java将word转换为html

最新推荐文章于 2023-11-13 17:16:15 发布

只为学习与记录

最新推荐文章于 2023-11-13 17:16:15 发布

阅读量1.4w

点赞数 1

分类专栏： java

本文链接：https://blog.youkuaiyun.com/tangyaliang11/article/details/79007873

版权

java 专栏收录该内容

6 篇文章

订阅专栏

本文介绍了一种使用Java批量将.doc和.docx文件转换为HTML的方法。通过利用Apache POI库，该程序能够读取Word文档，并将其转换为HTML格式，适用于文档格式转换的需求场景。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

	public static void main(String[] args) throws Exception {
		String filePath = "C:/Users/Administrator/Desktop/92个诊疗方案及临床路径/";
		File file = new File(filePath);
		File[] files = file.listFiles();
		String name = null;
		for (File file2 : files) {
			Thread.sleep(500);
			name = file2.getName().substring(0, file2.getName().lastIndexOf("."));
			System.out.println(file2.getName());
			if (file2.getName().endsWith(".docx") || file2.getName().endsWith(".DOCX")) {
				CaseHtm.docx(filePath ,file2.getName(),name +".htm");
			}else{
				CaseHtm.dox(filePath ,file2.getName(),name +".htm");
			}
			
        }
	}
	/**
	 * 转换docx
	 * @param filePath
	 * @param fileName
	 * @param htmlName
	 * @throws Exception
	 */
	public static void docx(String filePath ,String fileName,String htmlName) throws Exception{
		final String file = filePath + fileName;
		File f = new File(file);  
		// ) 加载word文档生成 XWPFDocument对象
		InputStream in = new FileInputStream(f);
		XWPFDocument document = new XWPFDocument(in);
		// ) 解析 XHTML配置 (这里设置IURIResolver来设置图片存放的目录)
		File imageFolderFile = new File(filePath);
		XHTMLOptions options = XHTMLOptions.create().URIResolver(new FileURIResolver(imageFolderFile));
		options.setExtractor(new FileImageExtractor(imageFolderFile));
		options.setIgnoreStylesIfUnused(false);
		options.setFragment(true);
		// ) 将 XWPFDocument转换成XHTML
		OutputStream out = new FileOutputStream(new File(filePath + htmlName));
		XHTMLConverter.getInstance().convert(document, out, options);
	}
	/**
	 * 转换doc
	 * @param filePath
	 * @param fileName
	 * @param htmlName
	 * @throws Exception
	 */
	public static void dox(String filePath ,String fileName,String htmlName) throws Exception{
        final String file = filePath + fileName;
        InputStream input = new FileInputStream(new File(file));
        HWPFDocument wordDocument = new HWPFDocument(input);
        WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
       //解析word文档
       wordToHtmlConverter.processDocument(wordDocument);
       Document htmlDocument = wordToHtmlConverter.getDocument();
       
       File htmlFile = new File(filePath + htmlName);
       OutputStream outStream = new FileOutputStream(htmlFile);

       DOMSource domSource = new DOMSource(htmlDocument);
       StreamResult streamResult = new StreamResult(outStream);

       TransformerFactory factory = TransformerFactory.newInstance();
       Transformer serializer = factory.newTransformer();
       serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
       serializer.setOutputProperty(OutputKeys.INDENT, "yes");
       serializer.setOutputProperty(OutputKeys.METHOD, "html");
       
       serializer.transform(domSource, streamResult);
       outStream.close();
   }

<dependency>
    <groupId>fr.opensagres.xdocreport</groupId>
    <artifactId>fr.opensagres.xdocreport.document</artifactId>
    <version>1.0.5</version>
</dependency>
<dependency>  
    <groupId>fr.opensagres.xdocreport</groupId>  
    <artifactId>org.apache.poi.xwpf.converter.xhtml</artifactId>  
    <version>1.0.5</version>  
</dependency>
    <dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi</artifactId>
    <version>3.12</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-scratchpad</artifactId>
    <version>3.12</version>
</dependency>