java通过url在线预览Word、excel、ppt、pdf、txt文档中的内容【只获得其中的文字】

在页面上显示各种文档中的内容。在servlet中的逻辑

word： 

BufferedInputStream bis = null;
  URL url = null;
  HttpURLConnection httpUrl = null; // 建立链接
  url = new URL(urlReal);
  httpUrl = (HttpURLConnection) url.openConnection();// 连接指定的资源
  httpUrl.connect();// 获取网络输入流
  bis = new BufferedInputStream(httpUrl.getInputStream());

  String bodyText = null;
  WordExtractor ex = new WordExtractor(bis);
  bodyText = ex.getText();
  response.getWriter().write(bodyText);

excel：

BufferedInputStream bis = null;
  URL url = null;
  HttpURLConnection httpUrl = null; // 建立链接
  url = new URL(urlReal);
  httpUrl = (HttpURLConnection) url.openConnection();// 连接指定的资源
  httpUrl.connect();// 获取网络输入流
  bis = new BufferedInputStream(httpUrl.getInputStream());  

content = new StringBuffer();
  HSSFWorkbook workbook = new HSSFWorkbook(bis);
  for (int numSheets = 0; numSheets < workbook.getNumberOfSheets(); numSheets++) {
   HSSFSheet aSheet = workbook.getSheetAt(numSheets);// 获得一个sheet
   content.append("/n");
   if (null == aSheet) {
    continue;
   }
   for (int rowNum = 0; rowNum <= aSheet.getLastRowNum(); rowNum++) {
    content.append("/n");
    HSSFRow aRow = aSheet.getRow(rowNum);
    if (null == aRow) {
     continue;
    }
    for (short cellNum = 0; cellNum <= aRow.getLastCellNum(); cellNum++) {
     HSSFCell aCell = aRow.getCell(cellNum);
     if (null == aCell) {
      continue;
     }
     if (aCell.getCellType() == HSSFCell.CELL_TYPE_STRING) {
      content.append(aCell.getRichStringCellValue()
        .getString());
     } else if (aCell.getCellType() == HSSFCell.CELL_TYPE_NUMERIC) {
      boolean b = HSSFDateUtil.isCellDateFormatted(aCell);
      if (b) {
       Date date = aCell.getDateCellValue();
       SimpleDateFormat df = new SimpleDateFormat(
         "yyyy-MM-dd");
       content.append(df.format(date));
      }
     }
    }
   }
  }
  response.getWriter().write(content.toString());

ppt：

BufferedInputStream bis = null;
  URL url = null;
  HttpURLConnection httpUrl = null; // 建立链接
  url = new URL(urlReal);
  httpUrl = (HttpURLConnection) url.openConnection();// 连接指定的资源
  httpUrl.connect();// 获取网络输入流
  bis = new BufferedInputStream(httpUrl.getInputStream());

StringBuffer content = new StringBuffer("");
  SlideShow ss = new SlideShow(new HSLFSlideShow(bis));
  Slide[] slides = ss.getSlides();
  for (int i = 0; i < slides.length; i++) {
   TextRun[] t = slides[i].getTextRuns();
   for (int j = 0; j < t.length; j++) {
    content.append(t[j].getText());
   }
   content.append(slides[i].getTitle());
  }
  response.getWriter().write(content.toString());

pdf：

BufferedInputStream bis = null;
  URL url = null;
  HttpURLConnection httpUrl = null; // 建立链接
  url = new URL(urlReal);
  httpUrl = (HttpURLConnection) url.openConnection();// 连接指定的资源
  httpUrl.connect();// 获取网络输入流
  bis = new BufferedInputStream(httpUrl.getInputStream());

 PDDocument pdfdocument = null;
  PDFParser parser = new PDFParser(bis);
  parser.parse();
  pdfdocument = parser.getPDDocument();
  ByteArrayOutputStream out = new ByteArrayOutputStream();
  OutputStreamWriter writer = new OutputStreamWriter(out);
  PDFTextStripper stripper = new PDFTextStripper();
  stripper.writeText(pdfdocument.getDocument(), writer);
  writer.close();
  byte[] contents = out.toByteArray();

  String ts = new String(contents);
  response.getWriter().write(ts);

txt：

BufferedReader bis = null;
  URL url = null;
  HttpURLConnection httpUrl = null; // 建立链接
  url = new URL(urlReal);
  httpUrl = (HttpURLConnection) url.openConnection();// 连接指定的资源
  httpUrl.connect();// 获取网络输入流
  bis = new BufferedReader( new InputStreamReader(httpUrl.getInputStream()));

StringBuffer buf=new StringBuffer();
  String temp;
  while ((temp = bis.readLine()) != null) {
   buf.append(temp);
   response.getWriter().write(temp);
   if(buf.length()>=1000){
    break;
   }
  }
  bis.close();