Link Search Menu Expand Document

Extract PDF text To Stream - C#

PDF Extractor SDK sample in C# demonstrating ‘Extract PDF text To Stream’

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

namespace ExtractToStream
    class Program
        static void Main(string[] args)
            // Create Bytescout.PDFExtractor.TextExtractor instance
            TextExtractor extractor = new TextExtractor();
            extractor.RegistrationName = "demo";
            extractor.RegistrationKey = "demo";

            // Load sample PDF document

            // Get page count
            int pageCount = extractor.GetPageCount();

            for (int i = 0; i < pageCount; i++)
                // Create new stream. You can use MemoryStream or any other System.IO.Stream inheritor.
                FileStream stream = new FileStream(@".\page" + i + ".txt", FileMode.Create);
                // Save text from page to the file stream
                extractor.SavePageTextToStream(i, stream);

                // Close stream

            // Cleanup

            // Open first output file in default associated application
            ProcessStartInfo processStartInfo = new ProcessStartInfo(@".\page1.txt");
            processStartInfo.UseShellExecute = true;

Download Source Code (.zip)

Return to the previous page Explore PDF Extractor SDK