Extract HTML Title, Description, Keywords

This example expands on the "getting started" example by showing how to access the HTML title, description, and keywords within each page spidered. These are the contents of the META tags for keywords, description, and title found in the HTML header.

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;
i: Integer;
success: Integer;

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

//  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 = 1) then
      begin
        //  Show the URL of the page just spidered.
        Memo1.Lines.Add(spider.LastUrl);

        //  The HTML META keywords, title, and description are available in these properties:
        Memo1.Lines.Add(spider.LastHtmlTitle);
        Memo1.Lines.Add(spider.LastHtmlDescription);
        Memo1.Lines.Add(spider.LastHtmlKeywords);

        //  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
            ShowMessage('No more URLs to spider');
          end
        else
          begin
            ShowMessage(spider.LastErrorText);
          end;
      end;
    //  Sleep 1 second before spidering the next URL.
    spider.SleepMs(1000);
  end;


end;