Extract all HTML Objects from a Web Page

Demonstrates how to download a Web page (at a URL) and extract all HTML objects. Eg. images, links, CSS files, JavaScript files, etc.

Download Chilkat MHT ActiveX

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

...

procedure TForm1.Button1Click(Sender: TObject);
var
mht: TChilkatMht;
success: Integer;
mhtDoc: String;
unpackDir: String;
htmlFilename: String;
partsSubdir: String;

begin
mht := TChilkatMht.Create(Self);

success := mht.UnlockComponent('Anything for 30-day trial');
if (success <> 1) then
  begin
    Memo1.Lines.Add(mht.LastErrorText);
    Exit;
  end;

//  Download a URL into an in-memory MHT web archive contained
//  in a string variable:

mhtDoc := mht.GetMHT('http://www.gopackaging.com/');
if (Length(mhtDoc) = 0 ) then
  begin
    Memo1.Lines.Add(mht.LastErrorText);
    Exit;
  end;

//  Now extract the HTML and embedded objects:
unpackDir := '/Users/chilkat/temp/';
htmlFilename := 'gopackaging.html';
partsSubdir := 'objects';
//  Extract to /Users/chilkat/temp/gopackaging.html.
//  images and other embedded objects are placed in
//  /Users/chilkat/temp/objects.  Directories are automatically
//  created if they don't already exist.
success := mht.UnpackMHTString(mhtDoc,unpackDir,htmlFilename,partsSubdir);
if (success <> 1) then
  begin
    Memo1.Lines.Add(mht.LastErrorText);
  end
else
  begin
    ShowMessage('Unpacked!');
  end;

end;