解决 pdfbox 转图片出现图片元素丢失

 解决问题1：引入包

        <!-- pdf工具 -->
        <dependency>
                <groupId>org.apache.pdfbox</groupId>
            <artifactId>pdfbox</artifactId>
        </dependency>
        <dependency>   
		  <groupId>org.apache.pdfbox</groupId>   
		  <artifactId>fontbox</artifactId>   
		</dependency>
        
        <!-- 解决图片丢失 -->
		<dependency>   
			<groupId>com.github.jai-imageio</groupId>
    		<artifactId>jai-imageio-jpeg2000</artifactId>
    		<version>1.4.0</version>
		</dependency>

2、代码示例

/**
	 * 将pdf指定页转换为图片
	 * @param imagePath 保存到图片
	 * @param pdfUrl pdf地址
     * @param dpi 转换质量，越大质量越好，最好不超过200
	 * @param page 指定页码，从1 开始
	 * @param imgType jpg/png
	 * @throws IOException
	 */
public static boolean PDFToImg(String imagePath, String pdfUrl, int dpi, int page, String imgType){
		boolean result = false;
		File imgFile = new File(imagePath);
		File file = new File(pdfUrl);
		/* dpi越大转换后越清晰，相对转换速度越慢 */
		try(FileImageOutputStream imageOutput = new FileImageOutputStream(imgFile);
				FileInputStream inputStream = new FileInputStream(file);
				PDDocument pdDocument = PDDocument.load(inputStream);) {
			PDFRenderer renderer = new PDFRenderer(pdDocument);
			int pages = pdDocument.getNumberOfPages();
			if (page <= pages && page > 0) {
				BufferedImage bufferedImage = renderer.renderImageWithDPI(page-1,dpi);
				ImageIO.write(bufferedImage, imgType, imageOutput);
			}
			result = true;
		} catch (Exception e) {
    		log.error(e.getMessage(),e);
		}
		return result;
	}

调用：
//dpi最好不超过200
boolean r = FileUtil.PDFToImg("D:/WORK/data/recog/cut_pdf/145c2cf0cc2447ff91e65a6fdb41b29b-1.png", "D:/WORK/data/recog/cut_pdf/145c2cf0cc2447ff91e65a6fdb41b29b-1.pdf", 200, 1, "png");