Information access system and method for archiving web pages

jPreferencej jCoche Archive! fBrowsing Cochel jBrowsing Archivej jScheduling}

• Press | ToGo 1 to put wolked pages ... | category. • Chonge Cache Policy

URL pattern: [http://interoctive.wsj.com/pages/techroan

Cache Flag: 1 On |V

• Press [ OK | to add a each flag entry. Chonge Cache ValidTime

FIG. 7A

public class inputFiiterSomple extends javabin \

public Object Execute(OutputStream os.Hashtable ht)throws lOException \ String url = (String)ht.get("url"); String fname = (String)ht.get("path"); byte orig_date[3 = readCacheFile(fname); byte result_data[] = dolnputFilter{orig_dato); writeCacheFile(fname, resuit_data);

FIG. 7B

public class outputFilterSample extends javabin {

public Object Execute(OutputStream os.Hashtable ht)throws lOException \ String url = (String)ht.get("url"); String tname = (String)ht.get("path"); byte cached_date[] = readCacheFile(fname); byte result_data[] = doOutputFilter(orig_data); os.write(result_data);

I

I

FIG. 7C

public class headerFilterSample extends javabin [

public Object Execute{OutputStream os.Hashtable ht)fhrows lOException [ String orig_header = (String)ht.ge1("ht.header"); String result_header = doHeaderFilter(orig_header); os.write(resuH_header.getBytes());

!

}