import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.Writer;
import java.net.MalformedURLException;
import java.net.URL;
import java.net.URLConnection;
import java.util.ArrayList;
import java.util.Hashtable;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

public class Main {
    
    static Pattern emailAddress_Pattern = Pattern.compile("[_A-Za-z0-9-\\+]+(\\.[_A-Za-z0-9-]+)*@[A-Za-z0-9-]+(\\.[A-Za-z0-9]+)*(\\.[A-Za-z]{2,})"); //mykong //Westjet: [_a-zA-Z0-9-]+(.[_a-zA-Z0-9-]+)*@[a-zA-Z0-9-]+(.[a-zA-Z0-9-]+)*.(([0-9]{1,3})|([a-zA-Z]{2,6}))
    static Pattern domainName_Pattern = Pattern.compile("(https?|ftp|file)://[-a-zA-Z0-9+&@#/%?=~_|!:,.;]*[-a-zA-Z0-9+&@#/%=~_|]"); //((?!-)[A-Za-z0-9-]{1,63}(?<!-)\\.)+[A-Za-z]{2,6}"); //http://www.mkyong.com/regular-expressions/domain-name-regular-expression-example/
    static Pattern relativeURL_Pattern = Pattern.compile("");
    
    /*Args[0]: name of file to stick emails into
     * args[1]: root url of sites to crawl
     * args[2]: number of email addresses to find
     */
    public static void main(String[] args){
        Writer output = null;
        try{
            output = new BufferedWriter(new FileWriter(args[0], true));
        }catch(Exception e){
            e.printStackTrace();
        }
        
        String rootWebsiteHTML = getHTMLFromURL(args[1]);
        Matcher email_matcher = emailAddress_Pattern.matcher(rootWebsiteHTML);
        Matcher domain_matcher = domainName_Pattern.matcher(rootWebsiteHTML);
        Matcher relativeURL_matcher = relativeURL_Pattern.matcher(rootWebsiteHTML);
       
        Hashtable<String, Boolean> visitedHashTable = new Hashtable<String, Boolean>();
        visitedHashTable.put(args[1], true);
        Hashtable<String, Boolean> foundEmails = new Hashtable<String, Boolean>();
        
        //getEmails
        List<String> emails = new ArrayList<String>();
        findResource(email_matcher, emails, foundEmails);
        
        //getDomains
        List<String> domains = new ArrayList<String>();
            //getRelativeLinks
           /* List<String> relativeLinks = new ArrayList<String>();
            findResource(relativeURL_matcher, relativeLinks);
            
            //turn into complete links and add to domains list
            for(int i = 0; i < relativeLinks.size(); i++){
                domains.add(args[1]+relativeLinks.get(i));
            }*/
        findResource(domain_matcher, domains, visitedHashTable);
        
        for(int i = 0; (i < Integer.parseInt(args[2])) && (i < domains.size()); i++){
            
            String html = getHTMLFromURL(domains.get(i));
            email_matcher = emailAddress_Pattern.matcher(html);
            
            //getEmails
            findResource(email_matcher, emails, foundEmails);
            
            //getMoreDomains if not stopping after root
            //domain_matcher = domainName_Pattern.matcher(html);
            //findResource(domain_matcher, domains, visitedHashTable);
        }
        
        //save emails to file
        if(output != null){
            for(String email: emails){
                try {
                    output.write(email);
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
    }
    
    public static void findResource(Matcher patternMatcher, List<String> listToAddTo, Hashtable<String, Boolean> doNotAddList){
        
        Matcher matcher = patternMatcher;
        List<String> resourcesFound = listToAddTo;
        
        while (matcher.find()) {
        	if(doNotAddList.get(matcher.group()) == null){
        		resourcesFound.add(matcher.group());
        		//ensure we don't add it again if we've already found it
        		doNotAddList.put(matcher.group(), true);
        		System.out.println("Found: " + matcher.group());
        	}
        }
    }

    public static String getHTMLFromURL(String Url){
        
        URL url;
        String html = "";
         
        try {
            // get URL content

            url = new URL(Url);
            URLConnection conn = url.openConnection();

            // open the stream and put it into BufferedReader
            BufferedReader br = new BufferedReader(new InputStreamReader(conn.getInputStream()));
           
            String inputLine;
            while ((inputLine = br.readLine()) != null) {
                html += inputLine;
            }
            br.close();

        } catch (MalformedURLException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
	        
        return html;
    }
}