Many programmers' sanity depends on reading DilBert every day.
However, we are programmers. We should not need to put up with all the
popup ads and such around the payload.

This HttpUnit snippet reads the HTML page - without reading all its
extras. Then it locates the actual Dilbert cartoon, downloads it to
your c:/temp folder, and presents it in Internet Explorer.

The presentation system is easy to reconfigure for other browsers.

Note the // reveal(page) statement. If you de-comment it, you will see
the Dilbert page, without all its GIFs.

When using HttpUnit to build a Web site, you can easily configure
reveal() to serve a page with the GIFs available. This permits your
tests to temporarily show the page under test, giving you more rapid
feedback than bouncing a server would.

But in production, you would want to comment out calls to reveal() or
explore() before integrating!

--PhlIp

    import java.io.DataOutputStream;
    import java.io.File;
    import java.io.FileNotFoundException;
    import java.io.FileOutputStream;
    import java.io.FileWriter;
    import java.io.IOException;
    import java.net.MalformedURLException;
    import junit.framework.TestCase;
    import org.xml.sax.SAXException;
    import com.meterware.httpunit.*;

    public class filchDilbert 
      extends TestCase
    {
        protected void setUp() {
            HttpUnitOptions.setScriptingEnabled(false);
    //      HttpUnitOptions.setMatchesIgnoreCase(true);
        //  HttpUnitOptions.setImagesTreatedAsAltText(true);
    //      HttpUnitOptions.setParserWarningsEnabled(true);     
        }
    
        private void assertMatch(String regex, String input) throws Exception 
        {       
            boolean shouldMatch = input.matches(regex);
            assertTrue("<" + regex + "> did not match <" + input + ">", shouldMatch);
        }

        public void reveal(WebResponse page) 
            throws FileNotFoundException, 
                   IOException 
        {
        
            String location = "c:/temp/test.html";
            FileWriter out = new FileWriter(location);
            String htmlContents = page.getText();
            out.write(htmlContents);
            out.close();
            explore(location);
            System.out.println(htmlContents);
        }
    
        private void explore(String location) throws IOException 
        {
            Runtime.getRuntime().exec("\"C:\\Program Files\\Internet Explorer\\iexplore.exe\" "+ location);
        }
        private void saveBinary(File fileOut, String dilbertsGif) throws FileNotFoundException, IOException 
        {
            FileOutputStream fos = new FileOutputStream(fileOut);
            DataOutputStream stream = new DataOutputStream(fos);        
            stream.writeBytes(dilbertsGif);
            stream.close();
            fos.close();
        }

        public void test_hitFrontPage() throws MalformedURLException, IOException, SAXException, Exception
        {
            WebConversation     conversation = new WebConversation();
            String server = "http://www.dilbert.com/";
    
            WebRequest  request  = new GetMethodWebRequest( server );
            WebResponse page = conversation.getResponse( request ); 
            assertMatch("Dilbert.*", page.getTitle());
        
    //      reveal(page);
        
    // find: <IMG SRC="/comics/dilbert/archive/images/dilbert2091507040420.gif" BORDER=0 ALT="Today's Dilbert Comic">
        
            WebImage todaysDilbert = page.getImageWithAltText("Today's Dilbert Comic");
            System.out.println(todaysDilbert.getSource());
            request = todaysDilbert.getRequest();
            WebResponse response = conversation.getResponse(request);
            File fileOut = new File("C:/temp/dilbert.gif" );        
            saveBinary(fileOut, response.getText());
            explore(fileOut.getAbsolutePath());
        }


    }

CategoryTesting, Category''''''WebScraping