
    }

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

}

测试类

package com.web;

import us.codecraft.webmagic.Spider;


public class T2 {
    public static void main(String[] args) {
        String username = "";
        String fanUrl = "https://blog.csdn.net/" + username + "/article/list/";
        FanCountSpider fanCountSpider = new FanCountSpider();
        Spider.create(fanCountSpider).addUrl(fanUrl).thread(1).run();
        System.out.println(fanCountSpider.count);
    }
}