Text Extraction from PDF using PDFBox in Java

text-extraction-java-pdfbox.java

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
import java.io.File;
import java.io.IOException;

public class PDFTextExtractor {
    public static void main(String[] args) {
        // Path to your PDF file
        String filePath = "sample.pdf";
        
        try (PDDocument document = PDDocument.load(new File(filePath))) {
            
            // 1. Create PDFTextStripper instance
            PDFTextStripper textStripper = new PDFTextStripper();
            
            // 2. Configure extraction settings (optional)
            textStripper.setSortByPosition(true); // Maintains physical layout
            textStripper.setStartPage(1); // First page to extract
            textStripper.setEndPage(document.getNumberOfPages()); // Last page
            
            // 3. Extract text from entire document
            String text = textStripper.getText(document);
            
            // 4. Output results
            System.out.println("=== Extracted Text ===");
            System.out.println(text);
            
            // 5. (Optional) Save to text file
            // Files.writeString(Path.of("extracted.txt"), text);
            
        } catch (IOException e) {
            System.err.println("Error extracting text: " + e.getMessage());
        }
    }
}