trush / webmagic-canrd-service · Files

package com.canrd.webmagic.processor;

import com.canrd.webmagic.processor.pipeline.ArticlePipeline;
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.Html;

public class ChemicalPagePcoessor implements PageProcessor {
    private Site site = Site.me().setRetryTimes(3).setSleepTime(100);
    @Override
    public void process(Page page) {

    };

    public void doArticleContent(Page page){
        Html html = page.getHtml();

    }

    public static void main(String[] args) {
        // 创建一个Spider，并把我们的处理器放进去
        Spider.create(new ChemicalPagePcoessor())
                // 添加这个Spider要爬取的网页地址
                .addUrl("https://www.nature.com/nature/research-articles?sort=PubDate&page=1")
                .addPipeline(new ArticlePipeline())
                // 开启5个线程执行，并开始爬取
                .thread(5).run();
    }
}