Java爬虫工具包(Jsoup)爬取网页代码
一、实现步骤
1、导入依赖pom.xml
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.15.3</version>
</dependency>
2、编写实体类
package com.sgz.springboot.pc;
import lombok.AllArgsConstructor;
import lombok.Data;
import lombok.NoArgsConstructor;
@Data
@NoArgsConstructor
@AllArgsConstructor
public class Content {
private String title;
private String img;
private String price;
}
3、编写主方法
package com.sgz.springboot.pc;
import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import java.net.URL;
import java.util.ArrayList;
import java.util.List;
public class HtmlParseUtil {
public static void main(String[] args) throws Exception {
new HtmlParseUtil().parseJD("Java").forEach(System.out::println);
}
public List<Content> parseJD(String keywords) throws Exception{
String url = "https://search.jd.com/Search?keyword="+keywords;
Document document = Jsoup.parse(new URL(url), 30000);
Element element = document.getElementById("J_goodsList");
Elements elements = element.getElementsByTag("li");
ArrayList<Content> goodsList = new ArrayList<>();
for (Element el : elements) {
String img = el.getElementsByTag("img").eq(0).attr("data-lazy-img");
String price = el.getElementsByClass("p-price").eq(0).text();
String title = el.getElementsByClass("p-name").eq(0).text();
Content content = new Content();
content.setTitle(title);
content.setPrice(price);
content.setImg(img);
goodsList.add(content);
}
return goodsList;
}
}