C# および VB.NET で PDF ドキュメントからテキスト、パス、画像を抽出する

using BitMiracle.Docotic.Pdf;

using var pdf = new PdfDocument("your_document.pdf");
var options = new PdfTextExtractionOptions
{
    SkipInvisibleText = true,
    WithFormatting = true
};
string formattedText = pdf.GetText(options);
Console.WriteLine(formattedText);

using var pdf = new PdfDocument("your_document.pdf");
PdfPage page = pdf.Pages[0];
foreach (PdfTextData data in page.GetWords())
{
    Console.WriteLine(
    $"{{\n" +
    $"  text: '{data.GetText()}',\n" +
    $"  bounds: {data.Bounds},\n" +
    $"  font name: '{data.Font.Name}',\n" +
    $"  font size: {data.FontSize},\n" +
    $"  transformation matrix: {data.TransformationMatrix},\n" +
    $"  rendering mode: '{data.RenderingMode}',\n" +
    $"  brush: {data.Brush},\n" +
    $"  pen: {data.Pen}\n" +
    $"}},"
    );
}

using BitMiracle.Docotic.Pdf;

using var pdf = new PdfDocument("your_document.pdf");
int i = 0;
foreach (PdfImage image in pdf.GetImages())
{
    string imageFile = image.Save(i.ToString());
    ++i;
}