Link Search Menu Expand Document

Extract Text From PDF By Pages - C#

PDF Extractor SDK sample in C# demonstrating ‘Extract Text From PDF By Pages’

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

namespace ExtractTextByPages
	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++)
				string fileName = "page" + i + ".txt";
				// Save extracted page text to file
				extractor.SavePageTextToFile(i, fileName);

			// 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