Java实现Word/Pdf/TXT转html

引言:

最近公司在做一个教育培训学习及在线考试的项目,本人主要从事网络课程模块,主要做课程分类,课程,课件的创建及在线学习和统计的功能,因为课件涉及到多种类型,像视频,音频,图文,外部链接及文档类型.其中就涉及到一个问题,就是文档型课件课程在网页上的展示和学习问题,因为要在线统计学习的课程,学习的人员,学习的时长,所以不能像传统做法将文档下载到本地学习,那样就不受系统控制了,所以最终的方案是,在上传文档型课件的时候,将其文件对应的转换成HTML文件,以便在网页上能够浏览学习

下边主要针对word,pdf和txt文本文件进行转换

一:Java实现将word转换为html

   1:引入依赖

 <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>

2:代码demo

 package com.svse.controller;

 import javax.xml.parsers.DocumentBuilderFactory;
 import javax.xml.parsers.ParserConfigurationException;
 import javax.xml.transform.OutputKeys;
 import javax.xml.transform.Transformer;
 import javax.xml.transform.TransformerException;
 import javax.xml.transform.TransformerFactory;
 import javax.xml.transform.dom.DOMSource;
 import javax.xml.transform.stream.StreamResult;

 import org.apache.poi.hwpf.HWPFDocument;
 import org.apache.poi.hwpf.converter.PicturesManager;
 import org.apache.poi.hwpf.converter.WordToHtmlConverter;
 import org.apache.poi.hwpf.usermodel.PictureType;
 import org.apache.poi.xwpf.converter.core.BasicURIResolver;
 import org.apache.poi.xwpf.converter.core.FileImageExtractor;
 import org.apache.poi.xwpf.converter.core.FileURIResolver;
 import org.apache.poi.xwpf.converter.core.IURIResolver;
 import org.apache.poi.xwpf.converter.core.IXWPFConverter;
 import org.apache.poi.xwpf.converter.xhtml.XHTMLConverter;
 import org.apache.poi.xwpf.converter.xhtml.XHTMLOptions;
 import org.apache.poi.xwpf.usermodel.XWPFDocument;
 /**
  * word 转换成html
  */
 public class TestWordToHtml {

     public static  final String STORAGEPATH="C://works//files//";
     public static  final String IP="192.168.30.222";
     public static  final String PORT="8010";
     public static void main(String[] args) throws IOException, TransformerException, ParserConfigurationException {
         TestWordToHtml wt=new TestWordToHtml();
         //wt.Word2003ToHtml("甲骨文考证.doc");
         wt.Word2007ToHtml("甲骨文考证.docx");

     }

      /**
      * 2003版本word转换成html
      * @throws IOException
      * @throws TransformerException
      * @throws ParserConfigurationException
      */
     public void Word2003ToHtml(String fileName) throws IOException, TransformerException, ParserConfigurationException {

         final String imagepath = STORAGEPATH+"fileImage/";//解析时候如果doc文件中有图片  图片会保存在此路径
         final String strRanString=getRandomNum();
         String filepath =STORAGEPATH;
         String htmlName =fileName.substring(0, fileName.indexOf("."))+ "2003.html";
         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());
         //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 +strRanString+suggestedName);
                 try {
                     OutputStream os = new FileOutputStream(file);
                     os.write(content);
                     os.close();
                 } catch (FileNotFoundException e) {
                     e.printStackTrace();
                 } catch (IOException e) {
                     e.printStackTrace();
                 }

                 return  "http://"+IP+":"+PORT+"//uploadFile/fileImage/"+strRanString+suggestedName;
                // return imagepath +strRanString+suggestedName;
             }
         });

         //解析word文档
         wordToHtmlConverter.processDocument(wordDocument);
         Document htmlDocument = wordToHtmlConverter.getDocument();

         File htmlFile = new File(filepath +strRanString+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();

         System.out.println("生成html文件路径:"+ "http://"+IP+":"+PORT+"//uploadFile/"+strRanString+htmlName);
     }

     /**
      * 2007版本word转换成html
      * @throws IOException
      */
     public void Word2007ToHtml(String fileName) throws IOException {

        final String strRanString=getRandomNum();

