import javax.imageio.*;
import java.awt.image.*;
import java.awt.*;
import java.security.NoSuchAlgorithmException;
import java.security.MessageDigest;
import java.lang.reflect.*;
import java.net.*;
import java.io.*;
import javax.swing.*;
import java.util.regex.*;
import java.util.List;
import java.util.zip.*;
import java.util.*;

public class main {
  public static void main(String[] args) throws Exception {
    String s = load("tinybrain.blog.de");
    List<String> tok = htmlcoarsetok(s);
    for (String _s : tok)
      print(_s);
  }
  
  static String load(String bla) { try {
 
    return loadPage(bla);
  
} catch (Throwable __e) { throw __e instanceof RuntimeException ? (RuntimeException) __e : new RuntimeException(__e); }}

static List<String> htmlcoarsetok(String s) {
  List<String> tok = new ArrayList<String>();
  int l = s.length();
  
  int i = 0;
  while (i < l) {
    int j = i;
    char c;
    
    // scan for non-tags
    while (j < l) {
      if (s.charAt(j) != '<')
        // regular character
        ++j;
      else if (s.substring(j, Math.min(j+4, l)).equals("<!--")) {
        // HTML comment
        j = j+4;
        do ++j; while (j < l && !s.substring(j, Math.min(j+3, l)).equals("-->"));
        j = Math.min(j+3, l);
      } else
        // it's a tag
        break;
    }
    tok.add(s.substring(i, j));
    i = j;
    if (i >= l) break;
    c = s.charAt(i);

    // scan for tags
    if (c == '<') {
      ++j;
      
      while (j < l && s.charAt(j) != '>') ++j; // TODO: strings?
      if (j < l) ++j;
    }

    tok.add(s.substring(i, j));
    i = j;
  }
  
  return tok;
}

static void print() {
  System.out.println();
}

static void print(Object o) {
  System.out.println(o);
}

static void print(long i) {
  System.out.println(i);
}

  public static String loadPage(String url) throws IOException {
    if (url.indexOf("://") < 0)
      url = "http://" + url;
    return loadPage(new URL(url));
  }
  
  public static String loadPage(URL url) throws IOException {
    System.out.println("Loading: " + url.toExternalForm());
    URLConnection con = url.openConnection();
    return loadPage(con, url);
  }

  public static String loadPage(URLConnection con, URL url) throws IOException {
    String contentType = con.getContentType();
    if (contentType == null)
      throw new IOException("Page could not be read: " + url);
    //Log.info("Content-Type: " + contentType);
    String charset = loadPage_guessCharset(contentType);
    Reader r = new InputStreamReader(con.getInputStream(), charset);
    StringBuilder buf = new StringBuilder();
    while (true) {
      int ch = r.read();
      if (ch < 0)
        break;
      //Log.info("Chars read: " + buf.length());
      buf.append((char) ch);
    }
    return buf.toString();
  }
  
  static String loadPage_guessCharset(String contentType) {
    Pattern p = Pattern.compile("text/html;\\s+charset=([^\\s]+)\\s*");
    Matcher m = p.matcher(contentType);
    /* If Content-Type doesn't match this pre-conception, choose default and hope for the best. */
    return m.matches() ? m.group(1) : "ISO-8859-1";
  }

}