PDF转word

子午谷2024-03-03 17:53

一、引入maven依赖

shell 复制代码

<dependency>
	<groupId>com.aspose</groupId>
	<artifactId>aspose-pdf</artifactId>
	<version>22.10</version>
</dependency>

二、核心代码

java 复制代码

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

/**
 * @author ：jerry
 * @date ：Created in 2022/11/15 19:00
 * @description：PDF转word
 * @version: V1.1
 */
public class PdfWord {

  //测试
    public static void main(String[] args) throws IOException {
        pdfDoc("/Users/jerry/Downloads/考研背景知识盘点（政英数）.pdf", ".DOCX");

    }
  
    //pdf转doc
    public static String pdfDoc(String pdfPath, String fileFormatValue) {
        String wordPath = pdfPath.substring(0, pdfPath.lastIndexOf(".")) + fileFormatValue;
        try {
            //新建一个word文档
            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.setPageInfo(new PageInfo());
            doc.save(os, getTypes(fileFormatValue));
            os.close();
            //转化用时

        } catch (Exception e) {
            System.out.println("Pdf 转 Word 失败...");
            e.printStackTrace();
        }
        return wordPath;
    }

    public static SaveFormat getTypes(String fileFormatValue) {
        SaveFormat docX = SaveFormat.DocX;
        switch (fileFormatValue) {
            //docX
            case ".DOCX":
                //黄金
                docX = SaveFormat.DocX;
                break;
            case ".PDF":
                //Pdf
                docX = SaveFormat.Pdf;
                break;
            case ".Html":
                //Html
                docX = SaveFormat.Html;
                break;
            case ".Xml":
                //Xml
                docX = SaveFormat.Xml;
                break;
            case ".XPS":
                //XPS
                docX = SaveFormat.Xps;
                break;
            case ".Excel":
                //Excel
                docX = SaveFormat.Excel;
                break;
            case ".svg":
                //Excel
                docX = SaveFormat.Svg;
                break;
            default:
                //普通会员
                docX = SaveFormat.Doc;
        }
        return docX;
    }
}

注意事项:

1.有时候报错,可能是因为本机缺少相应的字体包,直接去字体网站 (https://cn.ffonts.net/)下载字体,放入本机的系统字体目录即可.