ChemicalPagePcoessor.java
1.4 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
package com.canrd.webmagic.processor;
import com.canrd.webmagic.DNS.DnsResolver;
import com.canrd.webmagic.processor.pipeline.ArticlePipeline;
import com.gargoylesoftware.htmlunit.AbstractPage;
import us.codecraft.webmagic.Page;
import us.codecraft.webmagic.Request;
import us.codecraft.webmagic.Site;
import us.codecraft.webmagic.Spider;
import us.codecraft.webmagic.processor.PageProcessor;
import us.codecraft.webmagic.selector.Html;
import us.codecraft.webmagic.selector.PlainText;
public class ChemicalPagePcoessor implements PageProcessor {
private Request request;
String domain = new PlainText(request.getUrl()).regex("//(.*?)/").get();
String ip = DnsResolver.resolve(domain);
private Site site = Site.me().setRetryTimes(3).setSleepTime(100).setDomain(domain).addCookie("ip", ip);;
@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();
}
}