java提取PDF文件文本

package com.example.pdf.util;

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.encryption.InvalidPasswordException;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.pdfbox.text.PDFTextStripperByArea;

import java.io.File;
import java.io.IOException;

public class PDFUtils {
    public static void main(String[] args) {

        File file=new File("D:\\test.pdf");

        try (PDDocument document = PDDocument.load(file)) {

            document.getClass();

            if(!document.isEncrypted()) {
                PDFTextStripperByArea stripper = new PDFTextStripperByArea();
                stripper.setSortByPosition(true);
                PDFTextStripper tStripper = new PDFTextStripper();

                String pdfFileInText = tStripper.getText(document);

                String[] lines = pdfFileInText.split("\\r?\\n");
                for(String line : lines) {
                    System.out.println(line);
                }

            }

        } catch (InvalidPasswordException e) {

            e.printStackTrace();
        } catch (IOException e) {

            e.printStackTrace();
        }

    }
}