42 lines
1.6 KiB
Java
42 lines
1.6 KiB
Java
package us.codecraft.webmagic.samples;
|
|
|
|
import us.codecraft.webmagic.Page;
|
|
import us.codecraft.webmagic.Site;
|
|
import us.codecraft.webmagic.Spider;
|
|
import us.codecraft.webmagic.monitor.SpiderMonitor;
|
|
import us.codecraft.webmagic.processor.PageProcessor;
|
|
import us.codecraft.webmagic.scheduler.BloomFilterDuplicateRemover;
|
|
import us.codecraft.webmagic.scheduler.QueueScheduler;
|
|
|
|
import javax.management.JMException;
|
|
import java.util.List;
|
|
|
|
/**
|
|
* @author code4crafter@gmail.com <br>
|
|
*/
|
|
public class OschinaBlogPageProcesser implements PageProcessor {
|
|
|
|
private Site site = Site.me().setDomain("my.oschina.net").addStartUrl("http://my.oschina.net/flashsword/blog");
|
|
|
|
@Override
|
|
public void process(Page page) {
|
|
List<String> links = page.getHtml().links().regex("http://my\\.oschina\\.net/flashsword/blog/\\d+").all();
|
|
page.addTargetRequests(links);
|
|
page.putField("title", page.getHtml().xpath("//div[@class='BlogEntity']/div[@class='BlogTitle']/h1/text()").toString());
|
|
page.putField("content", page.getHtml().xpath("//div[@class='BlogContent']/tidyText()").toString());
|
|
page.putField("tags",page.getHtml().xpath("//div[@class='BlogTags']/a/text()").all());
|
|
}
|
|
|
|
@Override
|
|
public Site getSite() {
|
|
return site;
|
|
|
|
}
|
|
|
|
public static void main(String[] args) throws JMException {
|
|
Spider spider = Spider.create(new OschinaBlogPageProcesser()).setScheduler(new QueueScheduler().setDuplicateRemover(new BloomFilterDuplicateRemover(2000)));
|
|
SpiderMonitor.instance().register(spider);
|
|
spider.run();
|
|
}
|
|
}
|