private string extractDomain(string htmlSection) { Regex pageRX = new Regex("(?<=<cite>)(.*?)(?=<)"); EndPointClient endPointClient = new EndPointClient(); return(endPointClient.extractBaseDomain(pageRX.Match(htmlSection).Value)); }
private string extractDomain(string htmlSection) { Regex pageRX = new Regex("(?<=<div class=\"BNeawe UPmit AP7Wnd\">)(.*?)(?=<)"); EndPointClient endPointClient = new EndPointClient(); return(endPointClient.extractBaseDomain(pageRX.Match(htmlSection).Value)); }
public void extractedBaseDomainTest() { string[] urlitems = { "https://www.test.com.au/pages.aspx", "https://www.test.com.au/pages", "https://www.test.com/pages", "https://www.test.com", "www.test.com.au/pages", "www.test.com.au", "www.test.com/pages", "www.test.com", "test.com.au", "test.com.au/pages", "test.com/pages", "test.com", }; string[] expected = { "test.com.au", "test.com.au", "test.com", "test.com", "test.com.au", "test.com.au", "test.com", "test.com", "test.com.au", "test.com.au", "test.com", "test.com", }; List <string> expectedURL = new List <string>(expected); List <string> extractedTest = new List <string>(); foreach (string url in urlitems) { EndPointClient endPointClient = new EndPointClient(); string extractUrl = endPointClient.extractBaseDomain(url); extractedTest.Add(extractUrl); } Assert.Equal <string>(expectedURL, extractedTest); }