springboot 文档处理转换 PDF转Word 图片转Word PDF转Excel 图片转Excel PDF转图片 图片转PDF

在Spring Boot中，可以使用一些现有的Java库来处理和转换文档、图片和PDF文件。以下是一些常用的库和示例代码：

1. PDF转Word：
   • 使用Apache PDFBox库来提取PDF中的文本内容，然后使用Apache POI库将文本内容保存为Word文件。

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.apache.poi.xwpf.usermodel.XWPFRun;

import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;

public class PdfToWordConverter {

    public static void convert(String pdfFilePath, String wordFilePath) throws IOException {
        PDDocument document = PDDocument.load(new File(pdfFilePath));
        PDFTextStripper stripper = new PDFTextStripper();

        XWPFDocument wordDocument = new XWPFDocument();
        XWPFParagraph paragraph = wordDocument.createParagraph();
        XWPFRun run = paragraph.createRun();

        run.setText(stripper.getText(document));

        FileOutputStream out = new FileOutputStream(wordFilePath);
        wordDocument.write(out);
        out.close();

        document.close();
        wordDocument.close();

        System.out.println("PDF转Word成功！");
    }
}

2. 图片转Word：
   • 使用Apache POI库来创建一个Word文档，并将图片插入到文档中。

import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFRun;

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

public class ImageToWordConverter {

    public static void convert(String imageFilePath, String wordFilePath) throws IOException {
        XWPFDocument wordDocument = new XWPFDocument();
        XWPFRun run = wordDocument.createParagraph().createRun();

        FileInputStream imageInputStream = new FileInputStream(imageFilePath);
        BufferedImage image = ImageIO.read(imageInputStream);
        imageInputStream.close();

        FileOutputStream out = new FileOutputStream(wordFilePath);
        ImageIO.write(image, "png", out);
        out.close();

        wordDocument.close();

        System.out.println("图片转Word成功！");
    }
}

3. PDF转Excel：
   • 使用Apache PDFBox库来提取PDF中的表格数据，然后使用Apache POI库将表格数据保存为Excel文件。

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.poi.ss.usermodel.*;
import org.apache.poi.xssf.usermodel.XSSFWorkbook;

import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;

public class PdfToExcelConverter {

    public static void convert(String pdfFilePath, String excelFilePath) throws IOException {
        PDDocument document = PDDocument.load(new File(pdfFilePath));
        PDFTextStripper stripper = new PDFTextStripper();

        Workbook workbook = new XSSFWorkbook();
        Sheet sheet = workbook.createSheet();

        int rowIndex = 0;
        for (PDPage page : document.getPages()) {
            stripper.setStartPage(document.getDocumentCatalog().getPages().indexOf(page) + 1);
            stripper.setEndPage(document.getDocumentCatalog().getPages().indexOf(page) + 1);

            String text = stripper.getText(document);
            String[] lines = text.split("\\r?\\n");

            for (int i = 0; i < lines.length; i++) {
                Row row = sheet.createRow(rowIndex++);
                String[] cells = lines[i].split("\\t");
                for (int j = 0; j < cells.length; j++) {
                    Cell cell = row.createCell(j);
                    cell.setCellValue(cells[j]);
                }
            }
        }

        FileOutputStream out = new FileOutputStream(excelFilePath);
        workbook.write(out);
        out.close();

        document.close();
        workbook.close();

        System.out.println("PDF转Excel成功！");
    }
}

4. 图片转Excel：
   • 使用Apache POI库创建一个Excel文件，并将图片插入到Excel文件的单元格中。

import org.apache.poi.ss.usermodel.*;
import org.apache.poi.xssf.usermodel.XSSFWorkbook;

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

public class ImageToExcelConverter {

    public static void convert(String imageFilePath, String excelFilePath) throws IOException {
        Workbook workbook = new XSSFWorkbook();
        Sheet sheet = workbook.createSheet();
        Drawing drawing = sheet.createDrawingPatriarch();
        CreationHelper helper = workbook.getCreationHelper();

        BufferedImage image = ImageIO.read(new File(imageFilePath));
        int pictureIdx = workbook.addPicture(ImageIO.read(new FileInputStream(imageFilePath)), Workbook.PICTURE_TYPE_PNG);

        ClientAnchor anchor = helper.createClientAnchor();
        anchor.setCol1(0);
        anchor.setRow1(0);

        Picture picture = drawing.createPicture(anchor, pictureIdx);
        picture.resize();

        FileOutputStream out = new FileOutputStream(excelFilePath);
        workbook.write(out);
        out.close();

        workbook.close();

        System.out.println("图片转Excel成功！");
    }
}

5. PDF转图片：
   • 使用Apache PDFBox库将PDF转换为一系列图片文件。

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.rendering.PDFRenderer;

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

public class PdfToImageConverter {

    public static void convert(String pdfFilePath, String imageFilePath) throws IOException {
        PDDocument document = PDDocument.load(new File(pdfFilePath));
        PDFRenderer renderer = new PDFRenderer(document);

        for (int i = 0; i < document.getNumberOfPages(); i++) {
            BufferedImage image = renderer.renderImage(i);
            ImageIO.write(image, "png", new File(imageFilePath + "_" + (i + 1) + ".png"));
        }

        document.close();

        System.out.println("PDF转图片成功！");
    }
}

6. 图片转PDF：
   • 使用Apache PDFBox库将图片转换为PDF文件。

import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDPageContentStream;
import org.apache.pdfbox.pdmodel.PDPageContentStream.AppendMode;
import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;

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

public class ImageToPdfConverter {

    public static void convert(String imageFilePath, String pdfFilePath) throws IOException {
        PDDocument document = new PDDocument();
        BufferedImage image = ImageIO.read(new File(imageFilePath));

        PDPage page = new PDPage();
        document.addPage(page);

        PDImageXObject ximage = PDImageXObject.createFromFile(imageFilePath, document);
        PDPageContentStream contentStream = new PDPageContentStream(document, page, AppendMode.APPEND, true, true);

        contentStream.drawImage(ximage, 0, 0, page.getMediaBox().getWidth(), page.getMediaBox().getHeight());
        contentStream.close();

        document.save(pdfFilePath);
        document.close();

        System.out.println("图片转PDF成功！");
    }
}

请注意，以上示例代码仅提供了基本的实现思路和方法，您可能需要根据实际需求进行适当的修改和优化。另外，这些示例代码需要相应的依赖库，请确保在项目中添加了这些库的依赖