java 实现word，excel，pdf等转html（还有其他的）

最新推荐文章于 2024-08-22 17:10:27 发布

車先生

最新推荐文章于 2024-08-22 17:10:27 发布

阅读量695

点赞数 8

文章标签： word pdf

本文链接：https://blog.csdn.net/Hduebbs/article/details/136538171

版权

不要看网上博主写了很多行，这个价包三行搞定转换

这个网站详细的讲解了如何使用

https://www.e-iceblue.cn/spiredocforjavaconversion/convert-word-to-html-using-java.html

但是其中pdf转html，其中样式有部分丢失，表格横线竖线丢失了，建议使用如下方法

        <dependency>
            <groupId>org.apache.pdfbox</groupId>
            <artifactId>pdfbox</artifactId>
            <version>2.0.24</version>
        </dependency>

    public static void main(String[] args) throws IOException {

        String pdfFilePath = "D:\\your.pdf";

        //传入PDF地址
        PdfToImage(pdfFilePath);

    }

 public static void PdfToImage(String pdfurl) {
        StringBuffer buffer = new StringBuffer();
        FileOutputStream fos;
        PDDocument document;
        File pdfFile;
        int size;
        BufferedImage image;
        FileOutputStream out;
        Long randStr = 0l;
        //PDF转换成HTML保存的文件夹
        String path = "D:\\image";
        File htmlsDir = new File(path);
        if (!htmlsDir.exists()) {
            htmlsDir.mkdirs();
        }
        File htmlDir = new File(path + "/");
        if (!htmlDir.exists()) {
            htmlDir.mkdirs();
        }
        try {
            //遍历处理pdf附件
            randStr = System.currentTimeMillis();
            buffer.append("<!doctype html>\r\n");
            buffer.append("<head>\r\n");
            buffer.append("<meta charset=\"UTF-8\">\r\n");
            buffer.append("</head>\r\n");
            buffer.append("<body style=\"background-color:gray;\">\r\n");
            buffer.append("<style>\r\n");
            buffer.append("img {background-color:#fff; text-align:center; width:100%; max-width:100%;margin-top:6px;}\r\n");
            buffer.append("</style>\r\n");
            document = new PDDocument();
            //pdf附件
            pdfFile = new File(pdfurl);
            document = PDDocument.load(pdfFile, (String) null);
            size = document.getNumberOfPages();
            Long start = System.currentTimeMillis(), end = null;
            System.out.println("===>pdf : " + pdfFile.getName() + " , size : " + size);
            PDFRenderer reader = new PDFRenderer(document);
            for (int i = 0; i < size; i++) {
                //image = newPDFRenderer(document).renderImageWithDPI(i,130,ImageType.RGB);
                image = reader.renderImage(i, 1.5f);
                //生成图片,保存位置
                out = new FileOutputStream(path + "/" + "image" + "_" + i + ".jpg");
                ImageIO.write(image, "png", out); //使用png的清晰度
                //将图片路径追加到网页文件里
                buffer.append("<img src=\"" + path + "/" + "image" + "_" + i + ".jpg\"/>\r\n");
                image = null;
                out.flush();
                out.close();
            }
            reader = null;
            document.close();
            buffer.append("</body>\r\n");
            buffer.append("</html>");
            end = System.currentTimeMillis() - start;
            System.out.println("===> Reading pdf times: " + (end / 1000));
            start = end = null;
            //生成网页文件
            fos = new FileOutputStream(path + randStr + ".html");
            System.out.println(path + randStr + ".html");
            fos.write(buffer.toString().getBytes());
            fos.flush();
            fos.close();
            buffer.setLength(0);


        } catch (Exception e) {
            System.out.println("===>Reader parse pdf to jpg error : " + e.getMessage());
            e.printStackTrace();
        }
    }

小伙伴们，点赞加收藏