- 浏览: 31017 次
- 性别:
- 来自: 沈阳
最新评论
/**
* 读取word2003
*/
public String readExtDocContent(String fileName){
// 创建输入流读取DOC文件
InputStream in = null;
WordExtractor extractor = null;
String text = null;
try {
in = new FileInputStream(new File(fileName));
extractor = new WordExtractor(in);
text = extractor.getText();
} catch (FileNotFoundException e) {
e.printStackTrace();
}catch (IOException e) {
e.printStackTrace();
} finally{
try {
if(in != null){
in.close();
}
} catch (IOException e) {
e.printStackTrace();
}
}
return text;
}
/**
* 读取word2007-2013
*/
public String readExtDocxContent(String fileName){
// 创建输入流读取DOC文件
String text = null;
OPCPackage opcPackage = null;
try {
opcPackage = POIXMLDocument.openPackage(fileName);
XWPFDocument xwpf = new XWPFDocument(opcPackage);
POIXMLTextExtractor ex = new XWPFWordExtractor(xwpf);
text = ex.getText();
} catch (Exception e) {
e.printStackTrace();
log.error("转换word异常:" + e);
} finally{
try {
if(opcPackage != null){
opcPackage.close();
}
} catch (IOException e) {
e.printStackTrace();
}
}
return text;
}
/**
* 读取Excel2003
*/
public String readExtXlsContent(String fileName){
String content = "";
try {
HSSFWorkbook workbook = new HSSFWorkbook(new FileInputStream(fileName));
ExcelExtractor extractor = new ExcelExtractor(workbook);
extractor.setFormulasNotResults(true);
extractor.setIncludeSheetNames(false);
content = extractor.getText();
log.debug("content:" + content);
} catch (Exception e) {
e.printStackTrace();
return "";
}
return content;
}
/**
* 读取Excel2007+
*/
public String readExtXlsxContent(String fileName){
String content = "";
try {
XSSFWorkbook workbook = new XSSFWorkbook(new FileInputStream(fileName));
XSSFExcelExtractor extractor = new XSSFExcelExtractor(workbook);
extractor.setFormulasNotResults(true);
extractor.setIncludeSheetNames(false);
content = extractor.getText();
} catch (Exception e) {
e.printStackTrace();
return "";
}
return content;
}
/**
* 读取ppt2003
*/
public String readExtPptContent(String fileName){
String text = "";
try {
SlideShow ss = new SlideShow(new HSLFSlideShow(new FileInputStream(fileName)));
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++) {
text += t[j].getText();
}
}
} catch (Exception e) {
e.printStackTrace();
}
return text;
}
/**
* 读取ppt2007+
*/
public String readExtPptxContent(String fileName){
String text = "";
XMLSlideShow xmlslideshow = null;
try {
xmlslideshow = new XMLSlideShow(new FileInputStream(fileName));
XSLFPowerPointExtractor ppt = new XSLFPowerPointExtractor(xmlslideshow);
text= ppt.getText();
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
return text;
}
/**
* 读取pdf
*/
public String readExtPDFContent(String fileName){
String text = "";
try {
PDFParser parser = new PDFParser(new FileInputStream(fileName));
parser.parse();
PDFTextStripper stripper = new PDFTextStripper();
text = stripper.getText(parser.getPDDocument());
parser.getPDDocument().close();
} catch (Exception e) {
e.printStackTrace();
return "";
}
return text;
}
* 读取word2003
*/
public String readExtDocContent(String fileName){
// 创建输入流读取DOC文件
InputStream in = null;
WordExtractor extractor = null;
String text = null;
try {
in = new FileInputStream(new File(fileName));
extractor = new WordExtractor(in);
text = extractor.getText();
} catch (FileNotFoundException e) {
e.printStackTrace();
}catch (IOException e) {
e.printStackTrace();
} finally{
try {
if(in != null){
in.close();
}
} catch (IOException e) {
e.printStackTrace();
}
}
return text;
}
/**
* 读取word2007-2013
*/
public String readExtDocxContent(String fileName){
// 创建输入流读取DOC文件
String text = null;
OPCPackage opcPackage = null;
try {
opcPackage = POIXMLDocument.openPackage(fileName);
XWPFDocument xwpf = new XWPFDocument(opcPackage);
POIXMLTextExtractor ex = new XWPFWordExtractor(xwpf);
text = ex.getText();
} catch (Exception e) {
e.printStackTrace();
log.error("转换word异常:" + e);
} finally{
try {
if(opcPackage != null){
opcPackage.close();
}
} catch (IOException e) {
e.printStackTrace();
}
}
return text;
}
/**
* 读取Excel2003
*/
public String readExtXlsContent(String fileName){
String content = "";
try {
HSSFWorkbook workbook = new HSSFWorkbook(new FileInputStream(fileName));
ExcelExtractor extractor = new ExcelExtractor(workbook);
extractor.setFormulasNotResults(true);
extractor.setIncludeSheetNames(false);
content = extractor.getText();
log.debug("content:" + content);
