java爬取网页_Java 爬虫 爬取html网页解析

1、springboot项目，引入jsoup

org.jsoup

jsoup

1.10.2

2、准备解析对象

Content.java

package com.asia.pojo;

import lombok.AllArgsConstructor;

import lombok.Data;

import lombok.NoArgsConstructor;

//java项目 www.fhadmin.org

@Data

@NoArgsConstructor

@AllArgsConstructor

public class Content {

private String title;

private String img;

private String price;

}

3、爬虫工具类

HtmlParseUtil.java

package com.asia.utils;

import java.net.URL;

import java.net.URLDecoder;

import java.util.ArrayList;

import java.util.List;

import org.jsoup.Jsoup;

import org.jsoup.nodes.Document;

import org.jsoup.nodes.Element;

import org.jsoup.select.Elements;

import com.asia.pojo.Content;

//java项目 www.fhadmin.org

public class HtmlParseUtil {

public static void main(String[] args) throws Exception {

new HtmlParseUtil().parseJD("西瓜").forEach(System.out::println);

}

public List parseJD(String keywords) throws Exception {

String url = "https://search.jd.com/Search?keyword=" + URLDecoder.decode(keywords, "GBK");

// 解析网页.(Jsoup返回Document就是浏览器的Document对象)

Document document = Jsoup.parse((new URL(url)), 30000);

Element element = document.getElementById("J_goodsList");

Elements elements = element.getElementsByTag("li");

List list = new ArrayList();

for (Element el : elements) {

String src = el.getElementsByTag("img").eq(0).attr("data-lazy-img");

String price = el.getElementsByClass("p-price").eq(0).text();

String name = el.getElementsByClass("p-name").eq(0).text();

list.add(new Content(name, src, price));

}

return list;

}

}