CanonicalizeUrl

The CanonicalizeUrl method is a utility function that canonicalizes a URL into a standard form to avoid duplicates. For example, "http://www.chilkatsoft.com/" and "http://www.chilkatsoft.com/default.asp" are the same URL.

Download Chilkat Spider ActiveX

uses
    Windows, Messages, SysUtils, Variants, Classes, Graphics, Controls, Forms,
    Dialogs, StdCtrls,
    SPIDERXLib_TLB,
    SPIDERXLib_TLB,
    OleCtrls;

...

procedure TForm1.Button1Click(Sender: TObject);
var
spider: TSpider;

begin
//  The Chilkat Spider component/library is free.
spider := TSpider.Create(Self);

//  Does a DNS lookup to find the default domain, which may or may not include the "www." depending on the DNS results.
//  Also domain names are converted to lowercase:
Memo1.Lines.Add(spider.CanonicalizeUrl('http://www.ChilkatSoft.com/'));

//  CanonicalizeUrl will drop the HTML fragment:
Memo1.Lines.Add(spider.CanonicalizeUrl('http://www.chilkatsoft.com/purchase2.asp#buyZip'));

//  If a username/password is in the URL, it gets dropped:
Memo1.Lines.Add(spider.CanonicalizeUrl('http://username:password@www.chilkatsoft.com/purchase2.asp#buyZip'));

//  Port 80 and 443 are dropped:
Memo1.Lines.Add(spider.CanonicalizeUrl('http://www.chilkatsoft.com:80/purchase2.asp'));
Memo1.Lines.Add(spider.CanonicalizeUrl('https://www.paypal.com:443/'));

//  Removes default pages:
//  default.asp, index.html, index.htm, default.html, index.htm, default.htm
//  index.php, index.asp, default.php, .cfm, .aspx, ,php3, .pl, .cgi, .txt, .shtml, .phtml
Memo1.Lines.Add(spider.CanonicalizeUrl('http://www.chilkatsoft.com/index.asp'));
Memo1.Lines.Add(spider.CanonicalizeUrl('http://www.chilkatsoft.com/index.asp'));
Memo1.Lines.Add(spider.CanonicalizeUrl('http://www.chilkatsoft.com/index.php'));
Memo1.Lines.Add(spider.CanonicalizeUrl('http://www.chilkatsoft.com/index.pl'));
Memo1.Lines.Add(spider.CanonicalizeUrl('http://www.chilkatsoft.com/index.htm'));

//  Output:
//  http://chilkatsoft.com/
//  http://chilkatsoft.com/purchase2.asp
//  http://chilkatsoft.com/purchase2.asp
//  http://chilkatsoft.com/purchase2.asp
//  https://www.paypal.com/
//  http://chilkatsoft.com/
//  http://chilkatsoft.com/
//  http://chilkatsoft.com/
//  http://chilkatsoft.com/
//  http://chilkatsoft.com/

end;