ByteScout Premium Suite – C# – Index PDF Documents In Folder with PDF Extractor SDK

Home
/
Articles
/
ByteScout Premium Suite – C# – Index PDF Documents In Folder with PDF Extractor SDK

printable version:
ByteScout-Premium-Suite-C-sharp-Index-PDF-Documents-In-Folder-with-PDF-Extractor-SDK.pdf

How to index PDF documents in folder with PDF extractor SDK in C# and ByteScout Premium Suite

If you want to learn more then this tutorial will show how to index PDF documents in folder with PDF extractor SDK in C#

Every ByteScout tool includes simple example C# source codes that you can get here or in the folder with installed ByteScout product. What is ByteScout Premium Suite? It is the bundle that includes twelve SDK products from ByteScout including tools and components for PDF, barcodes, spreadsheets, screen video recording. It can help you to index PDF documents in folder with PDF extractor SDK in your C# application.

The SDK samples given below describe how to quickly make your application do index PDF documents in folder with PDF extractor SDK in C# with the help of ByteScout Premium Suite. Follow the instructions from scratch to work and copy the C# code. Complete and detailed tutorials and documentation are available along with installed ByteScout Premium Suite if you’d like to learn more about the topic and the details of the API.

All these programming tutorials along with source code samples and ByteScout free trial version are available for download from our website.

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 Bytescout.PDFExtractor;
using System;
using System.Collections.Generic;
using System.IO;

namespace IndexDocsInFolder
{
    class Program
    {
        static void Main(string[] args)
        {
            try
            {
                // Output file list
                var lstAllFilesInfo = new List<FileIndexOutput>();

                // Get all files inside directory
                var allFiles = Directory.GetFiles(@".\Files", "*.*");

                // Iterate all files, and get details
                foreach (var itmFile in allFiles)
                {
                    // Get basic file information
                    FileInfo fileInfo = new FileInfo(itmFile);

                    // Check whether file is supported
                    if (_IsFileSupported(fileInfo))
                    {
                        // Fill file index model
                        var oFileIndex = new FileIndexOutput();
                        oFileIndex.fileName = fileInfo.Name;
                        oFileIndex.fileDate = fileInfo.CreationTime;
                        oFileIndex.content = _GetFileContent(fileInfo);

                        // Add to final list
                        lstAllFilesInfo.Add(oFileIndex);
                    }
                }

                // Print all output
                Console.WriteLine("Total {0} files indexed\n", lstAllFilesInfo.Count);
                foreach (var itmFileInfo in lstAllFilesInfo)
                {
                    Console.WriteLine("fileName: {0}", itmFileInfo.fileName);
                    Console.WriteLine("fileDate: {0}", itmFileInfo.fileDate.ToString("MMM dd yyyy hh:mm:ss"));
                    Console.WriteLine("content: {0}", itmFileInfo.content.Trim());
                    Console.WriteLine();
                }
            }
            catch (Exception ex)
            {
                Console.WriteLine(ex.Message);
            }

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

        /// <summary>
        /// Get File Content
        /// </summary>
        private static string _GetFileContent(FileInfo fileInfo)
        {
            string fileExtension = System.IO.Path.GetExtension(fileInfo.FullName);

            if (fileExtension == ".pdf")
            {
                return _GetPdfFileContent(fileInfo);
            }
            else if (fileExtension == ".png" || fileExtension == ".jpg")
            {
                return _GetImageContet(fileInfo);
            }

            throw new Exception("File not supported.");
        }

        /// <summary>
        /// Get PDF File Content
        /// </summary>
        private static string _GetPdfFileContent(FileInfo fileInfo)
        {
            //Read all file content...
            using (TextExtractor textExtractor = new TextExtractor("demo","demo"))
            {
                //Load Document
                textExtractor.LoadDocumentFromFile(fileInfo.FullName);

                return textExtractor.GetText();
            }
        }

        /// <summary>
        /// Get Image Contents
        /// </summary>
        private static string _GetImageContet(FileInfo fileInfo)
        {
            //Read all file content...
            using (TextExtractor extractor = new TextExtractor())
            {
                // Load document
                extractor.LoadDocumentFromFile(fileInfo.FullName);

                //Set option to repair text
                extractor.OCRMode = OCRMode.TextFromImagesAndVectorsAndRepairedFonts;

                // 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\";

                // 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 https://github.com/bytescout/ocrdata

                // Set PDF document rendering resolution
                extractor.OCRResolution = 300;

                // Read all text
                return extractor.GetText();
            }
        }

        /// <summary>
        /// Check whether file is valid
        /// </summary>
        private static bool _IsFileSupported(FileInfo fileInfo)
        {
            //Get File Extension
            string fileExtension = Path.GetExtension(fileInfo.Name);

            //Check whether file extension is valid
            return (fileExtension == ".pdf" || fileExtension == ".png" || fileExtension == ".jpg");
        }

    }

    /// <summary>
    /// FileIndexOutput class
    /// </summary>
    public class FileIndexOutput
    {
        public string fileName { get; set; }

        public DateTime fileDate { get; set; }

        public string content { get; set; }
    }

}