java <em>poi</em>怎么将<em>word</em>转&l

用poi读取 xlsx或者 docx,然后输出成 html文件。

protected void processHyperlink(HWPFDocumentCore wordDocument,
org.w3c.dom.Element currentBlock,
Range textRange,
int currentTableLevel,
java.lang.String hyperlink)

实现代码如下：

public class Word2Html {

	public static void main(String argv[]) {
		7a686964616fe78988e69d83365try {
			//word 路径       html输出路径
			convert2Html("D:/doctohtml/1.doc","D:/doctohtml/1.html");
		} catch (Exception e) {
			e.printStackTrace();
		}
	}

	public static void writeFile(String content, String path) {
		FileOutputStream fos = null;
		BufferedWriter bw = null;
		try {
			File file = new File(path);
			fos = new FileOutputStream(file);
			bw = new BufferedWriter(new OutputStreamWriter(fos,"utf-8"));
			bw.write(content);
		} catch (FileNotFoundException fnfe) {
			fnfe.printStackTrace();
		} catch (IOException ioe) {
			ioe.printStackTrace();
		} finally {
			try {
				if (bw != null)
					bw.close();
				if (fos != null)
					fos.close();
			} catch (IOException ie) {
			}
		}
	}

	public static void convert2Html(String fileName, String outPutFile)
			throws TransformerException, IOException,
			ParserConfigurationException {
		HWPFDocument wordDocument = new HWPFDocument(new FileInputStream(fileName));//WordToHtmlUtils.loadDoc(new FileInputStream(inputFile));
		WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
				DocumentBuilderFactory.newInstance().newDocumentBuilder()
						.newDocument());
		 wordToHtmlConverter.setPicturesManager( new PicturesManager()
         {
             public String savePicture( byte[] content,
                     PictureType pictureType, String suggestedName,
                     float widthInches, float heightInches )
             {
                 //html 中  图片标签中 显示的图片路路径  <img src="d:/test/0.jpg"/>
                 return "d:/doctohtml/"+suggestedName;
             }
         } );
		wordToHtmlConverter.processDocument(wordDocument);
		//save pictures
		List pics=wordDocument.getPicturesTable().getAllPictures();
		if(pics!=null){
			for(int i=0;i<pics.size();i++){
				Picture pic = (Picture)pics.get(i);
				System.out.println();
				try {
					//word中图片的存储路径
					pic.writeImageContent(new FileOutputStream("D:/doctohtml/"
							+ pic.suggestFullFileName()));
				} catch (FileNotFoundException e) {
					e.printStackTrace();
				}  
			}
		}
		Document htmlDocument = wordToHtmlConverter.getDocument();
		ByteArrayOutputStream out = new ByteArrayOutputStream();
		DOMSource domSource = new DOMSource(htmlDocument);
		StreamResult streamResult = new StreamResult(out);

		TransformerFactory tf = TransformerFactory.newInstance();
		Transformer serializer = tf.newTransformer();
		serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
		serializer.setOutputProperty(OutputKeys.INDENT, "yes");
		serializer.setOutputProperty(OutputKeys.METHOD, "html");
		serializer.transform(domSource, streamResult);
		out.close();
		writeFile(new String(out.toByteArray()), outPutFile);
	}
}

Java可以使用这个开源框架，对word进行读取合并等操作，Apache POI是一个开源的利用Java读写Excel、WORD等微软OLE2组件文档的项目。最新的3.5版本e799bee5baa6e997aee7ad94e4b893e5b19e334有很多改进，加入了对采用OOXML格式的Office 2007支持，如xlsx、docx、pptx文档。 示例如下：import org.apache.poi.POITextExtractor;
import org.apache.poi.hwpf.extractor.WordExtractor;
//得到.doc文件提取器
org.apache.poi.hwpf.extractor.WordExtractor doc = new WordExtractor(new FileInputStream(filePath));
//提取.doc正文文本
String text = doc.getText();
//提取.doc批注
String[] comments = doc. getCommentsText();

2007

import org.apache.poi.POITextExtractor;
import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
import org.apache.poi.xwpf.usermodel.XWPFComment;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
//得到.docx文件提取器
org.apache.poi.xwpf.extractor.XWPFWordExtractor docx = new XWPFWordExtractor(POIXMLDocument.openPackage(filePath));
//提取.docx正文文本
String text = docx.getText();
//提取.docx批注
org.apache.poi.xwpf.usermodel.XWPFComment[] comments = docx.getDocument()).getComments();
for(XWPFComment comment:comments){
comment.getId();//提取批注Id
comment.getAuthor();//提取批注修改人
comment.getText();//提取批注内容
}