} catch (Exception e) {
e.printStackTrace();
return "";
}
return content;
}
/**
* 读取Excel2007+
*/
public String readExtXlsxContent(String fileName){
String content = "";
try {
XSSFWorkbook workbook = new XSSFWorkbook(new FileInputStream(fileName));
XSSFExcelExtractor extractor = new XSSFExcelExtractor(workbook);
extractor.setFormulasNotResults(true);
extractor.setIncludeSheetNames(false);
content = extractor.getText();
} catch (Exception e) {
e.printStackTrace();
return "";
}
return content;
}
/**
* 读取ppt2003
*/
public String readExtPptContent(String fileName){
String text = "";
try {
SlideShow ss = new SlideShow(new HSLFSlideShow(new FileInputStream(fileName)));
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++) {
text += t[j].getText();
}
}
} catch (Exception e) {
e.printStackTrace();
}
return text;
}
/**
* 读取ppt2007+
*/
public String readExtPptxContent(String fileName){
String text = "";
XMLSlideShow xmlslideshow = null;
try {
xmlslideshow = new XMLSlideShow(new FileInputStream(fileName));
XSLFPowerPointExtractor ppt = new XSLFPowerPointExtractor(xmlslideshow);
text= ppt.getText();
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
return text;
}
/**
* 读取pdf
*/
public String readExtPDFContent(String fileName){
String text = "";
try {
PDFParser parser = new PDFParser(new FileInputStream(fileName));
parser.parse();
PDFTextStripper stripper = new PDFTextStripper();
text = stripper.getText(parser.getPDDocument());
parser.getPDDocument().close();
} catch (Exception e) {
e.printStackTrace();
return "";
}
return text;
}
- poi3.8.rar (9.3 MB)
- 下载次数: 12
发表评论
-
百度地图和ztree开发电子围栏功能
2016-09-29 09:27 4673jsp <%@ page language=" ... -
Oracle11g Enterprise Manager配置失败
2014-04-29 11:20 2527Win7先安装oracle 11g时,安装检测到系统的主 IP ... -
java弹窗导入导出文件
2014-03-24 11:42 1437package com.action.frame; impo ... -
jsp访问上级窗口元素
2014-04-29 11:22 411opener.document.getElementById( ... -
页面关闭IE触发事件方法
2013-09-30 09:56 544function window.onbeforeunload( ... -
页面右下角消息提示
2013-09-29 14:05 466<%@ page language="java ... -
oracle 日期列表
2013-09-29 12:52 475获取某个时间段之间的月份列表(示例返回2009-03到2010 ... -
倒计时
2013-09-24 10:01 314//提交 function doSubmit(){ ... -
oracle11G 最新驱动包
2013-09-24 10:00 670oracle11G 最新驱动包 解决与Spring冲突问题 ... -
获取第几天后的日期
2013-09-16 09:23 555Calendar cal = Calendar.getInst ... -
web工程下获取properties文件
2013-09-16 09:19 530String propertiesPath = getClas ... -
javamail
2013-09-16 09:15 525final SendMail sendmail = new S ... -
java根据年和周获取当前的日期时间段
2013-09-16 09:10 1240String[] dates = new String[7]; ... -
JSP判断日期间隔天数
2013-07-15 11:14 594var temp_field1 = $("#temp ... -
dtree不选中子节点处理
2013-05-17 10:35 1234//dtree.js 208行(chks[i].checked ... -
IE8下JS插入表格
2013-05-17 10:25 614//IE8下使用JS插入JSP表格 var tbl = do ... -
JSP选项卡显示
2013-05-17 10:22 1988<%@ page language="java ... -
JSP样式实例
2013-05-10 15:59 635<%@ page contentType="t ... -
Oracle表空间和用户创建赋权限
2013-05-10 15:54 631--RLDM CREATE TABLESPACE RLDM D ... -
hibernate oracle 主键递增
2013-05-10 15:47 454<?xml version="1.0" ...
相关推荐
java操作office所需要的资源包。 可以下载直接使用
Apache POI是Apache软件基金会的开放源码函式库,POI提供API给Java程序对Microsoft Office格式档案读和写的功能
POI是Apache开源项目之一,对Office文件的操作拥有强大的功能。附件中为常用的操作之一:Excel解析,支持Excel2003和2007的解析,示例仅供参考。
Apache POI是Apache软件基金会的开放源码函式库,POI提供API给Java程序对Microsoft Office格式档案读和写的功能。 结构: HSSF - 提供读写Microsoft Excel格式档案的功能。 XSSF - 提供读写Microsoft Excel ...
POI 3.8(包含源码,操作OFFICE所需的所有JAR包和相关API)
Apache POI是Apache软件基金会的开放源码函式库,POI提供API给Java程式对Microsoft Office格式档案读和写的功能。 .NET的开发人员则可以利用NPOI (POI for .NET) 来存取 POI 的功能。POI_3.8_API帮助文档。随时随地...
poi的组件,用于解析office文档,全部的组建放在里面,包含支持包,在对应文件夹里
读取、导入Excel,word,xls等office文件 需要的poi-scratchpad-3.8.jar包
Apache POI 是用Java编写的免费开源的跨平台的 Java API,Apache POI提供API给Java程式对Microsoft Office格式档案读和写的功能。POI为“Poor Obfuscation Implementation”的首字母缩写,意为“简洁版的模糊实现...
poi最新版本3.8,操作对Word,Excel导入导出数据库很有帮助,项目中很多都在使用poi,最新版本赶紧使用吧!此版本不清楚支持不支持office2010,我没有测试过,应该可以支持吧!呵呵!(此文件可以用winRar打开)
poi-3.8-bata 支持到office2007 PoiExcel.txt 如有xbeans.jar需要刪除,poi-3.8-bata,裏面有新版本的xmlbeans-2.3.0.jar
office转html所需的poi的jar包,包含了所有的jar包。其中poi的poi-ooxml-schemas-3.8包可用ooxml-schemas-1.1包代替,解决word2007+无法转化
导出Excel文件利用apache的poi第三方包,可在阿帕奇官网下载(最新版本为3.8,支持office2010)。解压文件后,只需要把项目导入到eclipse,再将hibernate.cfg.xml里连接Oracle的URL和用户名、密码更改下。参考entity...
使用poi将word转换为HTML,支持word2003 和 word2007 ,带jar包,在电脑没有安装MS office时也可以用! 还有一个是用jacob写的 也支持word2003 word2007 这个包到处都有,可自行下载!这个需要装有office才可使用!