Link Search Menu Expand Document

Split PDF Document By Text - C#

PDF Extractor SDK sample in C# demonstrating ‘Split PDF Document By Text’

using System;
using System.IO;
using Bytescout.PDFExtractor;

namespace SplittingExample
    class Program
        static void Main(string[] args)
            // Input File
            string inputFile = "sample.pdf";

            // Output FOlder
            string outputFolder = "./output";

            // Regex-Enabled - Search for multiple strings
            //String[] pattern_list = new string[] {"Invoice", "1nvoice"};
            //String searchString = String.Format("({0})", String.Join("|", pattern_list));
            //bool isRegexEnabled = true;

            // Search single string
            string searchString = "Invoice";
            bool isRegexEnabled = false;

            // Registration name/key
            string registration_name = "demo";
            string registration_key = "demo";

            using (var extractor = new DocumentSplitter2(registration_name, registration_key))
                // Enable Optical Character Recognition (OCR)
                // in .Auto mode (SDK automatically checks if needs to use OCR or not)
                extractor.OCRMode = OCRMode.Auto;

                // Set the location of OCR language data files
                extractor.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\ocrdata_best\";

                // Set OCR language
                extractor.OCRLanguage = "eng"; // "eng" for english, "deu" for German, "fra" for French, "spa" for Spanish etc - according to files in "ocrdata" folder
                                               // Find more language files at

                // Repair broken letters

                // Remove noise

                // Auto-Detect Page Rotation
                extractor.OCRDetectPageRotation = true;

                // Add Filters for Horizonal/Vertical Line

                // Perform Split by Text
                var files = extractor.Split(inputFile, searchString,
                    caseSensitive: false,
                    useRegex: isRegexEnabled,
                    excludePageWithFoundText: false,
                    outputFolder: outputFolder);

                // Display Output
                Console.WriteLine(@"Splitted by Text: ");
                foreach (string file in files)
                    Console.WriteLine("    " + Path.GetFileName(file));

            Console.WriteLine("Press any key...");

Download Source Code (.zip)

Return to the previous page Explore PDF Extractor SDK