java实现pdf转word，解决个别排版错乱问题

admin管理员组

文章数量:1605134

项目中要实现客户上传完pdf，上传成功后直接就转成word格式的，之前网上一些免费的转出来的word大致还行，但是有些排版就错乱了，如下图:

下面这个是用java改造后的，效果如下，排版整齐，和pdf中的格式基本保持一样

• 下面直接上干货，首先引入maven坐标

<!-- https://mvnrepository/artifact/com.aspose/aspose-pdf -->

<dependency>

<groupId>com.aspose</groupId>

<artifactId>aspose-pdf</artifactId>

<version>21.8</version>

</dependency>

• 然后引入仓库地址

<repositories>

<!--pdf转word仓库地址 -->

<repository>

<id>AsposeJavaAPI</id>

<name>Aspose Java API</name>

<url>https://repository.aspose/repo/</url>

</repository>

</repositories>

• 下来下载依赖包下载到本地仓库

• 第一步生成新的jar包，完整代码如下

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;

/**
 *  pdf 转 word 第一步生成新的jar包
 */

public class PDFJarCrack {

    public static void main(String[] args) throws Exception{
        String jarPath = "D:\\repo\\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")) {
                    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 (Exception 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";
        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 (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();
    }

}

• 第2步pdf转word

import com.aspose.pdf.Document;
import com.aspose.pdf.SaveFormat;
import java.io.FileOutputStream;
import java.io.IOException;

/**
 *  第2步 pdf转word
 */
public class Pdf2Word {

    public static void main(String[] args) throws IOException {
        pdf2doc("D:\\test.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();
        }
    }

}

本文标签： JavaPDFword