Lazarus Pascal

Extract Embedded Files from PDF

Demonstrates how to get information about the embedded files (if any) contained within a PDF, and shows how to extract each file.

Note: This example requires Chilkat v9.5.0.95 or greater.

Lazarus Pascal

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.BinData,
  Chilkat.Pdf,
  Chilkat.JsonObject;

// ---------------------------------------------------------------------------

procedure RunDemo;
var
  success: Boolean;
  pdf: TPdf;
  numFiles: Integer;
  json: TJsonObject;
  bd: TBinData;
  i: Integer;
  filename: string;

begin
  success := False;

  //  This example requires the Chilkat API to have been previously unlocked.
  //  See Global Unlock Sample for sample code.

  pdf := TPdf.Create;

  success := pdf.LoadFile('qa_data/pdf/embedded_files/my_embedded_files_test.pdf');
  if (success = False) then
    begin
      WriteLn(pdf.LastErrorText);
      Exit;
    end;

  //  Note: The embedded file functionality was added in Chilkat v9.5.0.95

  //  How many embedded files exist within the opened PDF?
  numFiles := pdf.NumEmbeddedFiles;
  WriteLn('Number of embedded files: ' + numFiles);

  json := TJsonObject.Create;
  json.EmitCompact := False;

  bd := TBinData.Create;

  //  Get information about each file, and extract each to the filesystem.
  i := 0;
  while i < numFiles do
    begin

      success := pdf.GetEmbeddedFileInfo(i,json);
      if (success = False) then
        begin
          WriteLn(pdf.LastErrorText);
          Exit;
        end;

      WriteLn(json.Emit());

      //  Get the filename from the JSON.
      filename := 'someFile.dat';

      //  The filename SHOULD always be present..
      if (json.HasMember('filename') = True) then
        begin
          filename := json.StringOf('filename');
        end;

      //  Get the file data.
      success := pdf.GetEmbeddedFileBd(i,bd);
      if (success = False) then
        begin
          WriteLn(pdf.LastErrorText);
          Exit;
        end;

      //  Save the contents of the bd to the filename (in the current working directory) in the filesystem.
      success := bd.WriteFile(filename);
      if (success = False) then
        begin
          WriteLn('Failed to write output file.');
        end;

      i := i + 1;
    end;

  //  Sample output for the above code:

  //  Number of embedded files: 3
  //  {
  //    "filename": "employees.json",
  //    "desc": "JSON",
  //    "subType": "application/json",
  //    "size": 159,
  //    "creationDate": "D:20230715170506-05'00'",
  //    "modDate": "D:20160207153838-05'00'"
  //  }
  //  
  //  {
  //    "filename": "rsaPubKey.pem",
  //    "desc": "RSA Public Key PEM",
  //    "size": 451,
  //    "creationDate": "D:20230715170546-05'00'",
  //    "modDate": "D:20150724133153-05'00'"
  //  }
  //  
  //  {
  //    "filename": "starfish.jpg",
  //    "desc": "Starfish JPG",
  //    "subType": "image/jpeg",
  //    "size": 6229,
  //    "creationDate": "D:20230715170356-05'00'",
  //    "modDate": "D:20080529103055-05'00'"
  //  }


  pdf.Free;
  json.Free;
  bd.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.