Click or drag to resize

PdfFocusToXml Method

Saves all pages of the PDF document into XML document and returns it as string

Namespace: SautinSoft
Assembly: SautinSoft.PdfFocus (in SautinSoft.PdfFocus.dll) Version: 2024.3.28
Syntax
Copy
public string ToXml()

Return Value

String
String with XML document - in case of converting successful.
null - in case of converting failed.
Example
How to convert PDF to XML in memory using C#
Copy
using System;
using System.IO;

namespace Sample
{
    class Sample
    {
        static void Main(string[] args)
        {
            string pathToPdf = Path.GetFullPath(@"..\..\..\Table.pdf");
            string pathToXml = "Result.xml";

            byte[] pdf = File.ReadAllBytes(pathToPdf);
            string xml = null;
                                  // Get your free 30-day key here:   
             // https://sautinsoft.com/start-for-free/

            // Convert PDF file to XML file.
            SautinSoft.PdfFocus f = new SautinSoft.PdfFocus();

            // Let's convert all data (textual and tabular) to XML.
            f.XmlOptions.ConvertNonTabularDataToSpreadsheet = true;

            f.OpenPdf(pdf);

            if (f.PageCount > 0)
            {
                xml = f.ToXml();

                //Show XML document in browser
                if (!String.IsNullOrEmpty(xml))
                {
                    File.WriteAllText(pathToXml,xml);
                    System.Diagnostics.Process.Start(new System.Diagnostics.ProcessStartInfo(pathToXml) { UseShellExecute = true });
                }
            }
        }
    }
}
How to convert PDF to XML in memory using VB.Net
Copy
Imports System.IO
Imports System.Drawing.Imaging
Imports System.Collections.Generic
Imports SautinSoft

Module Sample

    Sub Main()
        Dim pathToPdf As String = Path.GetFullPath("..\..\..\Table.pdf")
        Dim pathToXml As String = "Result.xml"

        Dim pdf() As Byte = File.ReadAllBytes(pathToPdf)
        Dim xml As String = Nothing
                                ' Get your free 30-day key here: 
                                ' https://sautinsoft.com/start-for-free/

        ' Convert PDF file to XML file.
        Dim f As New SautinSoft.PdfFocus()

        ' Let's convert all data (textual and tabular) to XML.
        f.XmlOptions.ConvertNonTabularDataToSpreadsheet = True

        f.OpenPdf(pdf)

        If f.PageCount > 0 Then
            xml = f.ToXml()

            'Show XML document in browser
            If Not String.IsNullOrEmpty(xml) Then
                File.WriteAllText(pathToXml, xml)
                System.Diagnostics.Process.Start(New System.Diagnostics.ProcessStartInfo(pathToXml) With {.UseShellExecute = True})
            End If
        End If
    End Sub
End Module
See Also