Isolate table from pdf and get table data as a datatable

1. Install iTextSharp NuGet package:

In your ASP.NET project, open the NuGet Package Manager and search for "iTextSharp." Install the iTextSharp (iText 7 Community) package.

1. Create a method to extract the table as a DataTable:

using iText.Kernel.Pdf;
using iText.Layout;
using iText.Layout.Element;
using iText.Layout.Properties;
using iText.Kernel.Geom;
using iText.Kernel.Font;
using iText.IO.Font.Constants;
using iText.Kernel.Colors;

public DataTable ExtractTableFromPDF(string pdfFilePath, int tableIndex)
{
    DataTable dataTable = new DataTable();

    using (PdfDocument pdfDocument = new PdfDocument(new PdfReader(pdfFilePath)))
    {
        PdfPage page = pdfDocument.GetPage(1); // Assuming the table is on the first page

        ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
        string pageContent = PdfTextExtractor.GetTextFromPage(page, strategy);

        string[] lines = pageContent.Split('\n');

        // Assuming the table is represented as lines in the PDF
        string tableLine = lines[tableIndex];

        // Split the table line into individual cells based on separators (e.g., tabs, spaces, etc.)
        string[] cells = tableLine.Split(new char[] { '\t', ' ' }, StringSplitOptions.RemoveEmptyEntries);

        // Assuming the first row contains column headers, populate the DataTable's columns
        foreach (string cell in cells)
        {
            dataTable.Columns.Add(cell.Trim());
        }

        // Start from the second row to populate the DataTable's rows
        for (int i = tableIndex + 1; i < lines.Length; i++)
        {
            string rowLine = lines[i];
            string[] rowCells = rowLine.Split(new char[] { '\t', ' ' }, StringSplitOptions.RemoveEmptyEntries);
            DataRow dataRow = dataTable.NewRow();
            for (int j = 0; j < rowCells.Length; j++)
            {
                dataRow[j] = rowCells[j].Trim();
            }
            dataTable.Rows.Add(dataRow);
        }
    }

    return dataTable;
}

Check this, it may help you.

using iTextSharp.text;
using iTextSharp.text.pdf;
using System.Data;
using System.IO;


public DataTable ExtractTableFromPDF(string pdfFilePath)
{
    DataTable dataTable = new DataTable();

    using (PdfReader reader = new PdfReader(pdfFilePath))
    {
        for (int page = 1; page <= reader.NumberOfPages; page++)
        {
            ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
            string currentPageText = PdfTextExtractor.GetTextFromPage(reader, page, strategy);
            string[] lines = currentPageText.Split('\n');

            bool tableStarted = false;

            foreach (string line in lines)
            {
                if (line.Contains("HeaderRowText")) // Replace "HeaderRowText" with the unique identifier of the table's header row
                {
                    tableStarted = true;

                    string[] headers = line.Split('\t'); // Split by tab or another delimiter used in the table
                    foreach (string header in headers)
                    {
                        dataTable.Columns.Add(header);
                    }
                }
                else if (tableStarted && !string.IsNullOrWhiteSpace(line))
                {
                    string[] values = line.Split('\t'); // Split by tab or another delimiter used in the table
                    dataTable.Rows.Add(values);
                }
            }
        }
    }

    return dataTable;
}

string pdfFilePath = "path/to/your/pdf/file.pdf";
DataTable extractedTable = ExtractTableFromPDF(pdfFilePath);