Ctrlk
QuickstartContact SalesSign In
For the complete documentation index, see llms.txt. This page is also available as Markdown.
Extraction

Smart Data Extraction

Requirements

These packages are required to use these features in production. Trial keys have unlimited access to all features

Server SDKPackage: Smart Data ExtractionModule: Data ExtractionLive demo

Sample code shows how to use the Apryse Data Extraction module to extract tabular data, document structure and form fields from PDF documents. Sample code provided in Python, C++, C# (.Net), Java, Node.js (JavaScript), PHP, Ruby and VB.

Looking for data extraction + WebViewer UI? Check out our Document Structure Extraction - Showcase Sample Code

Learn more about our Server SDK and Smart Data Extraction.

Implementation steps

  1. Get started with Server SDK in your language/framework

  2. Download the Data Extraction Module

  3. Add the sample code provided in this guide

To use this feature in production, your license key will need the Smart Data Extraction Package. Trial keys already include all packages.

//---------------------------------------------------------------------------------------
// Copyright (c) 2001-2025 by Apryse Software Inc. All Rights Reserved.
// Consult legal.txt regarding legal and license information.
//---------------------------------------------------------------------------------------

using System;

using pdftron;
using pdftron.Common;
using pdftron.PDF;
using pdftron.SDF;
using pdftron.Filters;

namespace DataExtractionTestCS
{
	/// <summary>
	///---------------------------------------------------------------------------------------
	/// The Data Extraction suite is an optional PDFNet add-on collection that can be used to
	/// extract various types of data from PDF documents.
	///
	/// The Apryse SDK Data Extraction suite can be downloaded from https://docs.apryse.com/core/guides/info/modules#data-extraction-module
	//---------------------------------------------------------------------------------------
	/// </summary>
	class Class1
	{
		private static pdftron.PDFNetLoader pdfNetLoader = pdftron.PDFNetLoader.Instance();
		static Class1() { }

		// Relative path to the folder containing test files.
		static string input_path = "../../../../TestFiles/";
		static string output_path = "../../../../TestFiles/Output/";


		/// <summary>
		/// The following sample illustrates how to extract tables from PDF documents.
		/// </summary>
		static void TestTabularData()
		{
			// Test if the add-on is installed
			if (!DataExtractionModule.IsModuleAvailable(DataExtractionModule.DataExtractionEngine.e_tabular))
			{
				Console.WriteLine();
				Console.WriteLine("Unable to run Data Extraction: Apryse SDK Tabular Data module not available.");
				Console.WriteLine("---------------------------------------------------------------");
				Console.WriteLine("The Data Extraction suite is an optional add-on, available for download");
				Console.WriteLine("at https://docs.apryse.com/core/guides/info/modules#data-extraction-module .  If you have already downloaded this");
				Console.WriteLine("module, ensure that the SDK is able to find the required files");
				Console.WriteLine("using the PDFNet.AddResourceSearchPath() function.");
				Console.WriteLine();
				return;
			}

			try
			{
				// Extract tabular data as a JSON file
				DataExtractionModule.ExtractData(input_path + "table.pdf", output_path + "table.json", DataExtractionModule.DataExtractionEngine.e_tabular);

				// Extract tabular data as a JSON string
				string json = DataExtractionModule.ExtractData(input_path + "financial.pdf", DataExtractionModule.DataExtractionEngine.e_tabular);
				System.IO.File.WriteAllText(output_path + "financial.json", json);

				// Extract tabular data as an XLSX file
				DataExtractionModule.ExtractToXLSX(input_path + "table.pdf", output_path + "table.xlsx");

				// Extract tabular data as an XLSX stream (also known as filter)
				MemoryFilter output_xlsx_stream = new MemoryFilter(0, false);
				DataExtractionModule.ExtractToXLSX(input_path + "financial.pdf", output_xlsx_stream);
				output_xlsx_stream.SetAsInputFilter();
				output_xlsx_stream.WriteToFile(output_path + "financial.xlsx", false);
			}
			catch (PDFNetException e)
			{
				Console.WriteLine(e.Message);
			}
		}


