Commit 5dc9fe95 authored by yihua.huang's avatar yihua.huang

interface of PageMapper #120

parent 7668731f
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 code4crafter@gmail.com <br>
* @since 0.3.2
*/
public class GithubRepoPageProcessor implements PageProcessor {
private Site site = Site.me().setRetryTimes(3);
private PageMapper<GithubRepo> githubRepoPageMapper = new PageMapper<GithubRepo>(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);
page.putField("repo",githubRepo);
}
@Override
public Site getSite() {
return site;
}
public static void main(String[] args) {
Spider.create(new GithubRepoPageProcessor()).addUrl("https://github.com/code4craft").thread(5).run();
}
}
\ No newline at end of file
package us.codecraft.webmagic.model;
import us.codecraft.webmagic.Page;
/**
* @author code4crafer@gmail.com
* @since 0.5.2
*/
public class PageMapper<T> {
private Class<T> clazz;
public PageMapper(Class<T> clazz) {
this.clazz = clazz;
}
public T get(Page page){
return null;
}
}
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment