Here you can find the source of getHTML(String url, boolean removeNonLatinChars)
public static String getHTML(String url, boolean removeNonLatinChars) throws IOException
//package com.java2s; /*//from ww w. j av a2s.com * Copyright (C) 2014 desrever <desrever at nubits.com> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version 2 * of the License, or (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ import java.io.BufferedReader; import java.io.IOException; import java.io.InputStream; import java.io.InputStreamReader; import java.net.URL; import java.net.URLConnection; public class Main { public static String getHTML(String url, boolean removeNonLatinChars) throws IOException { String line = "", all = ""; URL myUrl = null; BufferedReader br = null; try { myUrl = new URL(url); URLConnection con = myUrl.openConnection(); con.setConnectTimeout(1000 * 8); con.setReadTimeout(1000 * 8); InputStream in = con.getInputStream(); br = new BufferedReader(new InputStreamReader(in)); while ((line = br.readLine()) != null) { all += line; } } finally { if (br != null) { br.close(); } } if (removeNonLatinChars) { all = all.replaceAll("[^\\x00-\\x7F]", ""); } return all; } }