public void TestDomainExtraction1()
{
var input = "http://www.foo.com";
var domain = UrlHelpers.ExtractDomainFromUrl(input);
Assert.AreEqual("www.foo.com", domain);
}
public void TestDomainExtraction3()
{
var input = "https://foo.com:2020";
var domain = UrlHelpers.ExtractDomainFromUrl(input);
Assert.AreEqual("foo.com", domain);
}
private static int checkKnownDomains(ViewModel viewModel, string text)
{
var result = 0;
// Yes, a regex for a URL is a beast to behold.
var regex = @"(ht|f)tp(s?)\:\/\/[0-9a-zA-Z]([-.\w]*[0-9a-zA-Z])*(:(0-9)*)*(\/?)([a-zA-Z0-9\-\.\?\,\'\/\\\+&%\$#_]*)?";
var matches = Regex.Matches(text, regex);
foreach (Match match in matches)
{
var url = match.Value.ToLower();
var domain = UrlHelpers.ExtractDomainFromUrl(url);
if (viewModel.KnownDomainScores.TryGetValue(domain, out var score))
{
result += score;
}
else
{
try {
result += processUrl(viewModel, url);
}
catch {
}
}
}
return(result);
}