java调用POI实现word转HTML.doc

1,导jar包。

2，Word2Html.java
1. package com.poi;  
2. import java.io.BufferedWriter;    
3. import java.io.File;    
4. import java.io.FileInputStream;    
5. import java.io.FileNotFoundException;    
6. import java.io.FileOutputStream;    
7. import java.io.IOException;    
8. import java.io.OutputStream;    
9. import java.io.OutputStreamWriter;    
10. import java.util.List;    
11.     
12. import javax.xml.parsers.DocumentBuilderFactory;    
13. import javax.xml.parsers.ParserConfigurationException;    
14. import javax.xml.transform.OutputKeys;    
15. import javax.xml.transform.Transformer;    
16. import javax.xml.transform.TransformerException;    
17. import javax.xml.transform.TransformerFactory;    
18. import javax.xml.transform.dom.DOMSource;    
19. import javax.xml.transform.stream.StreamResult;    
20.     
21. import mons.io.output.ByteArrayOutputStream;    
22. import org.apache.poi.hwpf.HWPFDocument;    
23. import org.apache.poi.hwpf.converter.PicturesManager;    
24. import org.apache.poi.hwpf.converter.WordToHtmlConverter;    
25. import org.apache.poi.hwpf.model.PicturesTable;    
26. import org.apache.poi.hwpf.usermodel.CharacterRun;    
27. import org.apache.poi.hwpf.usermodel.Paragraph;    
28. import org.apache.poi.hwpf.usermodel.Picture;    
29. import org.apache.poi.hwpf.usermodel.PictureType;    
30. import org.apache.poi.hwpf.usermodel.Range;    
31. import org.apache.poi.hwpf.usermodel.Table;    
32. import org.apache.poi.hwpf.usermodel.TableCell;    
33. import org.apache.poi.hwpf.usermodel.TableIterator;    
34. import org.apache.poi.hwpf.usermodel.TableRow;    
35. import org.w3c.dom.Document;   
36. /**  
37.  * @author: Chembo Huang  
38.  * @since: May 3, 2012  
39.  * @modified: May 3, 2012  
40.  * @version:  
41.  */    
42. public class Word2Html {    
43.     
44.     public static void main(String argv[]) {    
45.         try {    
46.             convert2Html("E://test//33.doc","E://test//abc.html");    
47.         } catch (Exception e) {    
48.             e.printStackTrace();    
49.         }    
50.     }    
51.     
52.     public static void writeFile(String content, String path) {    
53.         FileOutputStream fos = null;    
54.         BufferedWriter bw = null;    
55.         try {    
56.             File file = new File(path);    
57.             fos = new FileOutputStream(file);    
58.             bw = new BufferedWriter(new OutputStreamWriter(fos,"GB2312"));    
59.             bw.write(content);    
60.         } catch (FileNotFoundException fnfe) {    
61.             fnfe.printStackTrace();    
62.         } catch (IOException ioe) {    
63.             ioe.printStackTrace();    
64.         } finally {    
65.             try {    
66.                 if (bw != null)    
67.                     bw.close();    
68.                 if (fos != null)    
69.                     fos.close();    
70.             } catch (IOException ie) {    
71.             }    
72.         }    
73.     }    
74.     
75.     public static void convert2Html(String fileName, String outPutFile)    
76.             throws TransformerException, IOException,    
77.             ParserConfigurationException {    
78.         HWPFDocument wordDocument = new HWPFDocument(new FileInputStream(fileName));//WordToHtmlUtils.loadDoc(new FileInputStream(inputFile));    
79.         WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(    
80.                 DocumentBuilderFactory.newInstance().newDocumentBuilder()    
81.                         .newDocument());    
82.          wordToHtmlConverter.setPicturesManager( new PicturesManager()    
83.          {    
84.              public String savePicture( byte[] content,    
85.                      PictureType pictureType, String suggestedName,    
86.                      float widthInches, float heightInches )    
87.              {    
88.                  return suggestedName;    
89.              }    
90.          } );    
91.         wordToHtmlConverter.processDocument(wordDocument);    
92.         //save pictures    
93.         List pics=wordDocument.getPicturesTable().getAllPictures();    
94.         if(pics!=null){    
95.             for(int i=0;i<pics.size();i++){    
96.                 Picture pic = (Picture)pics.get(i);    
97.                 System.out.println();    
98.                 try {    
99.                     pic.writeImageContent(new FileOutputStream("E:/test/"    
100.                             + pic.suggestFullFileName()));    
101.                 } catch (FileNotFoundException e) {    
102.                     e.printStackTrace();    
103.                 }      
104.             }    
105.         }    
106.         Document htmlDocument = wordToHtmlConverter.getDocument();    
107.         ByteArrayOutputStream out = new ByteArrayOutputStream();    
108.         DOMSource domSource = new DOMSource(htmlDocument);    
109.         StreamResult streamResult = new StreamResult(out);    
110.     
111.         TransformerFactory tf = TransformerFactory.newInstance();    
112.         Transformer serializer = tf.newTransformer();    
113.         serializer.setOutputProperty(OutputKeys.ENCODING, "GB2312");    
114.         serializer.setOutputProperty(OutputKeys.INDENT, "yes");    
115.         serializer.setOutputProperty(OutputKeys.METHOD, "html");    
116.         serializer.transform(domSource, streamResult);    
117.         out.close();    
118.         writeFile(new String(out.toByteArray()), outPutFile);    
119.     }    
120. }