Download HTML from URL and Convert to XML

Downloads an HTML page from a URL and converts it to XML.

Download Chilkat HTML-to-XML ActiveX (also includes HTML-to-PlainText conversion)

Download Chilkat HTTP ActiveX

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

...

procedure TForm1.Button1Click(Sender: TObject);
var
http: TChilkatHttp;
success: Integer;
html: String;
htmlToXml: THtmlToXml;
xml: String;

begin
//  Note: This example uses two Chilkat products: Chilkat HTTP
//  and Chilkat HTML-to-XML.  The "Chilkat Bundle" can be licensed
//  at a price that is less than purchasing each product individually.
//  The "Chilkat Bundle" provides licenses to all existing Chilkat components.  Also, new-version upgrades are always free.

http := TChilkatHttp.Create(Self);

//  Any string argument automatically begins the 30-day trial.
success := http.UnlockComponent('30-day trial');
if (success <> 1) then
  begin
    Memo1.Lines.Add(http.LastErrorText);
    Exit;
  end;

html := http.QuickGetStr('http://www.intel.com/');
if (Length(html) = 0 ) then
  begin
    Memo1.Lines.Add(http.LastErrorText);
    Exit;
  end;

htmlToXml := THtmlToXml.Create(Self);

//  Any string argument automatically begins the 30-day trial.
success := htmlToXml.UnlockComponent('30-day trial');
if (success <> 1) then
  begin
    Memo1.Lines.Add(htmlToXml.LastErrorText);
    Exit;
  end;

//  Indicate the charset of the output XML we'll want.
htmlToXml.XmlCharset := 'utf-8';

//  Set the HTML:
htmlToXml.Html := html;

//  Convert to XML:

xml := htmlToXml.ToXml();

//  Save the XML to a file.
//  Make sure your charset here matches the charset
//  used for the XmlCharset property.
htmlToXml.WriteStringToFile(xml,'out.xml','utf-8');

ShowMessage('Finished.');
end;