		/// <summary>
		// The following sample illustrates how to extract document structure from PDF documents.
		/// </summary>
		static void TestDocumentStructure()
		{
			// Test if the add-on is installed
			if (!DataExtractionModule.IsModuleAvailable(DataExtractionModule.DataExtractionEngine.e_doc_structure))
			{
				Console.WriteLine();
				Console.WriteLine("Unable to run Data Extraction: Apryse SDK Structured Output module not available.");
				Console.WriteLine("---------------------------------------------------------------");
				Console.WriteLine("The Data Extraction suite is an optional add-on, available for download");
				Console.WriteLine("at https://docs.apryse.com/core/guides/info/modules#data-extraction-module . If you have already downloaded this");
				Console.WriteLine("module, ensure that the SDK is able to find the required files");
				Console.WriteLine("using the PDFNet.AddResourceSearchPath() function.");
				Console.WriteLine();
				return;
			}

			try
			{
				// Extract document structure as a JSON file
				DataExtractionModule.ExtractData(input_path + "paragraphs_and_tables.pdf", output_path + "paragraphs_and_tables.json", DataExtractionModule.DataExtractionEngine.e_doc_structure);

				// Extract document structure as a JSON string
				string json = DataExtractionModule.ExtractData(input_path + "tagged.pdf", DataExtractionModule.DataExtractionEngine.e_doc_structure);
				System.IO.File.WriteAllText(output_path + "tagged.json", json);

				// Extract document structure as a Markdown file using the Paddle OCR engine.
				// Note: unlike the default OCR engine, Paddle does not support automatic language
				// detection, so the OCR language must be set explicitly (the default is English).
				DataExtractionOptions options = new DataExtractionOptions();
				options.SetLanguage("eng");
				options.SetPreferredOCREngine(DataExtractionOptions.DataExtractionOCREngine.e_extract_ocr_paddle);
				DataExtractionModule.ExtractToMarkdown(input_path + "US061222892-a.pdf", output_path + "US061222892-a.md", options);
			}
			catch (PDFNetException e)
			{
				Console.WriteLine(e.Message);
			}
		}


		/// <summary>
		// The following sample illustrates how to extract form fields from PDF documents.
		/// </summary>
		static void TestFormFields()
		{
			// Test if the add-on is installed
			if (!DataExtractionModule.IsModuleAvailable(DataExtractionModule.DataExtractionEngine.e_form))
			{
				Console.WriteLine();
				Console.WriteLine("Unable to run Data Extraction: Apryse SDK AIFormFieldExtractor module not available.");
				Console.WriteLine("---------------------------------------------------------------");
				Console.WriteLine("The Data Extraction suite is an optional add-on, available for download");
				Console.WriteLine("at https://docs.apryse.com/core/guides/info/modules#data-extraction-module . If you have already downloaded this");
				Console.WriteLine("module, ensure that the SDK is able to find the required files");
				Console.WriteLine("using the PDFNet.AddResourceSearchPath() function.");
				Console.WriteLine();
				return;
			}

			try
			{
				// Extract form fields as a JSON file
				DataExtractionModule.ExtractData(input_path + "formfields-scanned.pdf", output_path + "formfields-scanned.json", DataExtractionModule.DataExtractionEngine.e_form);

				// Extract form fields as a JSON string
				string json = DataExtractionModule.ExtractData(input_path + "formfields.pdf", DataExtractionModule.DataExtractionEngine.e_form);
				System.IO.File.WriteAllText(output_path + "formfields.json", json);

				// Detect and add form fields to a PDF document.
				// PDF document already has form fields, and this sample will update to new found fields.
				using (PDFDoc doc = new PDFDoc(input_path + "formfields-scanned-withfields.pdf"))
				{
					DataExtractionModule.DetectAndAddFormFieldsToPDF(doc);
					doc.Save(output_path + "formfields-scanned-fields-new.pdf", SDFDoc.SaveOptions.e_linearized);
				}

				// Detect and add form fields to a PDF document.
				// PDF document already has form fields, and this sample will keep the original fields.
				using (PDFDoc doc = new PDFDoc(input_path + "formfields-scanned-withfields.pdf"))
				{
					DataExtractionOptions options = new DataExtractionOptions();
					options.SetOverlappingFormFieldBehavior("KeepOld");

					DataExtractionModule.DetectAndAddFormFieldsToPDF(doc, options);
					doc.Save(output_path + "formfields-scanned-fields-old.pdf", SDFDoc.SaveOptions.e_linearized);
				}
			}
			catch (PDFNetException e)
			{
				Console.WriteLine(e.Message);
			}
		}

