Java：使用apache POI如何将ms word文件转换为pdf？

时间：2011-06-01 13:16:03

标签： java itext apache-poi

使用apache POI如何将ms word文件转换为pdf？

我使用下面的代码，但它没有工作给出错误我猜我输入了错误的类？

import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.OutputStream;

import org.apache.poi.hslf.record.Document;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.hwpf.usermodel.Paragraph;
import org.apache.poi.hwpf.usermodel.Range;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;


public class TestCon {

    /**
     * @param args
     */
    public static void main(String[] args) {
        // TODO Auto-generated method stub

        POIFSFileSystem fs = null;  
         Document document = new Document(); 

         try {  
             System.out.println("Starting the test");  
             fs = new POIFSFileSystem(new FileInputStream("/document/test2.doc"));  

             HWPFDocument doc = new HWPFDocument(fs);  
             WordExtractor we = new WordExtractor(doc);  

             OutputStream file = new FileOutputStream(new File("/document/test.pdf")); 

             PdfWriter writer = PdfWriter.getInstance(document, file);  

             Range range = doc.getRange();
             document.open();  
             writer.setPageEmpty(true);  
             document.newPage();  
             writer.setPageEmpty(true);  

             String[] paragraphs = we.getParagraphText();  
             for (int i = 0; i < paragraphs.length; i++) {  

                 org.apache.poi.hwpf.usermodel.Paragraph pr = range.getParagraph(i);
                // CharacterRun run = pr.getCharacterRun(i);
                // run.setBold(true);
                // run.setCapitalized(true);
                // run.setItalic(true);
                 paragraphs[i] = paragraphs[i].replaceAll("\\cM?\r?\n", "");  
             System.out.println("Length:" + paragraphs[i].length());  
             System.out.println("Paragraph" + i + ": " + paragraphs[i].toString());  

             // add the paragraph to the document  
             document.add(new Paragraph(paragraphs[i]));  
             }  

             System.out.println("Document testing completed");  
         } catch (Exception e) {  
             System.out.println("Exception during test");  
             e.printStackTrace();  
         } finally {  
                         // close the document  
            document.close();  
                     }  
         }  
    }

7 个答案:

答案 0 :(得分：10)

解决了它

import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.OutputStream;

import com.lowagie.text.Document;
import com.lowagie.text.DocumentException;
import com.lowagie.text.Paragraph;
import com.lowagie.text.pdf.PdfWriter;


import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.extractor.WordExtractor;

import org.apache.poi.hwpf.usermodel.Range;
import org.apache.poi.poifs.filesystem.POIFSFileSystem;


public class TestCon {

    /**
     * @param args
     */
    public static void main(String[] args) {
        // TODO Auto-generated method stub

        POIFSFileSystem fs = null;  
        Document document = new Document();

         try {  
             System.out.println("Starting the test");  
             fs = new POIFSFileSystem(new FileInputStream("D:/Resume.doc"));  

             HWPFDocument doc = new HWPFDocument(fs);  
             WordExtractor we = new WordExtractor(doc);  

             OutputStream file = new FileOutputStream(new File("D:/test.pdf")); 

             PdfWriter writer = PdfWriter.getInstance(document, file);  

             Range range = doc.getRange();
             document.open();  
             writer.setPageEmpty(true);  
             document.newPage();  
             writer.setPageEmpty(true);  

             String[] paragraphs = we.getParagraphText();  
             for (int i = 0; i < paragraphs.length; i++) {  

                 org.apache.poi.hwpf.usermodel.Paragraph pr = range.getParagraph(i);
                // CharacterRun run = pr.getCharacterRun(i);
                // run.setBold(true);
                // run.setCapitalized(true);
                // run.setItalic(true);
                 paragraphs[i] = paragraphs[i].replaceAll("\\cM?\r?\n", "");  
             System.out.println("Length:" + paragraphs[i].length());  
             System.out.println("Paragraph" + i + ": " + paragraphs[i].toString());  

             // add the paragraph to the document  
             document.add(new Paragraph(paragraphs[i]));  
             }  

             System.out.println("Document testing completed");  
         } catch (Exception e) {  
             System.out.println("Exception during test");  
             e.printStackTrace();  
         } finally {  
                         // close the document  
            document.close();  
                     }  
         }  
    }

答案 1 :(得分：4)

