removes all subdomains of an url

removeSubdomainsOfURL.java

public static String removeSubdomains(String url, ArrayList<String> secondLevelDomains) {
	// We need our URL in three parts, protocol - domain - path
	String protocol= getProtocol(url);		
	url = url.substring(protocol.length());
	String urlDomain=url;
	String path="";
	if(urlDomain.contains("/")) {
		int slashPos = urlDomain.indexOf("/");
		path=urlDomain.substring(slashPos);
		urlDomain=urlDomain.substring(0, slashPos);
	}
	// Done, now let us count the dots . . 
	int dotCount = Strng.countOccurrences(urlDomain, ".");
	// example.com <-- nothing to cut
	if(dotCount==1){
		return protocol+url;
	}
	int dotOffset=2; // subdomain.example.com <-- default case, we want to remove everything before the 2nd last dot
	// however, somebody had the glorious idea, to have second level domains, such as co.uk
	for (String secondLevelDomain : secondLevelDomains) {
		// we need to check if our domain ends with a second level domain
		// example: something.co.uk we don't want to cut away "something", since it isn't a subdomain, but the actual domain
		if(urlDomain.endsWith(secondLevelDomain)) {
			// we increase the dot offset with the amount of dots in the second level domain (co.uk = +1)
			dotOffset += Strng.countOccurrences(secondLevelDomain, ".");
			break;
		}
	}
	// if we have something.co.uk, we have a offset of 3, but only 2 dots, hence nothing to remove
	if(dotOffset>dotCount) {
		return protocol+urlDomain+path;
	}
	// if we have sub.something.co.uk, we have a offset of 3 and 3 dots, so we remove "sub"
	int pos = Strng.nthLastIndexOf(dotOffset, ".", urlDomain)+1;
	urlDomain = urlDomain.substring(pos);	
	return protocol+urlDomain+path;
}

public static String getProtocol(String url) {
	String containsProtocolPattern = "^([a-zA-Z]*:\\/\\/)|^(\\/\\/)";
	Pattern pattern = Pattern.compile(containsProtocolPattern);
	Matcher m = pattern.matcher(url);
	if (m.find()) {	      
		return m.group();
	}
	return "";
}

public static ArrayList<String> getPublicSuffixList(boolean loadFromPublicSufficOrg) {
	ArrayList<String> secondLevelDomains = new ArrayList<String>();
	if(!loadFromPublicSufficOrg) {
		secondLevelDomains.add("co.uk");secondLevelDomains.add("co.at");secondLevelDomains.add("or.at");secondLevelDomains.add("ac.at");secondLevelDomains.add("gv.at");secondLevelDomains.add("ac.at");secondLevelDomains.add("ac.uk");secondLevelDomains.add("gov.uk");secondLevelDomains.add("ltd.uk");secondLevelDomains.add("fed.us");secondLevelDomains.add("isa.us");secondLevelDomains.add("nsn.us");secondLevelDomains.add("dni.us");secondLevelDomains.add("ac.ru");secondLevelDomains.add("com.ru");secondLevelDomains.add("edu.ru");secondLevelDomains.add("gov.ru");secondLevelDomains.add("int.ru");secondLevelDomains.add("mil.ru");secondLevelDomains.add("net.ru");secondLevelDomains.add("org.ru");secondLevelDomains.add("pp.ru");secondLevelDomains.add("com.au");secondLevelDomains.add("net.au");secondLevelDomains.add("org.au");secondLevelDomains.add("edu.au");secondLevelDomains.add("gov.au");
	}
	try {
		String a = URLHelpers.getHTTP("https://publicsuffix.org/list/public_suffix_list.dat", false, true);
		Scanner scanner = new Scanner(a);
		while (scanner.hasNextLine()) {
		String line = scanner.nextLine();
			if(!line.startsWith("//") && !line.startsWith("*") && line.contains(".")) {
				secondLevelDomains.add(line);
			}
		}
		scanner.close();
	} catch (Exception e) {
		e.printStackTrace();
	}
	return secondLevelDomains;
}