ByteScout Data Extraction Suite – C# – Read Values from PDF Form Fields with PDF Extractor SDK

Home
/
Articles
/
ByteScout Data Extraction Suite – C# – Read Values from PDF Form Fields with PDF Extractor SDK

printable version:
ByteScout-Data-Extraction-Suite-C-sharp-Read-Values-from-PDF-Form-Fields-with-PDF-Extractor-SDK.pdf

How to read values from PDF form fields with PDF extractor SDK in C# and ByteScout Data Extraction Suite

Learn to code in C# to read values from PDF form fields with PDF extractor SDK with this step-by-step tutorial

These source code samples are assembled by their programming language and functions they apply. ByteScout Data Extraction Suite is the bundle that includes three SDK tools for data extraction from PDF, scans, images and from spreadsheets: PDF Extractor SDK, Data Extraction SDK, Barcode Reader SDK and you can use it to read values from PDF form fields with PDF extractor SDK with C#.

The following code snippet for ByteScout Data Extraction Suite works best when you need to quickly read values from PDF form fields with PDF extractor SDK in your C# application. Follow the instructions from scratch to work and copy the C# code. Enjoy writing a code with ready-to-use sample codes in C#.

You can download free trial version of ByteScout Data Extraction Suite from our website with this and other source code samples for C#.

On-demand (REST Web API) version:
Web API (on-demand version)

On-premise offline SDK for Windows:
60 Day Free Trial (on-premise)

Program.cs

      using System;
using System.Xml;
using Bytescout.PDFExtractor;

namespace ReadValuesFromFormFields
{
    class Program
    {
        static void Main(string[] args)
        {
            try
            {
                // Create XMLExtractor interface
                using (XMLExtractor extractor = new XMLExtractor("demo", "demo"))
                {
                    // Load Sample PDF document
                    extractor.LoadDocumentFromFile("filled_form.pdf");

                    // Get PDF document text as XML
                    string xmlText = extractor.GetXML();

                    // Load XML
                    XmlDocument xmlDocument = new XmlDocument();
                    xmlDocument.LoadXml(xmlText);

                    // Select all "control" nodes
                    XmlNodeList formControls = xmlDocument.SelectNodes("//control");

                    if (formControls != null)
                    {
                        foreach (XmlNode formControl in formControls)
                        {
                            XmlAttribute typeAttribute = formControl.Attributes["type"];

                            // Get filled textboxes
                            if (typeAttribute.Value == "editbox")
                            {
                                if (!string.IsNullOrEmpty(formControl.InnerText))
                                {
                                    Console.WriteLine("EDITBOX " + formControl.Attributes["id"].Value + ": " + formControl.InnerText);
                                }
                            }
                            // Get checked checkboxes
                            else if (typeAttribute.Value == "checkbox")
                            {
                                if (formControl.Attributes["state"].Value == "1")
                                {
                                    Console.WriteLine("CHECKBOX " + formControl.Attributes["id"].Value + ": " + formControl.Attributes["state"].Value);
                                }
                            }

                        }
                    }
                }
            }
            catch (Exception ex)
            {
                Console.WriteLine(ex.Message);
            }

            Console.WriteLine();
            Console.WriteLine("Press any key to exit...");
            Console.ReadLine();
        }
    }
}