java 크롤링

크롤링 대상

전략

 1] ul.section_list_ranking > li > a 의 구조 

 2] a tag에 title 속성에서 값을 get 하자 

import java.io.IOException;

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

class Cwl {
	
	String target_url;
	
	Cwl() {
		this.target_url = "https://news.naver.com/main/main.nhn?mode=LSD&mid=shm&sid1=101";
	}
	
	public void requestUrl() throws IOException {
		Document doc = Jsoup.connect(this.target_url).get();
		Element element = doc.selectFirst("ul.section_list_ranking");
		Elements elements =  element.select("li > a");
		
		for (Element e : elements) {
			System.out.println(e.attr("title"));
		}
	}
}
public class stu01 extends Cwl{
	
	public static void main(String[] args) throws IOException {
		Cwl cwl_object = new Cwl();
		cwl_object.requestUrl();
	} // end of main function
}

 

결과