		/// <summary>
		// The following sample illustrates how to extract key-value pairs from PDF documents.
		/// </summary>
		static void TestGenericKeyValue()
		{
			if (!DataExtractionModule.IsModuleAvailable(DataExtractionModule.DataExtractionEngine.e_generic_key_value))
				{
					Console.WriteLine();
					Console.WriteLine("Unable to run Data Extraction: Apryse SDK AIPageObjectExtractor module not available.");
					Console.WriteLine("---------------------------------------------------------------");
					Console.WriteLine("The Data Extraction suite is an optional add-on, available for download");
					Console.WriteLine("at https://docs.apryse.com/core/guides/info/modules#data-extraction-module . If you have already downloaded this");
					Console.WriteLine("module, ensure that the SDK is able to find the required files");
					Console.WriteLine("using the PDFNet.AddResourceSearchPath() function.");
					Console.WriteLine();
					return;
				}

			try 
			{				
				// Simple example: Extract Keys & Values as a JSON file
				DataExtractionModule.ExtractData(input_path + "newsletter.pdf", output_path + "newsletter_key_val.json", DataExtractionModule.DataExtractionEngine.e_generic_key_value);

				// Example with customized options:
				// Extract Keys & Values from pages 2-4, excluding ads
				DataExtractionOptions options = new DataExtractionOptions();
				options.SetPages("2-4");

				RectCollection p2ExclusionZones = new RectCollection();
				// Exclude the add-on on page 2
				// These coordinates are in PDF user space, with the origin at the bottom left corner of the page
				// Coordinates rotate with the page, if it has rotation applied.
				p2ExclusionZones.AddRect(166, 47, 562, 222);
				options.AddExclusionZonesForPage(p2ExclusionZones, 2);

				RectCollection p4InclusionZones = new RectCollection();
				RectCollection p4ExclusionZones = new RectCollection();
				// Only include the article text for page 4, exclude ads and headings
				p4InclusionZones.AddRect(30, 432, 562, 684);
				p4ExclusionZones.AddRect(30, 657, 295, 684);
				options.AddInclusionZonesForPage(p4InclusionZones, 4);
				options.AddExclusionZonesForPage(p4ExclusionZones, 4);

				DataExtractionModule.ExtractData(input_path + "newsletter.pdf", output_path + "newsletter_key_val_with_zones.json", DataExtractionModule.DataExtractionEngine.e_generic_key_value, options);
			}
			catch (PDFNetException e)
			{
				Console.WriteLine(e.Message);
			}
		}



		/// <summary>
		// The following sample illustrates how to extract document classes from PDF documents.
		/// </summary>
		static void TestDocClassifier()
		{
			// Test if the add-on is installed
			if (!DataExtractionModule.IsModuleAvailable(DataExtractionModule.DataExtractionEngine.e_doc_classification))
			{
				Console.WriteLine();
				Console.WriteLine("Unable to run Data Extraction: Apryse SDK AIPageObjectExtractor module not available.");
				Console.WriteLine("---------------------------------------------------------------");
				Console.WriteLine("The Data Extraction suite is an optional add-on, available for download");
				Console.WriteLine("at http://www.pdftron.com/. If you have already downloaded this");
				Console.WriteLine("module, ensure that the SDK is able to find the required files");
				Console.WriteLine("using the PDFNet.AddResourceSearchPath() function.");
				Console.WriteLine();
				return;
			}

			try
			{
				// Simple example: classify pages as a JSON file
				DataExtractionModule.ExtractData(input_path + "Invoice.pdf", output_path + "Invoice_Classified.json", DataExtractionModule.DataExtractionEngine.e_doc_classification);

				// Classify pages as a JSON string
				string json = DataExtractionModule.ExtractData(input_path + "Scientific_Publication.pdf", DataExtractionModule.DataExtractionEngine.e_doc_classification);
				System.IO.File.WriteAllText(output_path + "Scientific_Publication_Classified.json", json);

				// Example with customized options:
				DataExtractionOptions options = new DataExtractionOptions();
				// Classes that don't meet the minimum confidence threshold of 70% will not be listed in the output JSON
				options.SetMinimumConfidenceThreshold(0.7);
				DataExtractionModule.ExtractData(input_path + "Email.pdf", output_path + "Email_Classified.json", DataExtractionModule.DataExtractionEngine.e_doc_classification, options);
			}
			catch (PDFNetException e)
			{
				Console.WriteLine(e.Message);
			}
		}


		/// <summary>
		/// The main entry point for the application.
		/// </summary>
		static void Main(string[] args)
		{
			// The first step in every application using PDFNet is to initialize the 
			// library and set the path to common PDF resources. The library is usually 
			// initialized only once, but calling Initialize() multiple times is also fine.
			PDFNet.Initialize(PDFTronLicense.Key);
			PDFNet.AddResourceSearchPath("../../../../../Lib/");

			TestTabularData();
			TestDocumentStructure();
			TestFormFields();
			TestGenericKeyValue();
			TestDocClassifier();

			PDFNet.Terminate();
		}
	}
}