java（Jsoup）抓取第三方网站图片

抓取网页img标签

package com.betawoo.portal.util;

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;

/**
 * Created by hgg on 2017/9/2.
 */
public class spiderUtils {
    public static void getHtmlWithUrl(String url) {
        try {
            Document doc = Jsoup.connect(url).userAgent("Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36").get();
//            System.out.println(doc);
            spiderUtils.getImagesWithHtml(doc);
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

    public static void getImagesWithHtml(Document doc) {
        Elements images = doc.getElementsByTag("img");
        for (Element image : images) {

            //页面所有img
            System.out.println(image.attr("src"));
        }
    }

    public static void main(String[] args) {
        //抓取网址
        spiderUtils.getHtmlWithUrl("https://zhidao.baidu.com/question/453277368.html");
    }
}

引入jar

<!--jsoup-->
        <dependency>
            <groupId>org.jsoup</groupId>
            <artifactId>jsoup</artifactId>
            <version>1.10.2</version>
        </dependency>