package crawler; import java.io.BufferedReader; import java.io.IOException; import java.io.InputStreamReader; import java.net.HttpURLConnection; import java.net.MalformedURLException; import java.net.URL; public class HtmlFetcher { public static String fetchHtmlContent(String urlString) { StringBuilder htmlContent = new StringBuilder(); HttpURLConnection connection = null; try { URL url = new URL(urlString); connection = (HttpURLConnection) url.openConnection(); connection.setRequestMethod("GET"); connection.setRequestProperty("User-Agent", "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3"); int code = connection.getResponseCode(); if (code == 200) { BufferedReader reader = new BufferedReader(new InputStreamReader(connection.getInputStream(), "utf-8")); String line = null; while ((line = reader.readLine()) != null) htmlContent.append(line); reader.close(); } } catch (MalformedURLException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } finally { if (connection != null) connection.disconnect(); } return htmlContent.toString(); } }