2024年3月5日发(作者:)

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】

分类: 毕业设计的问题学习 2011-04-01 18:43 阅读(273) 评论(2) 收藏 举报

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) nnection();// 连接指定的资源

t();// 获取网络输入流

bis = new BufferedInputStream(utStream());

String bodyText = null;

WordExtractor ex = new WordExtractor(bis);

bodyText = t();

ter().write(bodyText);

excel:

BufferedInputStream bis = null;

URL url = null;

HttpURLConnection httpUrl = null; // 建立链接

url = new URL(urlReal);

httpUrl = (HttpURLConnection) nnection();// 连接指定的资源

t();// 获取网络输入流

bis = new BufferedInputStream(utStream());

content = new StringBuffer();

HSSFWorkbook workbook = new HSSFWorkbook(bis);

for (int numSheets = 0; numSheets < berOfSheets(); numSheets++) {

HSSFSheet aSheet = etAt(numSheets);// 获得一个sheet

("/n");

if (null == aSheet) {

continue;

}

for (int rowNum = 0; rowNum <= tRowNum(); rowNum++) {

("/n");

HSSFRow aRow = (rowNum);

if (null == aRow) {

continue;

}

for (short cellNum = 0; cellNum <= tCellNum(); cellNum++) {

HSSFCell aCell = l(cellNum);

if (null == aCell) {

continue;

}

if (lType() == _TYPE_STRING) {

(hStringCellValue()

.getString());

} else if (lType() == _TYPE_NUMERIC) {

boolean b = DateFormatted(aCell);

if (b) {

Date date = eCellValue();

SimpleDateFormat df = new SimpleDateFormat(

"yyyy-MM-dd");

((date));

}

}

}

}

}

ter().write(ng());

ppt:

BufferedInputStream bis = null;

URL url = null;

HttpURLConnection httpUrl = null; // 建立链接

url = new URL(urlReal);

httpUrl = (HttpURLConnection) nnection();// 连接指定的资源

t();// 获取网络输入流

bis = new BufferedInputStream(utStream());

StringBuffer content = new StringBuffer("");

SlideShow ss = new SlideShow(new HSLFSlideShow(bis));

Slide[] slides = des();

for (int i = 0; i < ; i++) {

TextRun[] t = slides[i].getTextRuns();

for (int j = 0; j < ; j++) {

(t[j].getText());

}

(slides[i].getTitle());

}

ter().write(ng());

pdf:

BufferedInputStream bis = null;

URL url = null;

HttpURLConnection httpUrl = null; // 建立链接

url = new URL(urlReal);

httpUrl = (HttpURLConnection) nnection();// 连接指定的资源

t();// 获取网络输入流

bis = new BufferedInputStream(utStream());

PDDocument pdfdocument = null;

PDFParser parser = new PDFParser(bis);

();

pdfdocument = ocument();

ByteArrayOutputStream out = new ByteArrayOutputStream();

OutputStreamWriter writer = new OutputStreamWriter(out);

PDFTextStripper stripper = new PDFTextStripper();

ext(ument(), writer);

();

byte[] contents = Array();

String ts = new String(contents);

ter().write(ts);

txt:

BufferedReader bis = null;

URL url = null;

HttpURLConnection httpUrl = null; // 建立链接

url = new URL(urlReal);

httpUrl = (HttpURLConnection) nnection();// 连接指定的资源

t();// 获取网络输入流

bis = new BufferedReader( new InputStreamReader(utStream()));

StringBuffer buf=new StringBuffer();

String temp;

while ((temp = ne()) != null) {

(temp);

ter().write(temp);

if(()>=1000){

break;

}

}

();