         String filepath = STORAGEPATH+strRanString;
         String htmlName =fileName.substring(0, fileName.indexOf("."))+ "2007.html";
         File f = new File(STORAGEPATH+fileName);
         if (!f.exists()) {
             System.out.println("Sorry File does not Exists!");
         } else {
             if (f.getName().endsWith(".docx") || f.getName().endsWith(".DOCX")) {
                 try {
                     // 1) 加载word文档生成 XWPFDocument对象
                     InputStream in = new FileInputStream(f);
                     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 imageFolderFile = new File(filepath);
                     XHTMLOptions options = XHTMLOptions.create().URIResolver(new FileURIResolver(imageFolderFile));
                     options.setExtractor(new FileImageExtractor(imageFolderFile));
                     options.URIResolver(new IURIResolver() {
                         public String resolve(String uri) {
                             //http://192.168.30.222:8010//uploadFile/....
                             return "http://"+IP+":"+PORT+"//uploadFile/"+strRanString +"/"+ uri;
                         }
                     });

                     options.setIgnoreStylesIfUnused(false);
                     options.setFragment(true);  

                     // 3) 将 XWPFDocument转换成XHTML
                     OutputStream out = new FileOutputStream(new File(filepath + htmlName));
                     IXWPFConverter<XHTMLOptions> converter = XHTMLConverter.getInstance();
                     converter.convert(document,out, options);
                     //XHTMLConverter.getInstance().convert(document, out, options);
                     System.out.println("html路径:"+"http://"+IP+":"+PORT+"//uploadFile/"+strRanString+htmlName);
                 } catch (Exception e) {
                     e.printStackTrace();
                 }

             } else {
                 System.out.println("Enter only MS Office 2007+ files");
             }
         }
     }  

      /**
      *功能说明:生成时间戳
      *创建人:zsq
      *创建时间:2019年12月7日 下午2:37:09
      *
      */
      public static String getRandomNum(){
          Date dt = new Date();
          SimpleDateFormat sdf = new SimpleDateFormat("yyyyMMddHHmmss");
          String str=sdf.format(dt);
          return str;
      }

    } 

二:Java实现将Pdf转换为html

  1: 引入依赖

 <dependency>
             <groupId>net.sf.cssbox</groupId>
             <artifactId>pdf2dom</artifactId>
             <version>1.7</version>
         </dependency>
         <dependency>
             <groupId>org.apache.pdfbox</groupId>
             <artifactId>pdfbox</artifactId>
             <version>2.0.12</version>
         </dependency>
         <dependency>
             <groupId>org.apache.pdfbox</groupId>
             <artifactId>pdfbox-tools</artifactId>
             <version>2.0.12</version>
  </dependency>
         

2:代码Demo

 public class PdfToHtml {

   /*
     pdf转换html
      */
     public void pdfToHtmlTest(String inPdfPath,String outputHtmlPath)  {
        // String outputPath = "C:\\works\\files\\ZSQ保密知识测试题库.html";
            //try() 写在()里面会自动关闭流
         try{
             BufferedWriter out = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(new File(outputHtmlPath)),"utf-8"));
             //加载PDF文档
             //PDDocument document = PDDocument.load(bytes);
             PDDocument document = PDDocument.load(new File(inPdfPath));
             PDFDomTree pdfDomTree = new PDFDomTree();
             pdfDomTree.writeText(document,out);
         } catch (Exception e) {
             e.printStackTrace();
         }
     }

     public static void main(String[] args) throws IOException {
         PdfToHtml ph=new PdfToHtml();
         String pdfPath="C:\\works\\files\\武研中心行政考勤制度.pdf";
         String outputPath="C:\\works\\files\\武研中心行政考勤制度.html";
         ph.pdfToHtmlTest(pdfPath,outputPath);
   }

 }

三:Java实现将TXT转换为html

  /*
      * txt文档转html
        filePath:txt原文件路径
        htmlPosition:转化后生成的html路径
     */
     public static void txtToHtml(String filePath, String htmlPosition) {
         try {
             //String encoding = "GBK";
             File file = new File(filePath);
             if (file.isFile() && file.exists()) { // 判断文件是否存在
                 InputStreamReader read = new InputStreamReader(new FileInputStream(file), "GBK");
                 // 考虑到编码格式
                 BufferedReader bufferedReader = new BufferedReader(read);
                 // 写文件
                 FileOutputStream fos = new FileOutputStream(new File(htmlPosition));
                 OutputStreamWriter osw = new OutputStreamWriter(fos, "GBK");
                 BufferedWriter bw = new BufferedWriter(osw);
                 String lineTxt = null;
                 while ((lineTxt = bufferedReader.readLine()) != null) {
                     bw.write("&nbsp&nbsp&nbsp"+lineTxt + "</br>");
                 }
                 bw.close();
                 osw.close();
                 fos.close();
                 read.close();
             } else {
                 System.out.println("找不到指定的文件");
             }
         } catch (Exception e) {
             System.out.println("读取文件内容出错");
             e.printStackTrace();
         }
     }