Java tutorial
import java.io.BufferedReader; import java.io.FileReader; import java.util.regex.Matcher; import java.util.regex.Pattern; public class Main { public static void main(String[] arguments) throws Exception { StringBuffer output = new StringBuffer(); FileReader file = new FileReader("a.htm"); BufferedReader buff = new BufferedReader(file); boolean eof = false; while (!eof) { String line = buff.readLine(); if (line == null) eof = true; else output.append(line + "\n"); } buff.close(); String page = output.toString(); Pattern pattern = Pattern.compile("<a.+href=\"(.+?)\""); Matcher matcher = pattern.matcher(page); while (matcher.find()) { System.out.println(matcher.group(1)); } } }