java pdf转word,没页数限制,去除水印

1、pom.xml的依赖引入


        org.javassist
        javassist
        3.20.0-GA
    

    
    
        com.aspose
        pdf2word
        1
    

 依赖包下载:

链接: https://pan.baidu.com/s/15l_Zcw1uOIhFrahUuKF3lA

提取码: hnt9

2、Java代码


import com.aspose.pdf.Document;
import com.aspose.pdf.SaveFormat;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.apache.poi.xwpf.usermodel.XWPFParagraph;
import org.apache.poi.xwpf.usermodel.XWPFRun;

import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.util.List;

public class PdfTest {
    public static void main(String[] args) {
        pdf2doc("***\\企业级数据治理平台_安装手册_V1.1(1).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("."))+".doc";
            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();
            //去除水印
            removeWatermark(new File(wordPath));
            //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();
        }
    }

    //移除文字水印
    public static boolean removeWatermark(File file) {
        try {
            XWPFDocument doc = new XWPFDocument(new FileInputStream(file));
            // 段落
            List paragraphs = doc.getParagraphs();
            for (XWPFParagraph paragraph : paragraphs) {
                String text=paragraph.getText();
                if("Evaluation Only. Created with Aspose.PDF. Copyright 2002-2021 Aspose Pty Ltd.".equals(text)){
                    List runs = paragraph.getRuns();
                    runs.forEach(e-> e.setText("",0));
                }
            }
            FileOutputStream outStream = new FileOutputStream(file);
            doc.write(outStream);
            outStream.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return true;
    }
}

你可能感兴趣的:(java,pdf,word)