static void Main(string[] args)
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
extractor.OCRLanguageDataFolder = @"c:\Program Files\Bytescout PDF Extractor SDK\net2.00\tessdata";
// Load sample PDF document
extractor.LoadDocumentFromFile("sample_ocr.pdf");
// Apply predefined profiles
extractor.Profiles = "scanned, no-layout";
// Extract text to file
extractor.SaveTextToFile("result1.txt");
extractor.Reset();
// Load another document
extractor.LoadDocumentFromFile("sample_ocr.pdf");
// Load and apply custom profiles
extractor.LoadProfiles("profiles.json");
extractor.Profiles = "keep-formatting, ocr-forced-200dpi";
// Extract text to file
extractor.SaveTextToFile("result2.txt");
extractor.Dispose();
}
static void Main()
{
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
// Get PDF files
string[] pdfFiles = Directory.GetFiles(".", "*.pdf");
foreach (string file in pdfFiles)
{
// Load document
extractor.LoadDocumentFromFile(file);
// Save extracted text to .txt file
extractor.SaveTextToFile(Path.ChangeExtension(file, ".txt"));
// Reset the extractor before load another file
extractor.Reset();
}
// Cleanup
extractor.Dispose();
}
protected void Page_Load(object sender, EventArgs e)
{
// Directory containing test files
String inputFolder = Server.MapPath(@".\bin");
// Create Bytescout.PDFExtractor.TextExtractor instance
TextExtractor extractor = new TextExtractor();
extractor.RegistrationName = "demo";
extractor.RegistrationKey = "demo";
Response.Clear();
Response.ContentType = "text/html";
// Get PDF files
string[] pdfFiles = Directory.GetFiles(inputFolder, "*.pdf");
foreach (string file in pdfFiles)
{
// Load document
extractor.LoadDocumentFromFile(file);
// Save extracted text to output stream
extractor.SaveTextToStream(Response.OutputStream);
// Reset the extractor before load another file
extractor.Reset();
}
Response.End();
}
