博客刷访问次数

import java.net.HttpURLConnection;
import java.net.URL;
import java.net.URLConnection;

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

public class CSDNCrawler implements PageProcessor{

    private int k=0;
    private Site site=Site.me()
            .setDomain("http://www.csdn.net/")
            .setTimeOut(5000)
            .setRetryTimes(2)
            .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");
    private static final String URL_LIST1="http://blog\\.csdn\\.net/khuangliang/article/list/\\d";
    private static Spider sp=Spider.create(new CSDNCrawler());


    @Override
    public void process(Page page) {
        // TODO Auto-generated method stub
        if(page.getUrl().regex(URL_LIST1).match()){
            System.out.println("分页链接");
            //添加分页下所有文章的连接
            page.addTargetRequests(page.getHtml().xpath("//h1").links().all());
            page.addTargetRequests(page.getHtml().links().regex(URL_LIST1).all());
        }else{
            String curl=page.getUrl().toString();
            System.out.println("文章连接"+curl);

            for(int i=0;i<50;i++){
            try {
                URL url = new URL(curl);
                URLConnection URLconnection = url.openConnection();
                HttpURLConnection httpConnection = (HttpURLConnection) URLconnection;
                httpConnection.setRequestProperty("User-Agent", "Mozilla/4.0 (compatible; MSIE 5.0; Windows NT; DigExt)");
                int responseCode = httpConnection.getResponseCode();
                if (responseCode == HttpURLConnection.HTTP_OK) {
                    k++;
                    System.err.println("成功"+k);   
                    URLconnection.connect();
                } else {
                    System.err.println("失败");
                }
            } catch (Exception e) {
                e.printStackTrace();
            }
        }
        }

    }

    @Override
    public Site getSite() {
        // TODO Auto-generated method stub
        return site;
    }

    public static void main(String args[]){
        for(int i=0;i<100;i++){
        CSDNCrawler crawler=new CSDNCrawler();
        crawler.sp.addUrl("http://blog.csdn.net/khuangliang/article/list/1")
        .run();
        }
    }
}

（1） 首先通过爬虫获取所有的文章的连接，使用的是webmagic 国人自己写的爬虫。
（2）对于每个链接设置访问50次，通过爬虫来设置循环爬多少次试过不行，每次都得重新编译运行，看插件源码，是在run（）结束后把所有的线程都关闭了，所以在主函数里写100次是没有用的