Pascal (Lazarus/Delphi)

CanonicalizeUrl

See more Spider Examples

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. Pascal (Lazarus/Delphi)

program ChilkatDemo;

// Demonstrates using the Chilkat Pascal wrapper via the C bridge DLL.
// Builds as a console application under Lazarus (FPC) or Delphi.

{$IFDEF FPC}
  {$MODE DELPHI}
{$ENDIF}
{$APPTYPE CONSOLE}

uses
  {$IFDEF UNIX}
  cthreads,
  {$ENDIF}
  SysUtils,
  CkDllLoader,
  Chilkat.Spider;

// ---------------------------------------------------------------------------

procedure RunDemo;
var
  spider: TSpider;

begin
  spider := TSpider.Create;

  //  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:
  WriteLn(spider.CanonicalizeUrl('http://www.ChilkatSoft.com/'));

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

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

  //  Port 80 and 443 are dropped:
  WriteLn(spider.CanonicalizeUrl('http://www.chilkatsoft.com:80/purchase2.asp'));
  WriteLn(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
  WriteLn(spider.CanonicalizeUrl('http://www.chilkatsoft.com/index.asp'));
  WriteLn(spider.CanonicalizeUrl('http://www.chilkatsoft.com/index.asp'));
  WriteLn(spider.CanonicalizeUrl('http://www.chilkatsoft.com/index.php'));
  WriteLn(spider.CanonicalizeUrl('http://www.chilkatsoft.com/index.pl'));
  WriteLn(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/


  spider.Free;

end;

// ---------------------------------------------------------------------------

begin

  try
    RunDemo;
  except
    on E: Exception do
      WriteLn('Unhandled exception: ', E.ClassName, ': ', E.Message);
  end;

  WriteLn;
  {$IFDEF MSWINDOWS}
  WriteLn('Press Enter to exit...');
  ReadLn;
  {$ENDIF}
end.