Lazarus Pascal Requires Chilkat v11.7.0+

Extract PDF to Markdown

See more PDF Text Extraction Examples

Demonstrates the "markdown" operation, which returns the PDF's content as Markdown: headings (inferred from the font sizes when the PDF is not tagged), bold and italic, bullet and numbered lists, links, and ruled tables. Markdown output is well suited to AI and search pipelines. 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 PDF used in this example is available at markdown_features.pdf

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

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

  //  The "markdown" operation uses the same options as "text" (pages, reading order, filters, clean-up)
  //  plus its own options (see the pdf_extract_markdown_options example).  The defaults convert everything.
  success := pdf.ExtractText('markdown',json,jsonOut);
  if (success = False) then
    begin
      WriteLn(pdf.LastErrorText);
      Exit;
    end;

  //  The Markdown of all pages is in the "markdown" member.
  WriteLn(jsonOut.StringOf('markdown'));

  //  The quality report says where the headings came from: "structure" for a tagged PDF,
  //  "inferred" when they were recognized from the font size and weight, or "none".
  WriteLn('Headings: ' + jsonOut.StringOf('quality.pages[0].structure.headings'));

  //  Sample output:

  //  <!-- page 1 -->
  //  
  //  # Field Guide to Backyard Birds
  //  
  //  This short guide covers the birds most often seen at a suburban feeder in the eastern United States. The **bold** names are species you can expect in every season; the *italic* names are winter visitors only.
  //  
  //  ## What to Watch For
  //  
  //  - Size relative to a sparrow or a robin
  //  - Beak shape: thick for seed eaters, thin for insect eaters
  //  - Wing bars and tail markings seen in flight
  //  
  //  ## Getting Started
  //  
  //  1. Hang the feeder where it can be seen from a window.
  //  2. Fill it with black oil sunflower seed, which almost every species takes.
  //  3. Keep a notebook by the window and write down the date of each first sighting.
  //  
  //  For regional checklists and recordings of each song, see the [online bird atlas](https://www.example.com/birds).
  //  
  //  ## Common Visitors
  //  
  //  | Species | Size | Season | Preferred Food |
  //  | --- | --- | --- | --- |
  //  | Northern Cardinal | Robin | All year | Sunflower seed |
  //  | Black-capped Chickadee | Sparrow | All year | Sunflower seed, suet |
  //  | Dark-eyed Junco | Sparrow | Winter | Millet on the ground |
  //  | Downy Woodpecker | Sparrow | All year | Suet |
  //  
  //  Headings: inferred


  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.