<dependencies>
    <!-- Apache PDFBox -->
    <dependency>
        <groupId>org.apache.pdfbox</groupId>
        <artifactId>pdfbox</artifactId>
        <version>2.0.27</version>
    </dependency>

    <!-- Tess4J -->
    <dependency>
        <groupId>net.sourceforge.tess4j</groupId>
        <artifactId>tess4j</artifactId>
        <version>4.5.4</version>
    </dependency>
</dependencies>

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 String extractTextFromPDF(String filePath) throws IOException {
        File file = new File(filePath);
        PDDocument document = PDDocument.load(file);
        PDFTextStripper pdfStripper = new PDFTextStripper();
        String text = pdfStripper.getText(document);
        document.close();
        return text;
    }

    public static void main(String[] args) {
        try {
            String text = extractTextFromPDF("example.pdf");
            System.out.println(text);
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

import net.sourceforge.tess4j.Tesseract;
import net.sourceforge.tess4j.TesseractException;

import java.io.File;

public class OCRExample {

    public static String recognizeTextFromImage(String imagePath) throws TesseractException {
        Tesseract tesseract = new Tesseract();
        tesseract.setDatapath("tessdata"); // 設(shè)置Tesseract的數(shù)據(jù)文件路徑
        tesseract.setLanguage("eng"); // 設(shè)置識(shí)別語(yǔ)言為英文
        return tesseract.doOCR(new File(imagePath));
    }

    public static void main(String[] args) {
        try {
            String text = recognizeTextFromImage("example.png");
            System.out.println(text);
        } catch (TesseractException e) {
            e.printStackTrace();
        }
    }
}

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.rendering.PDFRenderer;
import org.apache.pdfbox.text.PDFTextStripper;
import net.sourceforge.tess4j.Tesseract;
import net.sourceforge.tess4j.TesseractException;

import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.IOException;

public class PDFOCRExample {

    public static String extractTextFromPDF(String filePath) throws IOException, TesseractException {
        File file = new File(filePath);
        PDDocument document = PDDocument.load(file);
        PDFTextStripper pdfStripper = new PDFTextStripper();
        StringBuilder text = new StringBuilder();

        for (int page = 0; page < document.getNumberOfPages(); page++) {
            String pageText = pdfStripper.getText(document);
            if (pageText.trim().isEmpty()) {
                // 如果頁(yè)面沒(méi)有文本，嘗試使用OCR識(shí)別
                PDFRenderer renderer = new PDFRenderer(document);
                BufferedImage image = renderer.renderImageWithDPI(page, 300); // 300 DPI for better OCR accuracy
                File tempImageFile = File.createTempFile("pdfpage", ".png");
                ImageIO.write(image, "png", tempImageFile);
                String ocrText = recognizeTextFromImage(tempImageFile.getAbsolutePath());
                text.append(ocrText);
                tempImageFile.delete();
            } else {
                text.append(pageText);
            }
        }

        document.close();
        return text.toString();
    }

    public static String recognizeTextFromImage(String imagePath) throws TesseractException {
        Tesseract tesseract = new Tesseract();
        tesseract.setDatapath("tessdata"); // 設(shè)置Tesseract的數(shù)據(jù)文件路徑
        tesseract.setLanguage("eng"); // 設(shè)置識(shí)別語(yǔ)言為英文
        return tesseract.doOCR(new File(imagePath));
    }

    public static void main(String[] args) {
        try {
            String text = extractTextFromPDF("example.pdf");
            System.out.println(text);
        } catch (IOException | TesseractException e) {
            e.printStackTrace();
        }
    }
}