Java如何實現Word/Pdf/TXT轉html

這篇文章給大家分享的是有關Java如何實現Word/Pdf/TXT轉html的內容。小編覺得挺實用的，因此分享給大家做個參考，一起跟隨小編過來看看吧。

一:Java實現將word轉換為html

1:引入依賴

 <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:代碼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 轉換成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("甲骨文考證.doc");
    wt.Word2007ToHtml("甲骨文考證.docx");

  }
    
   /**
   * 2003版本word轉換成html
   * @throws IOException
   * @throws TransformerException
   * @throws ParserConfigurationException
    */
  public void Word2003ToHtml(String fileName) throws IOException, TransformerException, ParserConfigurationException {
    
     final String imagepath = STORAGEPATH+"fileImage/";//解析時候如果doc文件中有圖片 圖片會保存在此路徑
    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());
    //設置圖片存放的位置
    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()){//圖片目錄不存在則創建
          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文檔
    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文件路徑:"+ "http://"+IP+":"+PORT+"//uploadFile/"+strRanString+htmlName);
   }
   /**
   * 2007版本word轉換成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) 加載word文檔生成 XWPFDocument對象 
           InputStream in = new FileInputStream(f); 
           XWPFDocument document = new XWPFDocument(in); 
           // 2) 解析 XHTML配置 (這里設置IURIResolver來設置圖片存放的目錄) 
           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) 將 XWPFDocument轉換成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路徑:"+"http://"+IP+":"+PORT+"//uploadFile/"+strRanString+htmlName);
         } catch (Exception e) {
           e.printStackTrace();
         }
       } else { 
         System.out.println("Enter only MS Office 2007+ files"); 
       } 
     } 
   } 
   /**
   *功能說明:生成時間戳
   *創建人:zsq
   *創建時間: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實現將Pdf轉換為html

1: 引入依賴

 <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:代碼Demo

 public class PdfToHtml { 
  /*
   pdf轉換html
   */
   public void pdfToHtmlTest(String inPdfPath,String outputHtmlPath) {
     // String outputPath = "C:\\works\\files\\ZSQ保密知識測試題庫.html";
       //try() 寫在()里面會自動關閉流
     try{
       BufferedWriter out = new BufferedWriter(new OutputStreamWriter(new FileOutputStream(new File(outputHtmlPath)),"utf-8"));
       //加載PDF文檔
       //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實現將TXT轉換為html

 /*
    * txt文檔轉html
     filePath:txt原文件路徑
     htmlPosition:轉化后生成的html路徑
   */
   public static void txtToHtml(String filePath, String htmlPosition) {
     try {
       //String encoding = "GBK";
       File file = new File(filePath);
       if (file.isFile() && file.exists()) { // 判斷文件是否存在
         InputStreamReader read = new InputStreamReader(new FileInputStream(file), "GBK");
         // 考慮到編碼格式
         BufferedReader bufferedReader = new BufferedReader(read);
         // 寫文件
         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("  "+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("讀取文件內容出錯");
       e.printStackTrace();
     }
   }

感謝各位的閱讀！關于“Java如何實現Word/Pdf/TXT轉html”這篇文章就分享到這里了，希望以上內容可以對大家有一定的幫助，讓大家可以學到更多知識，如果覺得文章不錯，可以把它分享出去讓更多的人看到吧！