Java - 크롤링, crawling

import java.io.BufferedReader;

import java.io.InputStreamReader;

import java.net.MalformedURLException;

import java.net.URL;

import javax.net.ssl.HttpsURLConnection;

public class CrawApp {

public static void crawling() {

String url = "https://웹페이지주소";

try {

URL obj = new URL(url);

HttpsURLConnection con = (HttpsURLConnection) obj.openConnection();

//연결이 완료되었음.

//1byte받음

BufferedReader in = new BufferedReader(new InputStreamReader(con.getInputStream(), "EUC-KR")) ;

String input;

StringBuilder sb = new StringBuilder();

while ((input = in.readLine()) != null) {

sb.append(input);

}

in.close();

System.out.println(sb.toString());

} catch (Exception e) {

e.printStackTrace();

}

}

public static void main(String[] args) {

crawling();

}

}

크롤링 - 크롬에서 아래 명령어로 파싱 가능

document.querySelector('#articleTitle');

<h3 id=?"articleTitle" class=?"tts_head">?굴착기 이용 GP철거 오늘 시작…김용우 육군총장 현장방문?</h3>?

var article = document.querySelector('#articleTitle');

article.textContent

"굴착기 이용 GP철거 오늘 시작…김용우 육군총장 현장방문"

var txt = document.querySelectorAll('.lo_txt');

txt[0].textContent

"273"