GoComics.com Downloader

import java.util.Scanner;
import java.net.URL;
import java.io.PrintWriter;
import java.io.File;
import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;

/**
 * @author Moshe Kaplan [email protected]
 * @version 2011.03.26
 * @since 1.6
 *
 *        The purpose of this class is to download every comic of a series from
 *        gocomics.com. It accomplishes this by finding the comic and
 *        downloading it, and then searching for a next button. When it finds a
 *        next button, it will then return a string of a URL pointing to the
 *        next comic.
 */
public class Downloader {

    /**
     * A simple main class to test functionality.
     *
     * @param args [0] The first URL to download a comic from (oldest comic of the series, or the first one you're missing)
     */
    public static void main(String[] args)
            throws java.net.MalformedURLException, java.io.IOException {
        if (args.length < 1) {
            System.out.println("You must put in a URL as a source");
            System.exit(1);
        }
        String next = Downloader.getPage(args[0]);
        while (!next.equals(""))
            next = Downloader.getPage(next);
    }

    /**
     * Downloads a page, the image, and returns the URL of the next page
     *
     * Downloads page. Scans the page for the URL of the image. Parses out the
     * date of the comic, and calls gifURLtoFile to download and save the
     * picture. Scans the page for the URL of the Next button, and returns that
     *
     * @param surl A string representation of a URL to download
     * @return The next page.
     *
     */
    public static String getPage(String surl) {
        try {
            URL url = new URL(surl);
            try {
                Scanner scan = new Scanner(url.openStream());
                while (scan.hasNextLine()) {
                    String data = scan.nextLine();
                    // now to find the URL of the image
                    if (data.matches(".*http://imgsrv.gocomics.com.*")) {
                        // extract URL
                        int x = data.indexOf("src=\"");
                        int y = data.indexOf("\"", x + 5);
                        String fileURL = data.substring(x + 5, y);
                        // extract title
                        String title = url.getPath().substring(
                                url.getPath().indexOf("/", 1));
                        System.out.println("Now Downloading: "
                                + title.replace("/", " "));
                        title = title.replace("/", ""); // title is only the
                                                        // numbers of the date
                                                        // now - example:
                                                        // 20070913
                        // Save gif to file
                        gifURLtoFile(new URL(fileURL), title);
                    }
                    // find URL for next page
                    if (data.matches(".*>Next >></a></span></div>.*")) {
                        // find last href=" , from there, till next "
                        int x = data.lastIndexOf("href=");
                        int y = data.indexOf("\"", x + 6);
                        String nextURL = data.substring(x + 6, y); // partial
                                                                    // URL
                        nextURL = url.getProtocol() + "://" + url.getHost()
                                + nextURL;
                        // optimization - save on Bandwidth - no need to DL the
                        // rest of the page.
                        return nextURL;
                    }
                }

            } catch (java.io.IOException e) {
                System.out.println("Unable to connect to: " + surl);
            }

        } catch (java.net.MalformedURLException e) {
            System.out.println("Invalid URL");
            System.out.println(surl);
        }
        return "";
    }

    /**
     * Saves a gif from a URL to a file
     *
     * @param url The URL of the gif picture
     * @param filename The name to save the gif as.
     */
    public static void gifURLtoFile(URL url, String filename) {
        try {
            ImageIO.write(ImageIO.read(url), "gif", new File(filename + ".gif"));
        } catch (Exception e) {
            System.out.println("Error Saving file at: " + url + " as "
                    + filename);
        }
    }
}