Java使用pdfbox进行pdf和图片之间的转换

雨点打透心脏的1/2处 2024-02-20 11:40 75阅读 0赞

### 简介 ###

#### pdfbox是[Apache][]开源的一个项目,支持pdf文档操作功能。   官网地址: [Apache PDFBox | A Java PDF Library][Apache PDFBox _ A Java PDF Library]   支持的功能如下图.   ![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L21pbmcxOTk1MTIyNA_size_16_color_FFFFFF_t_70]引入依赖 ####

<dependency>
                <groupId>org.apache.pdfbox</groupId>
                <artifactId>pdfbox-app</artifactId>
                <version>2.0.19</version>
            </dependency>

### pdf转换成图片 ###

/**
         * 经过测试,dpi为96,100,105,120,150,200中,105显示效果较为清晰,体积稳定,dpi越高图片体积越大,一般电脑显示分辨率为96
         */
        public static final float DEFAULT_DPI = 105;
    
        /**
         * 默认转换的图片格式为jpg
         */
        public static final String DEFAULT_FORMAT = "jpg";
    
    
        /**
         * pdf转换成图片
         *
         * @param pdfPath    pdf文件的路径   例如: D:\\test\\test.pdf (2页)
         * @param targetPath 输出的图片路径        D:\\test\\
         * @return 抽取出来的图片路径数组         Arrays.asList( "D:\\test\\1.jpg","D:\\test\\2.jpg" )
         */
        public static List<String> pdfToManyImage(String pdfPath, String targetPath) {
            File file = new File(pdfPath);
            if (!file.exists()) {
                return null;
            }
            try {
                //加载pdf文件
                PDDocument doc = PDDocument.load(file);
                //读取pdf文件
                PDFRenderer renderer = new PDFRenderer(doc);
                int pageCount = doc.getNumberOfPages();
                List<String> stringList = new ArrayList<>(pageCount);
                String filePath = null;
                BufferedImage image;
                for (int i = 0; i < pageCount; i++) {
                    //96/144/198
                    // Windows native DPI
                    image = renderer.renderImageWithDPI(i, DEFAULT_DPI);
                    // BufferedImage srcImage = resize(image, 240, 240);//产生缩略图
                    filePath = targetPath + (i + 1) + "." + DEFAULT_FORMAT;
                    //保存图片
                    ImageIO.write(image, DEFAULT_FORMAT, new File(filePath));
                    stringList.add(filePath);
                }
                return stringList;
            } catch (IOException e) {
                e.printStackTrace();
                return null;
            }
        }

### 图片合成pdf ###

/**
         * 多图片合成pdf的限制后缀
         */
        private static final List IMAGE_SUFFIX = Arrays.asList("jpg", "png", "jpeg");
       /**
         * 多个图片合成一个pdf
         *
         * @param imgFolder 多图片的文件夹路径  例如:"D:\\image\\"
         * @param target    合并的图片路径          "D:\\image\\merge.pdf"
         * @throws IOException
         */
        public static void manyImageToOnePdf(String imgFolder, String target) throws IOException {
            PDDocument doc = new PDDocument();
            //创建一个空的pdf文件
            doc.save(target);
            
            PDPage page;
            PDImageXObject pdImage;
            PDPageContentStream contents;
            BufferedImage bufferedImage;
            String fileName;
            float w, h;
            String suffix;
            File tempFile;
            int index;
    		
    		File folder = new File(imgFolder);
            for (int i = 0; i < folder.listFiles().length; i++) {
                tempFile = folder.listFiles()[i];
                if (!tempFile.isFile()) {
                    continue;
                }
    
                fileName = tempFile.getName();
                index = fileName.lastIndexOf(".");
                if (index == -1) {
                    continue;
                }
                //获取文件的后缀
                suffix = fileName.substring(index + 1);
                //如果文件后缀不是图片格式,跳过当前循环
                if (!IMAGE_SUFFIX.contains(suffix)) {
                    continue;
                }
                
                bufferedImage = ImageIO.read(folder.listFiles()[i]);
                //Retrieving the page
                pdImage = LosslessFactory.createFromImage(doc, bufferedImage);
                w = pdImage.getWidth();
                h = pdImage.getHeight();
                page = new PDPage(new PDRectangle(w, h));
                contents = new PDPageContentStream(doc, page);
                contents.drawImage(pdImage, 0, 0, w, h);
                System.out.println("Image inserted");
                contents.close();
                doc.addPage(page);
            }
            //保存pdf
            doc.save(target);
            //关闭pdf
            doc.close();
        }

### 多个pdf合成1个pdf ###

/**
         * pdf合并拼接
         *
         * @param files      pdf文件列表    例如:  Arrays.asList(new File("D:\\1.pdf"),new File("D:\\2.pdf"))
         * @param targetPath 合并后的文件         D:\\merge.pdf
         * @return 合并后的文件File对象
         */
        public static File manyPdfToOne(List<File> files, String targetPath) {
            try {
                PDFMergerUtility mergePdf = new PDFMergerUtility();
                for (File f : files) {
                    if (f.exists() && f.isFile()) {
                        // 循环添加要合并的pdf
                        mergePdf.addSource(f);
                    }
                }
                // 设置合并生成pdf文件名称
                mergePdf.setDestinationFileName(targetPath);
                // 合并pdf
                mergePdf.mergeDocuments(MemoryUsageSetting.setupMainMemoryOnly());
                return new File(targetPath);
            } catch (Exception e) {
                return null;
            }
        }

[Apache]: https://so.csdn.net/so/search?q=Apache&spm=1001.2101.3001.7020
[Apache PDFBox _ A Java PDF Library]: https://pdfbox.apache.org/
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L21pbmcxOTk1MTIyNA_size_16_color_FFFFFF_t_70]: https://img-blog.csdnimg.cn/20210118125936411.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L21pbmcxOTk1MTIyNA==,size_16,color_FFFFFF,t_70