Java：使用apache POI如何將ms word文件轉換爲pdf？

Question

通過使用apache POI如何將ms word文件轉換爲pdf？

我使用下面的代碼，但它不工作給錯誤我想我導入錯誤的類？

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(); 
        } 
     } 
    } 

Answer 1

得到它解決

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(); 
        } 
     } 
    } 

Answer 2

這裏有幾個步驟：

使用POI成格式無關的形式
1. 轉換格式無關的形式轉換成PDF
2. 閱讀Word文檔
3. 寫PDF

我不知道POI是否會爲你做第2步。我會推薦別的東西，比如iText。

Answer 3

作爲一個側面說明，它也可以閱讀的內容直接從Word/Excel的內容流於即時的，而不是從文件系統讀取它，並將其序列化到磁盤，例如從CMIS存儲庫檢索內容時：

eg

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

（DOC是org.apache.chemistry.opencmis.client.api.Document型的，在這種情況下，我適應您的代碼通過opencmis的方式來檢索的露天倉庫Word文件，並將其轉換爲PDF）

HTH

Answer 4

的下面的代碼爲我工作：

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(); 
     } 
    } 
} 

Answer 5

這爲我工作： -

來源： - 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); 
     } 
}