pdf文件转html（保留文本信息）

1、引入maven依赖 

<dependency>
            <groupId>net.sf.cssbox</groupId>
            <artifactId>pdf2dom</artifactId>
            <version>1.9</version>
        </dependency>

2、java实现

/**
     * pdf转html
     * @param inputFilename pdf文件路径
     * @param outFilename html文件路径
     * @throws IOException
     * @throws ParserConfigurationException
     */
    public static void generateHTMLFromPDF(String inputFilename, String outFilename) throws IOException, ParserConfigurationException {
        PDDocument pdf = PDDocument.load(new File(inputFilename));
        Writer output = new PrintWriter(outFilename, "utf-8");
        PDFDomTree tree = new PDFDomTree();
        tree.writeText(pdf, output);
        output.close();
    }

    /**
     * 测试
     * @param args
     * @throws IOException
     * @throws ParserConfigurationException
     */
    public static void main(String[] args) throws IOException, ParserConfigurationException {
        String input = "C:\\Users\\ysx\\Desktop\\fileTest\\DB521危险化学品企业可查验防护措施管理规范.pdf";
        String output = "C:\\Users\\ysx\\Desktop\\fileTest\\DB521危险化学品企业可查验防护措施管理规范.html";
        PdfUtil.generateHTMLFromPDF(input, output);
    }