webMagic--注解爬取数据

 
 
import us.codecraft.webmagic.Site;
import us.codecraft.webmagic.model.ConsolePageModelPipeline;
import us.codecraft.webmagic.model.OOSpider;
import us.codecraft.webmagic.model.annotation.ExtractBy;
import us.codecraft.webmagic.model.annotation.TargetUrl;
import us.codecraft.webmagic.pipeline.JsonFilePipeline;
import us.codecraft.webmagic.scheduler.RedisScheduler;

/**
* @auther mxh
* @time 2019/5/22 10:22
*/
@TargetUrl("https://b.faloo.com/y/0/0/0/0/0/0/[\\d+].html")
public class Demo {

@ExtractBy("//div[@class=\"l_bar\"]/div[@class=\"l_rc\"]/div[@class=\"l_title a_666\"]/h1/a/text()")
private String name;

@ExtractBy("//div[@class=\"l_bar\"]/div[@class=\"l_rc\"]/div[@class=\"l_title a_666\"]/span/allText()")
private String auther;

@ExtractBy("//div[@class=\"l_bar\"]/div[@class=\"l_rc\"]/div[@class=\"l_con\"]/a/text()")
private String introduce;

/*==============get/set=============*/

public String getName() {
return name;
}

public void setName(String name) {
this.name = name;
}

public String getAuther() {
return auther;
}

public void setAuther(String auther) {
this.auther = auther;
}

public String getIntroduce() {
return introduce;
}

public void setIntroduce(String introduce) {
this.introduce = introduce;
}

public static void main(String[] args) {
OOSpider.create(Site.me(), new ConsolePageModelPipeline(), Demo.class)
.addUrl("https://b.faloo.com/y/0/0/0/0/0/0/1.html")
// new QueueScheduler().setDuplicateRemover(new BloomFilterDuplicateRemover(10000000))
.setScheduler(new RedisScheduler("127.0.0.1"))
.addPipeline(new JsonFilePipeline("D:\\webmagic\\"))
.thread(4)
.run();
}

}
 

猜你喜欢

转载自www.cnblogs.com/mxh-java/p/10906420.html