Extract Table from PDF in C#

extract-table-from-pdf.cs

// Load source PDF document
var filePath = "input.pdf";
Aspose.Pdf.Document pdfDocument = new Aspose.Pdf.Document(filePath);
foreach (var page in pdfDocument.Pages)
{
    Aspose.Pdf.Text.TableAbsorber absorber = new Aspose.Pdf.Text.TableAbsorber();
    absorber.Visit(page);
    foreach (AbsorbedTable table in absorber.TableList)
    {
        Console.WriteLine("Table");
        foreach (AbsorbedRow row in table.RowList)
        {
            foreach (AbsorbedCell cell in row.CellList)
            {
                foreach (TextFragment fragment in cell.TextFragments)
                {
                    var sb = new StringBuilder();
                    foreach (TextSegment seg in fragment.Segments)
                        sb.Append(seg.Text);
                    Console.Write("{sb.ToString()}|");
                }
            }
            Console.WriteLine();
        }
    }
}

pdf-table-to-csv.cs

// Load PDF document
Document pdfDocument = new Document("input.pdf");

// Instantiate ExcelSave Option object
ExcelSaveOptions excelSave = new ExcelSaveOptions { Format = ExcelSaveOptions.ExcelFormat.CSV };

// Save the output in XLS format
pdfDocument.Save("PDFToXLS_out.xlsx", excelSave);