java爬虫
使用java 爬取 JD 上的图片
package com.codervibe.domain;
import lombok.AllArgsConstructor;
import lombok.Data;
import lombok.NoArgsConstructor;
import lombok.ToString;
@Data
@NoArgsConstructor
@AllArgsConstructor
@ToString
public class Content {
private String img;
private String price;
private String title;
}
package com.codervibe.untils;
import com.codervibe.domain.Content;
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 HtmlParseUntil {
public List<Content> parseJD(String keywords) throws Exception {
String url = "https://search.jd.com/Search?keyword=" + keywords;
Document document = Jsoup.parse(new URL(url), 60000);
Element element = document.getElementById("J_goodsList");
System.out.println(element.html());
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.setImg(img);
content.setPrice(price);
goodsList.add(content);
}
return goodsList;
}
}
- 测试代码使用的是junit测试
- 新建一个测试类 com.codervibe.pareTest
package com.codervibe;
import com.codervibe.untils.HtmlParseUntil;
import org.junit.Test;
public class pareTest {
@Test
public void test() throws Exception {
new HtmlParseUntil().parseJD("java").forEach(System.out::println);
}
}