How to Convert PDF to Text in C# and Java

using pdftron; 

using pdftron.PDF; 

 

namespace ConsoleApp1 

{ 

    internal class Program 

    { 

        static void Main(string[] args) 

        { 

            PDFNet.Initialize("your_license_key"); 

            PDFNet.AddResourceSearchPath(@"path_to_your_ocr_module"); 

 

            // Directory containing the PDF files 

            string directoryPath = "samples"; 

 

            // Get all PDF files in the directory 

            string[] pdfFiles = Directory.GetFiles(directoryPath, "*.pdf"); 

 

            foreach (string pdfFile in pdfFiles) 

            { 

                Console.WriteLine($"Processing file: {pdfFile}"); 

 

                using (PDFDoc doc = new PDFDoc(pdfFile)) 

                { 

                    doc.InitSecurityHandler(); 

 

                    // Extract text from the document 

                    string allText = ExtractTextFromDocument(doc); 

 

                    // If no text is found, perform OCR 

                    if (string.IsNullOrEmpty(allText.Trim())) 

                    { 

                        Console.WriteLine("No text found, performing OCR..."); 

                        PerformOCR(doc); 

                        allText = ExtractTextFromDocument(doc); 

                    } 

 

                    Console.WriteLine(allText); 

                } 

            } 

        } 

 

        static string ExtractTextFromDocument(PDFDoc doc) 

        { 

            TextExtractor txt = new TextExtractor(); 

            string allText = ""; 

 

            for (int i = 1; i <= doc.GetPageCount(); i++) 

            { 

                txt.Begin(doc.GetPage(i)); 

                allText += txt.GetAsText() + "\n"; 

            } 

 

            return allText; 

        } 

 

        static void PerformOCR(PDFDoc doc) 

        { 

            OCROptions ocrOptions = new OCROptions(); 

            ocrOptions.AddLang("eng"); 

            OCRModule.ProcessPDF(doc, ocrOptions); 

        } 

    } 

} 

import com.pdftron.pdf.*; 

import java.io.File; 

import com.pdftron.common.PDFNetException; 

 

public class App { 

public static void main(String[] args) { 

    try { 

      PDFNet.initialize("your_license_key"); 

      PDFNet.addResourceSearchPath("path_to_your_ocr_module"); 

 

      // Directory containing the PDF files 

      String directoryPath = "src\\samples"; 

 

      // Get all PDF files in the directory 

      File dir = new File(directoryPath); 

      File[] pdfFiles = dir.listFiles((d, name) -> name.toLowerCase().endsWith(".pdf")); 

 

      if (pdfFiles != null) { 

        for (File pdfFile : pdfFiles) { 

          System.out.println("Processing file: " + pdfFile.getAbsolutePath()); 

 

          PDFDoc doc = new PDFDoc(pdfFile.getAbsolutePath()); 

          doc.initSecurityHandler(); 

 

          // Extract text from the document 

          String allText = extractTextFromDocument(doc); 

 

          // If no text is found, perform OCR 

          if (allText.trim().isEmpty()) { 

            System.out.println("No text found, performing OCR..."); 

            performOCR(doc); 

            allText = extractTextFromDocument(doc); 

          } 

 

          System.out.println(allText); 

          doc.close(); 

        } 

      } 

    } catch (PDFNetException e) { 

      e.printStackTrace(); 

    } 

  } 

 

  static String extractTextFromDocument(PDFDoc doc) throws PDFNetException { 

    TextExtractor txt = new TextExtractor(); 

    StringBuilder allText = new StringBuilder(); 

 

    for (int i = 1; i <= doc.getPageCount(); i++) { 

      txt.begin(doc.getPage(i)); 

      allText.append(txt.getAsText()).append("\n"); 

    } 

 

    return allText.toString(); 

  } 

 

  static void performOCR(PDFDoc doc) throws PDFNetException { 

    OCROptions ocrOptions = new OCROptions(); 

    ocrOptions.addLang("eng"); 

    OCRModule.processPDF(doc, ocrOptions); 

  } 

}