java 实现pdf 转word去除水印和去除页数限制

背景

每次下载的pdf文档想转成word文档，都从网上找各种找网址，网上的网址要么存在必须要充值，要么转化效果不好等等问题。作为一个技术人员，所以想能否实现pdf转化为word文档

代码实现

1.1 pom.xml的dependencies引入maven依赖

    <dependency>
        <groupId>org.javassist</groupId>
        <artifactId>javassist</artifactId>
        <version>3.20.0-GA</version>
    </dependency>

    <!-- https://mvnrepository.com/artifact/com.aspose/aspose-pdf -->
    <dependency>
        <groupId>com.aspose</groupId>
        <artifactId>aspose-pdf</artifactId>
        <version>21.8</version>
    </dependency>
    <!-- poi-ooxml是poi的升级版本-->
    <dependency>
        <groupId>org.apache.poi</groupId>
        <artifactId>poi-ooxml</artifactId>
        <version>4.1.2</version>
    </dependency>

1.2 在pom.xml中添加仓库地址

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

2.修改jar

其中jarPath 为下载下来的依赖的jar包地址

package com.example.mycode.utils;

import javassist.*;

import java.io.*;
import java.util.ArrayList;
import java.util.Enumeration;
import java.util.List;
import java.util.jar.JarEntry;
import java.util.jar.JarFile;
import java.util.jar.JarOutputStream;

public class PDFJarCrack {
    public static void main(String[] args) throws Exception {
        String jarPath = "D:\\maven\\maven-Repository\\com\\aspose\\aspose-pdf\\21.8\\aspose-pdf-21.8.jar";
        crack(jarPath);
    }

    private static void crack(String jarName) throws Exception {
        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();
    }
}

执行完成后在jar包的目录下会生成aspose-pdf-21.8.cracked.jar

2.2 修改jar包名称

将原来的aspose-pdf-21.8.jar删除。将步骤2生成的jar更名为aspose-pdf-21.8.jar

2.3 源jar包，执行修改后的jar包也可以在百度云盘中下载

链接：https://pan.baidu.com/s/1P283TlJ4_D4sbxdkqkFxeA?pwd=1h3u
提取码：1h3u

3 编写转化代码

package com.example.mycode.utils;


import java.io.FileOutputStream;
import java.io.IOException;

import com.aspose.pdf.Document;
import com.aspose.pdf.SaveFormat;

public class Pdf2Word {
    public static void main(String[] args) throws IOException {
        pdf2doc("E:\\tmp\\6_自如房屋租赁合同.pdf");
    }

    //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();
        }
    }
}

执行完成后会在同级目录生成word文档。经过比对，转化效果比较好。