Arabic Text Extraction - C#
PDF Extractor SDK sample in C# demonstrating ‘Arabic Text Extraction’
Program.cs
using System.Diagnostics;
using Bytescout.PDFExtractor;
namespace ExtractText
{
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
extractor.LoadDocumentFromFile(@".\sample_english_arabic.pdf");
// Enable Arabic (and other RTL languages) text detection
extractor.RTLTextAutoDetectionEnabled = true;
// Save extracted text to file
extractor.SaveTextToFile(@".\result.txt");
// Cleanup
extractor.Dispose();
// Open result file in default associated application
ProcessStartInfo processStartInfo = new ProcessStartInfo(@".\result.txt");
processStartInfo.UseShellExecute = true;
Process.Start(processStartInfo);
}
}
}