Pascal (Lazarus/Delphi)

Using the Disk Cache

See more Spider Examples

The Chilkat Spider component has disk caching capabilities. To setup a disk cache, create a new directory anywhere on your local hard drive and set the CacheDir property to the path. For example, you might create "c:/spiderCache/". The UpdateCache property controls whether downloaded pages are saved to the cache. The FetchFromCache property controls whether the cache is first checked for pages. The LastFromCache property tells whether the last URL fetched came from cache or not. 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
  success: Boolean;
  spider: TSpider;
  i: Integer;

begin
  success := False;

  spider := TSpider.Create;

  //  Set our cache directory and make sure saving-to-cache and fetching-from-cache
  //  are both turned on:
  spider.CacheDir := 'c:/spiderCache/';
  spider.FetchFromCache := True;
  spider.UpdateCache := True;

  //  If you run this code twice, you'll find that the 2nd run is extremely fast
  //  because the pages will be retrieved from cache.

  //  The spider object crawls a single web site at a time.  As you'll see
  //  in later examples, you can collect outbound links and use them to 
  //  crawl the web.  For now, we'll simply spider 10 pages of chilkatsoft.com
  spider.Initialize('www.chilkatsoft.com');

  //  Add the 1st URL:
  spider.AddUnspidered('http://www.chilkatsoft.com/');

  //  Begin crawling the site by calling CrawlNext repeatedly.

  for i := 0 to 9 do
    begin

      success := spider.CrawlNext();
      if (success = True) then
        begin
          //  Show the URL of the page just spidered.
          WriteLn(spider.LastUrl);
          //  The HTML is available in the LastHtml property
        end
      else
        begin
          //  Did we get an error or are there no more URLs to crawl?
          if (spider.NumUnspidered = 0) then
            begin
              WriteLn('No more URLs to spider');
            end
          else
            begin
              WriteLn(spider.LastErrorText);
            end;
        end;

      //  Sleep 1 second before spidering the next URL.
      //  The reason for waiting a short time before the next fetch is to prevent
      //  undue stress on the web server.  However, if the last page was retrieved
      //  from cache, there is no need to pause.
      if (spider.LastFromCache <> True) then
        begin
          spider.SleepMs(1000);
        end;
    end;



  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.