当前位置:Gxlcms > 数据库问题 > webmagic自定义存储(mysql、redis存储)

webmagic自定义存储(mysql、redis存储)

时间:2021-07-01 10:21:17 帮助过:57人阅读

com.mdd.pip.pipeLine; import java.util.List; import org.springframework.beans.factory.annotation.Autowired; import org.springframework.stereotype.Component; import com.mdd.pip.model.ProxyIp; import com.mdd.pip.service.ProxyIpService; import us.codecraft.webmagic.ResultItems; import us.codecraft.webmagic.Task; import us.codecraft.webmagic.pipeline.Pipeline; @Component public class DataPipeLine implements Pipeline { @Autowired private ProxyIpService proxyIpService; /** * mysql 存储 */ /* * public void process(ResultItems resultItems, Task task) { * List<ProxyIp>proxyIpList = resultItems.get("proxyIpList"); * if(proxyIpList!=null&&!proxyIpList.isEmpty()){ * proxyIpService.saveProxyIpList(proxyIpList); } * * } */ /** * redis 存储 */ public void process(ResultItems resultItems, Task task) { List<ProxyIp> proxyIpList = resultItems.get("proxyIpList"); if (proxyIpList != null && !proxyIpList.isEmpty()) { proxyIpService.saveProxyListIpInRedis(proxyIpList); } } }
ResultItems 对象本质是一个Map。因此要我们保存对象的时候,只需要在爬取时把爬取得数据封装成对象,保存在
ResultItems 里即可。如果有很多数据,则可以考虑用List保存。
package com.mdd.pip.crawler;

import java.util.ArrayList;
import java.util.List;

import org.apache.log4j.Logger;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import org.springframework.stereotype.Component;

import com.mdd.pip.model.ProxyIp;
import us.codecraft.webmagic.Page;
import us.codecraft.webmagic.Site;
import us.codecraft.webmagic.processor.PageProcessor;

/**
 * 热刺代理网站ip抓取
 * 
 * @author xwl 2017.6.3
 */
@Component
public class XiCiProxyIpCrawler implements PageProcessor {

    private Logger logger = Logger.getLogger(XiCiProxyIpCrawler.class);

    // 部分一:抓取网站的相关配置,包括编码、抓取间隔、重试次数等
    private Site site = Site.me().setCycleRetryTimes(3).setRetryTimes(3).setSleepTime(1000)
            .setUserAgent("Mozilla/5.0 (Windows NT 6.1; WOW64; rv:53.0) Gecko/20100101 Firefox/53.0");

    public Site getSite() {
        return site;
    }

    
    public void process(Page page) {
        Document html = page.getHtml().getDocument();
        // 结果集
        List<ProxyIp> proxyIpList = new ArrayList<ProxyIp>();
        Elements trElements = html.getElementById("ip_list").getElementsByTag("tr");
        for (Element trEle : trElements) {
            Elements tdElements = trEle.getElementsByTag("td");
            if (tdElements == null||tdElements.size()<=0) {
                continue;
            }
            try {
                ProxyIp proxyIp = new ProxyIp();
                String ip = tdElements.get(1).text();
                String proxyPort = tdElements.get(2).text();
                String ipAddress = tdElements.get(3).text();
                String anonymity = tdElements.get(4).text();
                String proxyType = tdElements.get(5).text();
                String aliveTime = tdElements.get(6).text();
                proxyIp.setProxyIp(ip);
                proxyIp.setProxyPort(Integer.parseInt(proxyPort));
                proxyIp.setAliveTime(aliveTime);
                proxyIp.setAnonymity(anonymity);
                proxyIp.setIpAddress(ipAddress);
                proxyIp.setProxyType(proxyType);
                logger.info(proxyIp.getProxyIp()+":"+proxyIp.getProxyPort());
                proxyIpList.add(proxyIp);
            } catch (Exception e) {
                logger.error("IP代理解析出错!", e);
            }
        }
        page.putField("proxyIpList", proxyIpList);
    }
}
page.putField("proxyIpList", proxyIpList);本质是设值到了ResultItems对象里了。

这样插件式、定制化很值的我们借鉴。希望下一步看源码。

参考:
http://webmagic.io/docs/zh/posts/ch1-overview/architecture.html

webmagic自定义存储(mysql、redis存储)

标签:nts   html   否则   自定义   com   文件   raw   控制台   processor   

人气教程排行