Lazarus Pascal Requires Chilkat v11.7.0+

Exclude or Include Running Headers and Page Numbers

See more PDF Text Extraction Examples

Demonstrates the "repeatedHeadersFooters" filter. Text repeated at the same position on most pages, such as a running header and "Page N of 4" footers, is left out by default; set the filter to "include" to keep it. 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.Pdf,
  Chilkat.JsonObject;

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

procedure RunDemo;
var
  success: Boolean;
  pdf: TPdf;
  json: TJsonObject;
  jsonOut: TJsonObject;

begin
  success := False;

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

  //  The four-page PDF used in this example is available at running_header.pdf

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

  json := TJsonObject.Create;
  jsonOut := TJsonObject.Create;

  //  Every page has the header "Harbor Lighthouse Society - Annual Report 2026" at the top right
  //  and "Page N of 4" at the bottom.  By default both are excluded, so the text of page 2 is just
  //  its heading and paragraphs.
  json.UpdateString('pages','2');
  success := pdf.ExtractText('text',json,jsonOut);
  if (success = False) then
    begin
      WriteLn(pdf.LastErrorText);
      Exit;
    end;
  WriteLn('---- default (repeated headers and footers excluded) ----');
  WriteLn(jsonOut.StringOf('text'));

  //  Include them.  The detection looks at the neighbouring pages even when only one page is
  //  selected, so a single page extracted on its own still loses its running head by default.
  json.UpdateString('repeatedHeadersFooters','include');
  success := pdf.ExtractText('text',json,jsonOut);
  if (success = False) then
    begin
      WriteLn(pdf.LastErrorText);
      Exit;
    end;
  WriteLn('---- repeatedHeadersFooters: include ----');
  WriteLn(jsonOut.StringOf('text'));

  //  Sample output:

  //  ---- default (repeated headers and footers excluded) ----
  //  The Work
  //  
  //  The restoration society took ownership in 2021 with three goals: make the structure watertight, return the tower to public access, and relight the lantern with a historically accurate lens. The first two were met in the second season, and the lens arrived on loan in November.
  //  
  //  The spiral stair is original and is the most fragile part of the building. Twelve of the ninety-one treads were cracked or missing, and the central column had corroded badly at the second landing. The treads were cast from patterns taken off an intact tread.
  //  ---- repeatedHeadersFooters: include ----
  //  Harbor Lighthouse Society - Annual Report 2026
  //  
  //  The Work
  //  
  //  The restoration society took ownership in 2021 with three goals: ...
  //  
  //  The spiral stair is original and is the most fragile part of the building. ...
  //  
  //  Page 2 of 4


  pdf.Free;
  json.Free;
  jsonOut.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.