Delphi DLL
Delphi DLL
Extract HTML Title, Description, Keywords
See more Spider Examples
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.Chilkat Delphi DLL Downloads
uses
Winapi.Windows, Winapi.Messages, System.SysUtils, System.Variants, System.Classes, Vcl.Graphics,
Vcl.Controls, Vcl.Forms, Vcl.Dialogs, Vcl.StdCtrls, Spider;
...
procedure TForm1.Button1Click(Sender: TObject);
var
success: Boolean;
spider: HCkSpider;
i: Integer;
begin
success := False;
spider := CkSpider_Create();
// 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
CkSpider_Initialize(spider,'www.chilkatsoft.com');
// Add the 1st URL:
CkSpider_AddUnspidered(spider,'http://www.chilkatsoft.com/');
// Begin crawling the site by calling CrawlNext repeatedly.
for i := 0 to 9 do
begin
success := CkSpider_CrawlNext(spider);
if (success = True) then
begin
// Show the URL of the page just spidered.
Memo1.Lines.Add(CkSpider__lastUrl(spider));
// The HTML META keywords, title, and description are available in these properties:
Memo1.Lines.Add(CkSpider__lastHtmlTitle(spider));
Memo1.Lines.Add(CkSpider__lastHtmlDescription(spider));
Memo1.Lines.Add(CkSpider__lastHtmlKeywords(spider));
// 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 (CkSpider_getNumUnspidered(spider) = 0) then
begin
Memo1.Lines.Add('No more URLs to spider');
end
else
begin
Memo1.Lines.Add(CkSpider__lastErrorText(spider));
end;
end;
// Sleep 1 second before spidering the next URL.
CkSpider_SleepMs(spider,1000);
end;
CkSpider_Dispose(spider);
end;