java Word转Html
2023-09-11 14:22:24 时间
第一步:maven导入jar包
<dependency> <groupId>org.apache.poi</groupId> <artifactId>poi-scratchpad</artifactId> <version>3.14</version> </dependency> <dependency> <groupId>org.apache.poi</groupId> <artifactId>poi-ooxml</artifactId> <version>3.14</version> </dependency> <dependency> <groupId>fr.opensagres.xdocreport</groupId> <artifactId>xdocreport</artifactId> <version>1.0.6</version> </dependency> <dependency> <groupId>org.apache.poi</groupId> <artifactId>poi-ooxml-schemas</artifactId> <version>3.14</version> </dependency> <dependency> <groupId>org.apache.poi</groupId> <artifactId>ooxml-schemas</artifactId> <version>1.3</version> </dependency> <dependency> <groupId>org.jsoup</groupId> <artifactId>jsoup</artifactId> <version>1.11.3</version> </dependency>
转换方法:
/** * 将word2003转换为html文件 * * @param wordPath word文件路径 * @param wordName word文件名称无后缀 * @param suffix word文件后缀 * @param htmlPath html存储地址 * @throws IOException * @throws TransformerException * @throws ParserConfigurationException */ public static String Word2003ToHtml(String wordPath, String wordName, String suffix, String htmlPath) throws IOException, TransformerException, ParserConfigurationException { String htmlName = wordName + ".html"; final String imagePath = htmlPath + "image" + File.separator; // 判断html文件是否存在 File htmlFile = new File(htmlPath + htmlName); if (htmlFile.exists()) { return htmlFile.getAbsolutePath(); } // 原word文档 final String file = wordPath + File.separator + wordName + suffix; InputStream input = new FileInputStream(new File(file)); HWPFDocument wordDocument = new HWPFDocument(input); WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter( DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument()); // 设置图片存放的位置 wordToHtmlConverter.setPicturesManager(new PicturesManager() { public String savePicture(byte[] content, PictureType pictureType, String suggestedName, float widthInches, float heightInches) { File imgPath = new File(imagePath); if (!imgPath.exists()) {// 图片目录不存在则创建 imgPath.mkdirs(); } File file = new File(imagePath + suggestedName); try { OutputStream os = new FileOutputStream(file); os.write(content); os.close(); } catch (FileNotFoundException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } // 图片在html文件上的路径 相对路径 return "image/" + suggestedName; } }); // 解析word文档 wordToHtmlConverter.processDocument(wordDocument); Document htmlDocument = wordToHtmlConverter.getDocument(); // 生成html文件上级文件夹 File folder = new File(htmlPath); if (!folder.exists()) { folder.mkdirs(); } 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); return htmlFile.getAbsolutePath(); } /** * * 2007版本word转换成html * * @param wordPath word文件路径 * @param wordName word文件名称无后缀 * @param suffix word文件后缀 * @param htmlPath html存储地址 * @return * @throws IOException */ public static String Word2007ToHtml(String wordPath, String wordName, String suffix, String htmlPath) throws IOException { String htmlName = wordName + ".html"; String imagePath = htmlPath + "image" + File.separator; // 判断html文件是否存在 File htmlFile = new File(htmlPath + htmlName); if (htmlFile.exists()) { return htmlFile.getAbsolutePath(); } // word文件 File wordFile = new File(wordPath + File.separator + wordName + suffix); // 1) 加载word文档生成 XWPFDocument对象 InputStream in = new FileInputStream(wordFile); XWPFDocument document = new XWPFDocument(in); // 2) 解析 XHTML配置 (这里设置IURIResolver来设置图片存放的目录) File imgFolder = new File(imagePath); XHTMLOptions options = XHTMLOptions.create(); options.setExtractor(new FileImageExtractor(imgFolder)); // html中图片的路径 相对路径 options.URIResolver(new BasicURIResolver("image")); options.setIgnoreStylesIfUnused(false); options.setFragment(true); // 3) 将 XWPFDocument转换成XHTML // 生成html文件上级文件夹 File folder = new File(htmlPath); if (!folder.exists()) { folder.mkdirs(); } OutputStream out = new FileOutputStream(htmlFile); XHTMLConverter.getInstance().convert(document, out, options); return htmlFile.getAbsolutePath(); }
第三步:具体调用
public static void main(String[] args) { try { Word2007ToHtml("C:\\", "1", ".docx", "c://wordToHtml/"); } catch (Exception e) { e.printStackTrace(); } }
转自:https://blog.csdn.net/weixin_41889524/article/details/88988256
相关文章
- Win10 JAVA安装及环境搭建(windows jdk,windows java环境配置)
- Word处理控件Aspose.Words功能演示:使用 Java 将 Word 文档 (DOC/DOCX) 转换为 HTML
- 【JAVA】Eclipse中开启java和xml智能提示功能(图文,已解决!)
- 重构遗留程序的一次案例学习(java程序)
- ElasticSearch Java API使用
- CSDN日报191029:Java开发需要知道的HTML知识;Rust入坑指南
- 【Java】Eclipse如何创建java项目并运行
- .NET/ASP.NET/C#/WCF/SQL Server/My SQL/Java/JSP/JDBC/Spring/Spring MVC/PHP/Python/Ruby/Shell/Agile/CSS/HTML/HTTP/Unix/Linux大量PDF书籍/电子书籍下载, Effective Java 下载
- Java类的根Object
- Java 设计模式之桥接模式,Java 桥接模式 ,java Bridge Pattern
- 解决各版本安卓读写SD卡的问题-java.io.IOException: Operation not permitted问题(兼容到android13)
- java 正则举例
- (JAVA): 自定义枚举和enum枚举类型------详解。
- Java_类似java.lang.VerifyError: Expecting a stackmap frame at branch target 22 in method的解决方法
- 浅析js前端如何将word文档转为html:docx是怎样存储图片的、Java使用POI如何实现、前端使用Mammoth.js如何实现
- Java实例---flappy-bird实例[最终版]
- java 过滤HTML代码中的标签
- 华为OD机试 -最短木板长度(Java) | 机试题+算法思路+考点+代码解析 【2023】
- 【JAVA】Exception in thread "main" java.lang.NoClassDefFoundError
- Java类加载器的工作原理
- Java上的jQuery?解析HTML利器—Jsoup
- 【JAVA】浅谈java枚举类