package test.crawling;


import java.io.IOException;


import org.jsoup.Jsoup;

import org.jsoup.nodes.Document;

import org.jsoup.nodes.Element;

import org.jsoup.select.Elements;


public class Ex6Test {


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

// TODO Auto-generated method stub


String urls="http://media.daum.net";

Document daum_news=Jsoup.connect(urls).get();

Elements news_url=daum_news.select("div.box_headline>ul>li>strong>a");

for(Element element:news_url)

{

String url=element.attr("href");

System.out.println(url);

if(url.contains("media.daum.net"))

{

Document doc=Jsoup.connect(url).get();

Elements body=doc.select("div#harmonyContainer");

Elements title=doc.select("h3.tit_view");

String content=body.text();

String newstitle=title.text();

System.out.println("제목:"+newstitle);

System.out.println("내용:"+content);

}


}

}


}


1

     

콘솔창 출력 결과



+ Recent posts