eda095 lab 1

lab1.java

import java.io.*;
import java.lang.reflect.Array;
import java.net.MalformedURLException;
import java.net.URL;
import java.net.URLConnection;
import java.util.ArrayList;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 * Created by zol on 3/12/2015.
 */
public class Main {
    public static void main(String[] args) {

        if (args.length == 0) {
            System.out.println("Usage: PdfFetcher <url>");
        }
        try {
            URL url = new URL(args[0]);
            String contents = downloadHtml(url);
            ArrayList<String> parsedLinks = parseHtml(contents);
            ArrayList<URL> urls = stringsToUrls(url, parsedLinks);
            //downloadPdfs(urls);

        } catch (MalformedURLException e) {
            e.printStackTrace();
        }
        /*
        Matcher matcher = pattern.matcher("http://www.zolomon.com/game.pdf");
        System.out.println(matcher.matches());*/

    }

    private static ArrayList<URL> stringsToUrls(URL url, ArrayList<String> parsedLinks) {
        parsedLinks.parallelStream()
                .map((String l) -> {
                    try {
                        return new URL(l);
                    } catch (MalformedURLException e) {
                        e.printStackTrace();
                    }
                    return null;
                });

        return null;
    }

    private static ArrayList<String> parseHtml(String contents) {
        //Pattern pattern = Pattern.compile("(^(https?|ftp|file)://[-a-zA-Z0-9+&@#/%?=~_|!:,.;]*[-a-zA-Z0-9+&@#/%=~_|])");
        Pattern pattern = Pattern.compile("\"((https?://)?.*\\.pdf)\"");
        Matcher matcher = pattern.matcher(contents);
        ArrayList<String> urls = new ArrayList<>();
        while (matcher.find()) {
            urls.add(matcher.group().replace("\"", ""));
        }
        return urls;
    }

    private static String downloadHtml(URL url) {
        String encoding = "ISO-8859-1";
        URLConnection uc = null;
        try {
            uc = url.openConnection();

            String contentType = uc.getContentType();
            int encodingStart = contentType.indexOf("charset=");
            if (encodingStart != -1) {
                encoding = contentType.substring(encodingStart + 8);
            }
            InputStream in = new BufferedInputStream(uc.getInputStream());
            StringBuilder stringBuilder = new StringBuilder();
            try (Reader r = new InputStreamReader(in, encoding)) {

                int c;
                while ((c = r.read()) != -1) {
                    stringBuilder.append((char) c);
                }
            }
            in.close();
            return stringBuilder.toString();
        } catch (MalformedURLException ex) {
            System.err.println(url.toString() + " is not a parseable URL");
        } catch (UnsupportedEncodingException ex) {
            System.err.println("Server sent an encoding Java does not support: " + ex.getMessage());
        } catch (IOException e) {
            e.printStackTrace();
        }
        return null;
    }

    private static void downloadPdfs(URL[] urls) throws IOException {
        for (URL url : urls) downloadPdf(url);
    }

    private static String downloadPdf(URL url) throws IOException {
        URLConnection con = url.openConnection();
        String contentType = con.getContentType();
        int contentLength = con.getContentLength();
        if (contentType.startsWith("text/") || contentLength == -1) {
            throw new IOException("This is not a binary file");
        }

        try (InputStream raw = con.getInputStream()) {
            InputStream in = new BufferedInputStream(raw);
            byte[] data = new byte[contentLength];
            int offset = 0;
            while (offset < contentLength) {
                int bytesRead = in.read(data, offset, data.length - offset);
                if (bytesRead == -1) break;
                offset += bytesRead;
                System.out.println("Read: " + bytesRead);
            }

            if (offset != contentLength) {
                throw new IOException("Only read " + offset + " bytes; Expected " + contentLength + " bytes in total");
            }
            String filename = url.getFile();
            filename = filename.substring(filename.lastIndexOf("/") + 1);
            try (FileOutputStream fout = new FileOutputStream(filename)) {
                fout.write(data);
                fout.flush();
                System.out.println("File saved: " + filename);
            }
        }
        return null;
    }
}