java pdf转word 支持图片转换到word（最大程度的解决原PDF）

依赖

  
            org.apache.pdfbox
            pdfbox
            2.0.4
        
        
            net.coobird
            thumbnailator
            0.4.8
        
 
        
            org.apache.poi
            poi
            3.9
        
        
            org.apache.poi
            poi-ooxml
            3.9
        

处理图片的工具-代码

package com.example.pdf.Pdf2wordNew;
 
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.apache.xmlbeans.XmlException;
import org.apache.xmlbeans.XmlToken;
import org.openxmlformats.schemas.drawingml.x2006.main.CTNonVisualDrawingProps;
import org.openxmlformats.schemas.drawingml.x2006.main.CTPositiveSize2D;
import org.openxmlformats.schemas.drawingml.x2006.wordprocessingDrawing.CTInline;
 
import java.io.InputStream;
 
/**
 * @program: pdf
 * @author: xlk
 * @create: 2022-11-21 10:30
 */
public class MyXWPFDocument extends XWPFDocument {
    public MyXWPFDocument(InputStream in) throws Exception {
        super(in);
    }
 
    public MyXWPFDocument() {
        super();
    }
 
    public MyXWPFDocument(OPCPackage pkg) throws Exception {
        super(pkg);
    }
 
    /**
     *  处理图片工具
     * @param id
     * @param width     宽
     * @param height    高
     * @param paragraph 段落
     */
    public void createPicture(int id, int width, int height, XWPFParagraph paragraph) {
        final int EMU = 9525;
        width *= EMU;
        height *= EMU;
        String blipId = getAllPictures().get(id).getPackageRelationship().getId();
        CTInline inline = paragraph.createRun().getCTR().addNewDrawing().addNewInline();
        String picXml = ""
                + ""
                + "   "
                + "      "
                + "         " + "            
                + id
                + "\" name=\"Generated\"/>"
                + "            "
                + "         "
                + "         "
                + "            
                + blipId
                + "\" xmlns:r=\"http://schemas.openxmlformats.org/officeDocument/2006/relationships\"/>"
                + "            "
                + "               "
                + "            "
                + "         "
                + "         "
                + "            "
                + "               "
                + "               
                + width
                + "\" cy=\""
                + height
                + "\"/>"
                + "            "
                + "            "
                + "               "
                + "            "
                + "         "
                + "      "
                + "   " + "";
 
        inline.addNewGraphic().addNewGraphicData();
        XmlToken xmlToken = null;
        try {
            xmlToken = XmlToken.Factory.parse(picXml);
        } catch (XmlException xe) {
            xe.printStackTrace();
        }
        inline.set(xmlToken);
 
        inline.setDistT(0);
        inline.setDistB(0);
        inline.setDistL(0);
        inline.setDistR(0);
 
        CTPositiveSize2D extent = inline.addNewExtent();
        extent.setCx(width);
        extent.setCy(height);
 
        CTNonVisualDrawingProps docPr = inline.addNewDocPr();
        docPr.setId(id);
        docPr.setName("图片名称");
        docPr.setDescr("描述信息");
    }
}

开始转换

package com.example.pdf.Pdf2wordNew;
 
import net.coobird.thumbnailator.Thumbnails;
import org.apache.pdfbox.cos.COSName;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.pdmodel.PDPage;
import org.apache.pdfbox.pdmodel.PDResources;
import org.apache.pdfbox.pdmodel.graphics.image.PDImageXObject;
import org.apache.pdfbox.text.PDFTextStripper;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.apache.poi.xwpf.usermodel.XWPFRun;
 
import javax.imageio.ImageIO;
import java.awt.image.BufferedImage;
import java.io.*;
import java.util.Arrays;
import java.util.Iterator;
import java.util.List;
 
public class Pdf2wordNew {
 
    public static void main(String[] args) throws Exception {
 
        try { 
            
            String pdfFileName = "C:\\Users\\11949\\Desktop\\新建文件夹 (2)\\面试题.pdf";
 
            PDDocument pdf = PDDocument.load(new File(pdfFileName));
            int pageNumber = pdf.getNumberOfPages();
 
            String docFileName = pdfFileName.substring(0, pdfFileName.lastIndexOf(".")) + ".doc";
 
            File file = new File(docFileName);
            if (!file.exists()) {
                file.createNewFile();
            }
            MyXWPFDocument document = new MyXWPFDocument();
            FileOutputStream fos = new FileOutputStream(docFileName);
 
            //提取每一页的图片和文字，添加到 word 中
            for (int i = 0; i < pageNumber; i++) {
                PDPage page = pdf.getPage(i);
                PDResources resources = page.getResources();
                Iterable names = resources.getXObjectNames();
                Iterator iterator = names.iterator();
                while (iterator.hasNext()) {
                    COSName cosName = iterator.next();
                    if (resources.isImageXObject(cosName)) {
                        PDImageXObject imageXObject = (PDImageXObject) resources.getXObject(cosName);
                        File outImgFile = new File("C:\\Users\\11949\\Desktop\\新建文件夹 (2)\\"
                                + System.currentTimeMillis() + ".jpg");
                        Thumbnails.of(imageXObject.getImage()).scale(1).rotate(0).toFile(outImgFile);
                        BufferedImage bufferedImage = ImageIO.read(outImgFile);
                        int width = bufferedImage.getWidth();
                        int height = bufferedImage.getHeight();
                        if (width > 600) {
                            double ratio = Math.round((double) width / 550.0);
                            System.out.println("缩放比ratio：" + ratio);
                            width = (int) (width / ratio);
                            height = (int) (height / ratio);
                        }
                        System.out.println("width: " + width + ",  height: " + height);
                        FileInputStream in = new FileInputStream(outImgFile);
                        byte[] ba = new byte[in.available()];
                        in.read(ba);
                        ByteArrayInputStream byteInputStream = new ByteArrayInputStream(ba);
                        XWPFParagraph picture = document.createParagraph();
                        //添加图片
                        document.addPictureData(byteInputStream, MyXWPFDocument.PICTURE_TYPE_JPEG);
                        //图片大小、位置
                        document.createPicture(document.getAllPictures().size() - 1, width, height, picture);
                    }
                }
                PDFTextStripper stripper = new PDFTextStripper();
                stripper.setSortByPosition(true);
                stripper.setStartPage(i);
                stripper.setEndPage(i);
                //当前页中的文字
                String text = stripper.getText(pdf);
                System.out.println("  ==========  " + text);
                XWPFParagraph textParagraph = document.createParagraph();
                XWPFRun textRun = textParagraph.createRun();
                // 处理换行问题
                if (text.contains("\r\n")) {
                    String[] split = text.split("\r\n");
                    List strsToList1 = Arrays.asList(split);
                    for (String str : strsToList1) {
                        System.out.println(str);
                        textRun.setText(str);
                        textRun.addCarriageReturn();
                    }
                }
//                textRun.setText(text);
                textRun.setFontFamily("仿宋");
                textRun.setFontSize(10);
                //换行
                // 插入换行符
                textParagraph.setWordWrap(true);
            }
            document.write(fos);
            fos.close();
            pdf.close();
            System.out.println("pdf转换解析结束！！----");
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}