Find and display hyperlinks contained within a web page : HTML Parser « Network Protocol « Java

1. Java
2. Network Protocol
3. HTML Parser

Find and display hyperlinks contained within a web page

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{
    String page = loadPage(arguments[0]);
    Pattern pattern = Pattern.compile("<a.+href=\"(.+?)\"");
    Matcher matcher = pattern.matcher(page);
    while (matcher.find()) {
      System.out.println(matcher.group(1));
    }
  }

  static String loadPage(String name) throws Exception {
    StringBuffer output = new StringBuffer();
    FileReader file = new FileReader(name);
    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();
    return output.toString();
  }
}

 

Related examples in the same category