us.codecraft.webmagic.example.GithubRepoPageMapper Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of webmagic-extension Show documentation

The newest version!

package us.codecraft.webmagic.example;

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

/**
 * @author [email protected] 

 * @since 0.3.2
 */
public class GithubRepoPageMapper implements PageProcessor {

    private Site site = Site.me().setRetryTimes(3).setSleepTime(0);

    private PageMapper githubRepoPageMapper = new PageMapper(GithubRepo.class);

    @Override
    public void process(Page page) {
        page.addTargetRequests(page.getHtml().links().regex("(https://github\\.com/\\w+/\\w+)").all());
        page.addTargetRequests(page.getHtml().links().regex("(https://github\\.com/\\w+)").all());
        GithubRepo githubRepo = githubRepoPageMapper.get(page);
        if (githubRepo == null) {
            page.setSkip(true);
        } else {
            page.putField("repo", githubRepo);
        }

    }

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

    public static void main(String[] args) {
        Spider.create(new GithubRepoPageMapper()).addUrl("https://github.com/code4craft").thread(5).run();
    }
}