使用Java提取PDF中的文字的三种常见方法

<dependency>
    <groupId>org.apache.pdfbox</groupId>
    <artifactId>pdfbox</artifactId>
    <version>2.0.27</version>
</dependency>

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) {
        String pdfPath = "sample.pdf";  // 替换为你的 PDF 文件路径
        try (PDDocument document = PDDocument.load(new File(pdfPath))) {
            PDFTextStripper pdfStripper = new PDFTextStripper();
            String text = pdfStripper.getText(document);
            System.out.println("提取的文本内容：\n" + text);
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

<dependency>
    <groupId>com.itextpdf</groupId>
    <artifactId>itext7-core</artifactId>
    <version>7.1.17</version>
</dependency>

import com.itextpdf.kernel.pdf.*;
import com.itextpdf.kernel.pdf.canvas.parser.PdfTextExtractor;
import java.io.File;
import java.io.IOException;

public class ITextPDFTextExtractor {
    public static void main(String[] args) {
        String pdfPath = "sample.pdf";  // 替换为你的 PDF 文件路径
        try (PdfDocument pdfDoc = new PdfDocument(new PdfReader(pdfPath))) {
            StringBuilder extractedText = new StringBuilder();
            for (int i = 1; i <= pdfDoc.getNumberOfPages(); i++) {
                extractedText.append(PdfTextExtractor.getTextFromPage(pdfDoc.getPage(i))).append("\n");
            }
            System.out.println("提取的文本内容：\n" + extractedText);
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

<dependency>
    <groupId>net.sourceforge.tess4j</groupId>
    <artifactId>tess4j</artifactId>
    <version>4.5.5</version>
</dependency>

import net.sourceforge.tess4j.Tesseract;
import net.sourceforge.tess4j.TesseractException;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.rendering.PDFRenderer;
import java.awt.image.BufferedImage;
import java.io.File;
import java.io.IOException;

public class OCRPDFExtractor {
    public static void main(String[] args) throws IOException, TesseractException {
        String pdfPath = "scanned.pdf";  // 替换为你的 PDF 文件路径
        PDDocument document = PDDocument.load(new File(pdfPath));
        PDFRenderer pdfRenderer = new PDFRenderer(document);
        Tesseract tesseract = new Tesseract();
        tesseract.setDatapath("tessdata");  // 设置 Tesseract 训练数据路径
        tesseract.setLanguage("eng");  // 设置语言

        StringBuilder extractedText = new StringBuilder();
        for (int i = 0; i < document.getNumberOfPages(); i++) {
            BufferedImage image = pdfRenderer.renderImage(i);
            extractedText.append(tesseract.doOCR(image)).append("\n");
        }
        document.close();
        System.out.println("OCR 提取的文本内容：\n" + extractedText);
    }
}