Java实现PDF转为word文档

Java实现PDF转为word文档

具体步骤

1.在自己使用的IDE中创建一个新的.java文件
2.导入操作PDF所需的jar包

需要注意jar包的版本问题,下面是对应的下载链接
commons-logging-1.2.jar
fontbox-2.0.11.jar
pdfbox-2.0.11.jar
https://jar-download.com/artifacts/org.apache.pdfbox/pdfbox/2.0.11/source-code
jbig2-imageio-3.0.1.jar
https://jar-download.com/artifacts/org.apache.pdfbox/jbig2-imageio/3.0.1/source-code
pdfbox-tools-2.0.11.jar
https://jar-download.com/artifacts/org.apache.pdfbox/pdfbox-tools/2.0.11/source-code
3.源代码展示

public static void pdfToWord() throws Exception {
    String pdfFile = "F:/pdfToWord/mnfs.pdf";
    PDDocument doc = PDDocument.load(new File(pdfFile));
    int pagenumber = doc.getNumberOfPages();//获取总页数
    FileOutputStream fos = null;
    try {
        fos = new FileOutputStream(pdfFile.substring(0, pdfFile.indexOf(".")) + ".doc");
    } catch (FileNotFoundException e) {
        e.printStackTrace();
    }
    Writer writer = null;
    try {
        writer = new OutputStreamWriter(fos, "UTF-8");//文件按字节读取，然后按照UTF-8的格式编码显示
    } catch (UnsupportedEncodingException e) {
        e.printStackTrace();
    }
    PDFTextStripper stripper = new PDFTextStripper();//生成PDF文档内容剥离器
    stripper.setSortByPosition(true);//排序
    stripper.setStartPage(1);//设置转换的开始页
    stripper.setEndPage(pagenumber);//设置转换的结束页
    try {
        stripper.writeText(doc, writer);
        writer.close();
        doc.close();
    } catch (IOException e) {
        e.printStackTrace();
    }
}