Here you can find the source of getHTML(String pageURL, String encoding)
public static String getHTML(String pageURL, String encoding)
//package com.java2s; //License from project: Apache License import java.io.BufferedReader; import java.io.InputStreamReader; import java.net.HttpURLConnection; import java.net.URL; public class Main { public static String getHTML(String pageURL, String encoding) { StringBuilder pageHTML = new StringBuilder(); try {//from w w w.j a va 2 s . c o m URL url = new URL(pageURL); HttpURLConnection connection = (HttpURLConnection) url.openConnection(); connection.setRequestProperty("User-Agent", "MSIE 7.0"); BufferedReader br = new BufferedReader(new InputStreamReader(connection.getInputStream(), encoding)); String line = null; while ((line = br.readLine()) != null) { pageHTML.append(line); pageHTML.append("\r\n"); } connection.disconnect(); } catch (Exception e) { e.printStackTrace(); } return pageHTML.toString(); } }