这对我有用： -

来源： - http://www.programcreek.com/java-api-examples/index.php?api=org.apache.poi.xwpf.converter.pdf.PdfConverter 

package pdf;

import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.OutputStream;

import org.apache.poi.xwpf.converter.pdf.PdfConverter;
import org.apache.poi.xwpf.converter.pdf.PdfOptions;
import org.apache.poi.xwpf.usermodel.XWPFDocument;

public class PDF {
    public static void main(String[] args) throws Exception {
          String inputFile="D:/TEST.docx";
          String outputFile="D:/TEST.pdf";
          if (args != null && args.length == 2) {
            inputFile=args[0];
            outputFile=args[1];
          }
          System.out.println("inputFile:" + inputFile + ",outputFile:"+ outputFile);
          FileInputStream in=new FileInputStream(inputFile);
          XWPFDocument document=new XWPFDocument(in);
          File outFile=new File(outputFile);
          OutputStream out=new FileOutputStream(outFile);
          PdfOptions options=null;
          PdfConverter.getInstance().convert(document,out,options);
        }
}

答案 2 :(得分：3)

以下代码对我有用：

Public class DocToPdfConverter{

public static void main(String[] args) {

        String k=null;
        OutputStream fileForPdf =null;
        try {

            String fileName="/document/test2.doc";
            //Below Code is for .doc file 
            if(fileName.endsWith(".doc"))
            {
            HWPFDocument doc = new HWPFDocument(new FileInputStream(
                    fileName));
            WordExtractor we=new WordExtractor(doc);
            k = we.getText();

             fileForPdf = new FileOutputStream(new File(
                        "/document/DocToPdf.pdf")); 
            we.close();
            }

            //Below Code for 

            else if(fileName.endsWith(".docx"))
            {
                XWPFDocument docx = new XWPFDocument(new FileInputStream(
                        fileName));
                // using XWPFWordExtractor Class
                XWPFWordExtractor we = new XWPFWordExtractor(docx);
                 k = we.getText();

                 fileForPdf = new FileOutputStream(new File(
                            "/document/DocxToPdf.pdf"));    
                 we.close();
            }



            Document document = new Document();
            PdfWriter.getInstance(document, fileForPdf);

            document.open();

            document.add(new Paragraph(k));

            document.close();
            fileForPdf.close();



        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}

答案 3 :(得分：2)

这里有几个步骤：

  1. 使用POI将Word文档读入与格式无关的形式
  2. 将与格式无关的表单转换为PDF
  3. 写PDF

    4. 我不知道POI是否会为你做第2步。我推荐别的东西，比如iText。

答案 4 :(得分：2)

作为旁注，还可以直接从Word / Excel内容流中即时阅读内容，而不是从文件系统中读取内容并将其序列化到磁盘，例如从CMIS存储库中检索内容时： / p>

e.g。

 //HWPFDocument docx = new HWPFDocument(fs);  
 HWPFDocument docx = new HWPFDocument(doc.getContentStream().getStream());

（doc的类型为org.apache.chemistry.opencmis.client.api.Document，在这种情况下，我调整了您的代码，以便通过opencmis从Alfresco存储库中检索word文件，并将其转换为PDF格式）

HTH

答案 5 :(得分：2)

除了Kushagra的回答，这里还有更新的maven依赖项：

    <dependency>
        <groupId>fr.opensagres.xdocreport</groupId>
        <artifactId>fr.opensagres.xdocreport.converter.docx.xwpf</artifactId>
        <version>2.0.1</version>
    </dependency>
    <dependency>
        <groupId>fr.opensagres.xdocreport</groupId>
        <artifactId>fr.opensagres.xdocreport.converter</artifactId>
        <version>2.0.1</version>
    </dependency>
    <dependency>
        <groupId>fr.opensagres.xdocreport</groupId>
        <artifactId>fr.opensagres.poi.xwpf.converter.pdf</artifactId>
        <version>2.0.1</version>
    </dependency>
    <dependency>
        <groupId>fr.opensagres.xdocreport</groupId>
        <artifactId>fr.opensagres.poi.xwpf.converter.xhtml</artifactId>
        <version>2.0.1</version>
    </dependency>

答案 6 :(得分：0)

这可以节省我的一天，我从URL加载docx文件并将其转换为pdf：

pom.xml 

<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi</artifactId>
    <version>3.13</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-ooxml</artifactId>
    <version>3.13</version>
</dependency>
<dependency>
    <groupId>fr.opensagres.xdocreport</groupId>
    <artifactId>org.apache.poi.xwpf.converter.pdf</artifactId>
    <version>LATEST</version>
</dependency>

主类 

public String wordToPDFPOI(String url) throws Exception {
    InputStream doc = new URL(url).openStream();
    ByteArrayOutputStream baos = new ByteArrayOutputStream();

    XWPFDocument document = new XWPFDocument(doc);
    PdfOptions options = PdfOptions.create();
    PdfConverter.getInstance().convert(document, baos, options);
    String base64_encoded = Base64.encodeBytes(baos.toByteArray());

    return base64_encoded;
}
相关问题
最新问题