爬取 GIF 图片

导入pom

    us.codecraft
    webmagic-extension
    0.7.3

demo

package com.demon.reptile;

import org.apache.commons.lang3.StringUtils;
import us.codecraft.webmagic.Page;
import us.codecraft.webmagic.Site;
import us.codecraft.webmagic.Spider;
import us.codecraft.webmagic.processor.PageProcessor;

import java.util.Iterator;
import java.util.List;

/**
 * @author Demon-HY
 * @date 2019-6-17
 */
public class LaiFuGIFProcessor implements PageProcessor {

    // 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().setRetryTimes(3).setSleepTime(1000);

    private static final String HOST = "http://www.laifujiangxiaohua.com";

    @Override
    public void process(Page page) {
        // 读取属性用 /@src,读取text内容,用 /text()
        List gitPaths = page.getHtml().xpath("//section[@class='gif-image']//a//img/@data-gif").all();
        Iterator iterator = gitPaths.iterator();
        while (iterator.hasNext()) {
            String gitPath = iterator.next();
            if (StringUtils.isBlank(gitPath) || !gitPath.startsWith("http://down")) {
                iterator.remove();
            }
        }

        // 获取其他列表的信息   下一页的信息
        String nextLink =  HOST + page.getHtml().xpath("//li[@class='next']//a/@href").get();
        page.addTargetRequest(nextLink);   //
        page.setSkip(true);
    }

    @Override
    public Site getSite() {
        return site;
    }

    public static void main(String[] args) {
        // 从第一页开始抓，开启1个线程，启动爬虫
        Spider.create(new LaiFuGIFProcessor())
                .addUrl(HOST + "/tupian/gaoxiaogif_1.htm")
                .thread(1)
                .run();
    }
}