WebMagic爬取应用市场应用信息

WebMagic资料

官方教程 http://webmagic.io/docs/zh/

官方网址 http://webmagic.io/

代码实现

爬取华为应用市场应用信息，统计华为应用市场应用数量，启动20个线程，自定义MyPiple来保存数据。

AppStoreProcessor.java主类

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

/**
 * @author wzj
 * @create 2018-07-17 22:06
 **/
public class AppStoreProcessor implements PageProcessor
{
    // 部分一：抓取网站的相关配置，包括编码、抓取间隔、重试次数等
    private Site site = Site.me().setRetryTimes(3).setSleepTime(100);

    public void process(Page page)
    {
        //获取名称
        String name = page.getHtml().xpath("//p/span[@class='title']/text()").toString();

        page.putField("appName",name );

        if (page.getResultItems().get("appName") == null)
        {
            //skip this page
            page.setSkip(true);
        }

        //获取页面其他链接
        Selectable links = page.getHtml().links();
        page.addTargetRequests(links.regex("(http://app.hicloud.com/app/C\\d+)").all());
    }


    public Site getSite()
    {
        return site;
    }

    public static void main(String[] args)
    {
        Spider.create(new AppStoreProcessor())

                .addUrl("http://app.hicloud.com")
                .addPipeline(new MyPipeline())
                .thread(20)
                .run();
    }
}

自定义Piple，将结果保存到D:\\cache\\appstore.txt中

import us.codecraft.webmagic.ResultItems;
import us.codecraft.webmagic.Task;
import us.codecraft.webmagic.pipeline.Pipeline;

import java.io.FileWriter;
import java.io.IOException;

/**
 * @author wzj
 * @create 2018-07-17 22:16
 **/
public class MyPipeline implements Pipeline
{
    /**
     * 写入文件
     */
    private FileWriter fileWriter;

    /*
     * 统计数目
     */
    private int count = 1;


    public MyPipeline()
    {
        try
        {
            this.fileWriter = new FileWriter("D:\\cache\\appstore.txt");
        }
        catch (IOException e)
        {
            e.printStackTrace();
        }
    }

    /**
     * Process extracted results.
     *
     * @param resultItems resultItems
     * @param task        task
     */
    public void process(ResultItems resultItems, Task task)
    {
        String appName = resultItems.get("appName");
        String content = String.valueOf(count) + " " + appName;

        try
        {
            fileWriter.write(content);
            fileWriter.write("\n");
            fileWriter.flush();
        }
        catch (IOException e)
        {
            e.printStackTrace();
        }

        System.out.println(content);

        count ++;
    }
}