CS535 Object-Oriented Programming & Design
Fall Semester, 1996
HttpDownloader.java

import java.net.URL;
import java.net.URLConnection;
import java.net.MalformedURLException;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.io.File;
import java.io.BufferedOutputStream;
import java.io.FileOutputStream;


/** This class downloads html pages via http protocol. It downloads html text only. 
 *  No rendering of html is done. It assumes your machine is connected to
 *  the internet either directly or via slip or ppp. 
 *  The html pages can be saved to a file, displayed to
 *  the screen or placed in string.  Don't know how large a file can fit into a string.
 *
 * @version 1.0, 3 October 1996 
 * @author Roger Whitney (<a href=mailto:whitney@cs.sdsu.edu>whitney@cs.sdsu.edu</a>)
 */

class HttpDownloader
   {
   /**
    * Absolute http address of page to download. Here is an example of an absolute address:
    * http://www.eli.sdsu.edu/courses/index.html
    */
   private String httpTextUrl;
   
   public HttpDownloader( String absoluteURL )
      {
      httpTextUrl = absoluteURL;
      }

   /**
    * Examples of using this class
    */
   public static void main( String args[] )
      {
      System.out.println( "Starting to Access pages" );
      
      String coursesAddress = "http://www.eli.sdsu.edu/courses/index.html";
      HttpDownloader courses = new HttpDownloader( coursesAddress );
      courses.toScreen();

      System.out.println( "Now for second page" );
      
      String notesIndexAddress = "http://www.eli.sdsu.edu/courses/fall96/cs535/notes/index.html";
      HttpDownloader notesIndex = new HttpDownloader( notesIndexAddress );
      notesIndex.toFile( "index.html" );

      System.out.println( "Now for third page" );

      String finalStaticAddress = "http://www.eli.sdsu.edu/courses/fall96/cs535/notes/finalNotStatic/finalNotStatic.html";
      HttpDownloader finalStaticPage = new HttpDownloader( finalStaticAddress );
      System.out.println( finalStaticPage.toString( ) );
      }
   
   /**
    * Retrieves a web page and places the html in a string
    * @return a string containing the html of the web page
    */   
   public String toString()
      {
      try
         {
         int inputChar;
         int EOF = -1;
         int smallPageSize = 5000;
         
         StringBuffer pageAsString = new StringBuffer( smallPageSize );
         InputStream  httpStream =  getHttpStream();

          
         while ( (inputChar = httpStream.read()) != EOF )
            pageAsString.append( ( char ) inputChar );
            
            // cast to char so string interprets as char rather than underlying
            // unicode int representation
      
         return pageAsString.toString();
         }
      catch( IOException ioError )
         {
         System.err.println( "IO err in printing web page to screen" );
         return "IO Error in reading web page";
         }
      }

   /**
    * Retrieves a web page and displays the html on standard out
    */   
   public void toScreen()
      {
      try
         {
         readInputToOutput( getHttpStream(), System.out );
         }
      catch( IOException ioError )
         {
         System.err.println( "IO err in printing web page to screen" );
         }
      }
   /**
    * Retrieves a web page and places the html in a file. Erases previous contents of file. 
    * @param fileName   name of file used to store html of the web page
    */   
   public void toFile( String fileName )
      {
      try
         {
         File fileForHtml = new File( fileName );
         BufferedOutputStream bufferedFile;
         bufferedFile = new BufferedOutputStream( new FileOutputStream( fileForHtml ) );

         readInputToOutput( getHttpStream(), bufferedFile );
         bufferedFile.close();
         }
      catch( IOException ioError )
         {
         System.err.println( "IO err in saving web page to file: " + fileName );
         }
      }
      
   /**
    * Opens a inputstream to the web server containing
    * the web page indicated by httpTextUrl
    * @return the inputstream to the web server
    */   
   private InputStream getHttpStream()
      {
      try
         {
         URL http_URL = new URL( httpTextUrl );
         URLConnection httpconnection = http_URL.openConnection();
         return httpconnection.getInputStream();
         }
      catch( MalformedURLException ioError )
         { 
         System.out.println( "Malformed URL " + httpTextUrl);
         ioError.printStackTrace();
         System.out.println( "Exiting program");

         // Exit program, since the course has not covered exceptions
         // so students don't know how to catch exceptions yet
         System.exit( 1 );
         }
      catch ( IOException ioError )
         { 
         System.out.println( "IO Error on opening http connection" );
         ioError.printStackTrace();
         System.out.println( "Exiting program");
         System.exit( 1 );
         }
      
      // Program does not reach here, compiler insists on a return
      return null;
      }
      
   /**
    * Transfers contents of inputStream in to outputstream out
    */   
   private void readInputToOutput( InputStream in, OutputStream out ) throws IOException
      {
      int inputChar;
      int EOF = -1;
      while ( (inputChar = in.read()) != EOF )
         out.write( inputChar );
      }

   } // end class HttpDownloader