Java实现PDF转Word

1、引入jar包或依赖

这里用到的是aspose-pdf，这个依赖需要单独配置仓库地址，也可以直接去官网下载jar包

<repositories>
	<repository>
		<id>AsposeJavaAPI</id>
		<name>Aspose Java API</name>
		<url>https://repository.aspose.com/repo/</url>
	</repository>
</repositories>

pom文件详情

<dependencies>
        <dependency>
            <groupId>org.javassist</groupId>
            <artifactId>javassist</artifactId>
            <version>3.20.0-GA</version>
        </dependency>
        <dependency>
            <groupId>com.aspose</groupId>
            <artifactId>aspose-pdf</artifactId>
            <version>22.4</version>
        </dependency>
</dependencies>

不会配置仓库地址的话可以去官网下载jar包，官网链接
下面是百度网盘地址里面有未破解和已破解的jar包自行选择下载
链接：https://pan.baidu.com/s/1K4GIH-WnDPwv5wp5_hFSfQ?pwd=0aib
提取码：0aib

2、破解

找到你的jar包地址，引入依赖的去maven仓库地址找到jar，将地址填入代码中的jarPath，运行Main方法会在jar包统计目录下生成破解的包
aspose-pdf-22.4.cracked.jar,替换掉原来jar包就可以了

public class PDFJarCrack {
    public static void main(String[] args) throws Exception {
        String jarPath = "jar包地址";
        crack(jarPath);
    }
    
    private static void crack(String jarName) {
        try {
            ClassPool.getDefault().insertClassPath(jarName);
            CtClass ctClass = ClassPool.getDefault().getCtClass("com.aspose.pdf.ADocument");
            CtMethod[] declaredMethods = ctClass.getDeclaredMethods();
            int num = 0;
            for (int i = 0; i < declaredMethods.length; i++) {
                if (num == 2) {
                    break;
                }
                CtMethod method = declaredMethods[i];
                CtClass[] ps = method.getParameterTypes();
                if (ps.length == 2
                        && method.getName().equals("lI")
                        && ps[0].getName().equals("com.aspose.pdf.ADocument")
                        && ps[1].getName().equals("int")) {
                    // 最多只能转换4页 处理
                    System.out.println(method.getReturnType());
                    System.out.println(ps[1].getName());
                    method.setBody("{return false;}");
                    num = 1;
                }
                if (ps.length == 0 && method.getName().equals("lt")) {
                    // 水印处理
                    method.setBody("{return true;}");
                    num = 2;
                }
            }
            File file = new File(jarName);
            ctClass.writeFile(file.getParent());
            disposeJar(jarName, file.getParent() + "/com/aspose/pdf/ADocument.class");
        } catch (NotFoundException e) {
            e.printStackTrace();
        } catch (CannotCompileException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }

    }

    private static void disposeJar(String jarName, String replaceFile) {
        List<String> deletes = new ArrayList<>();
        deletes.add("META-INF/37E3C32D.SF");
        deletes.add("META-INF/37E3C32D.RSA");
        File oriFile = new File(jarName);
        if (!oriFile.exists()) {
            System.out.println("######Not Find File:" + jarName);
            return;
        }
        //将文件名命名成备份文件
        String bakJarName = jarName.substring(0, jarName.length() - 3) + "cracked.jar";
        //   File bakFile=new File(bakJarName);
        try {
            //创建文件（根据备份文件并删除部分）
            JarFile jarFile = new JarFile(jarName);
            JarOutputStream jos = new JarOutputStream(new FileOutputStream(bakJarName));
            Enumeration entries = jarFile.entries();
            while (entries.hasMoreElements()) {
                JarEntry entry = (JarEntry) entries.nextElement();
                if (!deletes.contains(entry.getName())) {
                    if (entry.getName().equals("com/aspose/pdf/ADocument.class")) {
                        System.out.println("Replace:-------" + entry.getName());
                        JarEntry jarEntry = new JarEntry(entry.getName());
                        jos.putNextEntry(jarEntry);
                        FileInputStream fin = new FileInputStream(replaceFile);
                        byte[] bytes = readStream(fin);
                        jos.write(bytes, 0, bytes.length);
                    } else {
                        jos.putNextEntry(entry);
                        byte[] bytes = readStream(jarFile.getInputStream(entry));
                        jos.write(bytes, 0, bytes.length);
                    }
                } else {
                    System.out.println("Delete:-------" + entry.getName());
                }
            }
            jos.flush();
            jos.close();
            jarFile.close();
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

    private static byte[] readStream(InputStream inStream) throws Exception {
        ByteArrayOutputStream outSteam = new ByteArrayOutputStream();
        byte[] buffer = new byte[1024];
        int len = -1;
        while ((len = inStream.read(buffer)) != -1) {
            outSteam.write(buffer, 0, len);
        }
        outSteam.close();
        inStream.close();
        return outSteam.toByteArray();
    }
}

控制台输出

3、pdf转word

填入你的pdf地址运行Main方法即可转换为word文档

public class Pdf2Word {
    public static void main(String[] args) throws IOException {
        pdf2doc("pdf地址");
    }
    
    //pdf转doc
    public static void pdf2doc(String pdfPath) {
        long old = System.currentTimeMillis();
        try {
            //新建一个word文档
            String wordPath=pdfPath.substring(0,pdfPath.lastIndexOf("."))+".docx";
            FileOutputStream os = new FileOutputStream(wordPath);
            //doc是将要被转化的word文档
            Document doc = new Document(pdfPath);
            //全面支持DOC, DOCX, OOXML, RTF HTML, OpenDocument, PDF, EPUB, XPS, SWF 相互转换
            doc.save(os, SaveFormat.DocX);
            os.close();
            //转化用时
            long now = System.currentTimeMillis();
            System.out.println("Pdf 转 Word 共耗时：" + ((now - old) / 1000.0) + "秒");
        } catch (Exception e) {
            System.out.println("Pdf 转 Word 失败...");
            e.printStackTrace();
        }
    }
}

控制台输出