Skip to content

Instantly share code, notes, and snippets.

@kryvoboker
Created August 19, 2020 19:42
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save kryvoboker/90efdab1a031a0183cbfeae09cd27ed7 to your computer and use it in GitHub Desktop.
Save kryvoboker/90efdab1a031a0183cbfeae09cd27ed7 to your computer and use it in GitHub Desktop.
HomeWork9(Работа с сетью)(3)
import java.io.BufferedReader;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
public class Main {
public static void main(String[] args) {
String urlAdress = "https://prog.kiev.ua/forum/index.php/board,2.0.html";
String text = getStringFromUrl(urlAdress);
StringBuilder sb = new StringBuilder();
String[] a = text.split(" ");
for (int i = 0; i < a.length; i += 1) {
if (a[i].contains("https://")) {
sb.append(a[i]).append(System.lineSeparator());
}
}
String st = sb.toString();
String source, delete;
source = st;
delete = "href=";
source = source.replace(delete, "");
delete = "Vestars";
source = source.replace(delete, "");
delete = "Vsevolod";
source = source.replace(delete, "");
delete = "войдите";
source = source.replace(delete, "");
delete = "YuraKhomenko";
source = source.replace(delete, "");
delete = "Java_start_Alexander_09_06_2020(Жилянская";
source = source.replace(delete, "");
delete = "Java_Start_Online_Max_Maleev";
source = source.replace(delete, "");
delete = "Java_Start_Online_Mariia(homeworks)";
source = source.replace(delete, "");
delete = ">1</a>";
source = source.replace(delete, "");
delete = ">2</a>";
source = source.replace(delete, "");
delete = ">3</a>";
source = source.replace(delete, "");
delete = "Java_OOP_Alexander_Beresteyka_21_09_2019";
source = source.replace(delete, "");
delete = "</script>";
source = source.replace(delete, "");
delete = "</span>";
source = source.replace(delete, "");
delete = "<script";
source = source.replace(delete, "");
delete = " var";
source = source.replace(delete, "");
delete = "</a>";
source = source.replace(delete, "");
delete = "<p>";
source = source.replace(delete, "");
delete = ".<br";
source = source.replace(delete, "");
delete = "письмо";
source = source.replace(delete, "");
delete = "зарегистрируйтесь";
source = source.replace(delete, "");
delete = "<img";
source = source.replace(delete, "");
delete = "IT";
source = source.replace(delete, "");
delete = "<span>&#1050;&#1091;&#1088;&#1089;&#1099;";
source = source.replace(delete, "");
delete = "<span>";
source = source.replace(delete, "");
delete = "Программирование";
source = source.replace(delete, "");
delete = "Java";
source = source.replace(delete, "");
delete = "Тема";
source = source.replace(delete, "");
delete = "Автор";
source = source.replace(delete, "");
delete = " <th";
source = source.replace(delete, "");
delete = "Ответов";
source = source.replace(delete, "");
delete = "Просмотров";
source = source.replace(delete, "");
delete = "</th>";
source = source.replace(delete, "");
delete = "Последний";
source = source.replace(delete, "");
delete = "Все";
source = source.replace(delete, "");
delete = "<img";
source = source.replace(delete, "");
delete = " </td>";
source = source.replace(delete, "");
delete = " </tr>";
source = source.replace(delete, "");
delete = " <tr>";
source = source.replace(delete, "");
delete = " <td";
source = source.replace(delete, "");
delete = " <span";
source = source.replace(delete, "");
delete = "ПРАВИЛА";
source = source.replace(delete, "");
delete = "'";
source = source.replace(delete, "");
delete = ",";
source = source.replace(delete, "");
delete = "kamaz_cs";
source = source.replace(delete, "");
delete = "Alexander";
source = source.replace(delete, "");
delete = "Домашнее";
source = source.replace(delete, "");
delete = "src=";
source = source.replace(delete, "");
delete = "Matvieiev";
source = source.replace(delete, "");
delete = "СПД";
source = source.replace(delete, "");
delete = ";";
delete = "\"";
source = source.replace(delete, "");
delete = ">";
source = source.replace(delete, "");
// System.out.println(source);
// System.out.println(text);
try (FileWriter writer = new FileWriter("text.txt")) {
writer.write(source);
writer.flush();
} catch (IOException e) {
e.printStackTrace();
}
}
public static String getStringFromUrl(String urlAdress) { //получения HTML разметки страницы
StringBuilder sb = new StringBuilder();
try {
URL url = new URL(urlAdress);
HttpURLConnection con = (HttpURLConnection) url.openConnection();
BufferedReader br = new BufferedReader(new InputStreamReader(con.getInputStream())); //InputStreamReader() -> может принимать второй параметр - это кодировка текста, если сервер передает информацию по другой кодировке и текст не читабельный
String text = null;
for (; (text = br.readLine()) != null;) {
sb.append(text).append(System.lineSeparator());
}
} catch (IOException e) {
e.printStackTrace();
}
return sb.toString();
}
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment