POI的简介
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。Poor Obfuscation Implementation即 简洁版的模糊实现。
1、基本功能
HSSF - 提供读写Microsoft Excel格式档案的功能。
XSSF - 提供读写Microsoft Excel OOXML格式档案的功能。
HWPF - 提供读写Microsoft Word格式档案的功能。
HSLF - 提供读写Microsoft PowerPoint格式档案的功能。
HDGF - 提供读写Microsoft Visio格式档案的功能。
POI的安装
下载地址:https://www.apache.org/dyn/closer.lua/poi/release/bin/poi-bin-4.0.0-20180907.tar.gz
————————————————
版权声明:本文为CSDN博主「一个处女座的程序猿」的原创文章,遵循CC 4.0 BY-SA版权协议,转载请附上原文出处链接及本声明。
原文链接:https://blog.csdn.net/qq_41185868/article/details/103219050
% gpg --import KEYS
% gpg --verify downloaded_file.asc downloaded_file
or
% pgpk -a KEYS
% pgpv downloaded_file.asc
or
% pgp -ka KEYS
% pgp downloaded_file.asc
POI的使用方法(基于POI的转换—Word、Excel、Ppt等转html)
1、基础案例
1.1、创建Excel 文档—利用Jakarta POI API 创建Excel 文档
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.hssf.usermodel.HSSFSheet;
import org.apache.poi.hssf.usermodel.HSSFRow;
import org.apache.poi.hssf.usermodel.HSSFCell;
import java.io.FileOutputStream;
public class CreateXL {
/** Excel 文件要存放的位置,假定在D盘下*/
public static String outputFile = "D:\\test.xls";
public static void main(String argv[]) {
try {
// 创建新的Excel 工作簿
HSSFWorkbook workbook = new HSSFWorkbook();
// 在Excel工作簿中建一工作表,其名为缺省值
// 如要新建一名为"效益指标"的工作表,其语句为:
// HSSFSheet sheet = workbook.createSheet("效益指标");
HSSFSheet sheet = workbook.createSheet();
// 在索引0的位置创建行(最顶端的行)
HSSFRow row = sheet.createRow((short)0);
//在索引0的位置创建单元格(左上端)
HSSFCell cell = row.createCell((short)0);
// 定义单元格为字符串类型
cell.setCellType(HSSFCell.CELL_TYPE_STRING);//已过时
// 在单元格中输入一些内容
cell.setCellValue("增加值");
// 新建一输出文件流
FileOutputStream fOut = new FileOutputStream(outputFile);
// 把相应的Excel 工作簿存盘
workbook.write(fOut);
fOut.flush();
// 操作结束,关闭文件
fOut.close();
System.out.println("文件生成...");
} catch (Exception e) {
System.out.println("已运行 xlCreate() : " + e);
}
}
}
1.2、读取Excel文档中的数据
读取Excel文档中的数据。假定在D盘JTest目录下有一个文件名为test1.xls的Excel文件。
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.hssf.usermodel.HSSFSheet;
import org.apache.poi.hssf.usermodel.HSSFRow;
import org.apache.poi.hssf.usermodel.HSSFCell;
import java.io.FileInputStream;
public class ReadXL {
/** Excel文件的存放位置。注意是反斜线*/
public static String fileToBeRead = "D:\\test1.xls";
public static void main(String argv[]) {
try {
// 创建对Excel工作簿文件的引用
HSSFWorkbook workbook = new HSSFWorkbook(new FileInputStream(fileToBeRead));
// 创建对工作表的引用。
// 本例是按名引用(让我们假定那张表有着缺省名"Sheet1")
HSSFSheet sheet = workbook.getSheet("Sheet1");
// 也可用getSheetAt(int index)按索引引用,
// 在Excel文档中,第一张工作表的缺省索引是0,
// 其语句为:HSSFSheet sheet = workbook.getSheetAt(0);
// 读取左上端单元
HSSFRow row = sheet.getRow(0);
HSSFCell cell = row.getCell((short)0);
// 输出单元内容,cell.getStringCellValue()就是取所在单元的值
System.out.println("左上端单元是: " + cell.getStringCellValue());
} catch (Exception e) {
System.out.println("已运行xlRead() : " + e);
}
}
}
1.3、处理WORD文档
import java.io. * ;
import org.apache.poi.hwpf.extractor.WordExtractor;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.hssf.usermodel.HSSFSheet;
import org.apache.poi.hssf.usermodel.HSSFRow;
import org.apache.poi.hssf.usermodel.HSSFCell;
public class TestPoi {
public TestPoi() {}
public static void main(String args[])throws Exception{
FileInputStream in = new FileInputStream("D:\\a.doc");
WordExtractor extractor = new WordExtractor();
String str = extractor.extractText(in);
//System.out.println("the result length is"+str.length());
System.out.println(str);
}
}
2、进阶案例应用
文章参考:
https://blog.csdn.net/yjclsx/article/details/51441632
http://blog.csdn.net/z69183787/article/details/17468039
在现在这个互联网在线时代,java实现在线预览的这个需求,或许是大家都想要的。当然,如果公司有钱,直接使用付费的第三方软件或者云在线预览服务就可以了,比如永中office、office web 365(http://www.officeweb365.com/)等公司,都有云端在线预览服务,可想而知,这些扩展功能,肯定是需要钱了。
但是,对于我们学生党,如果想要免费或者DIY,则可以用openoffice,还需要借助其他的工具(例如swfTools、FlexPaper等)才行。实现原理就是:
1.通过第三方工具openoffice,将word、excel、ppt、txt等文件转换为pdf文件;
2.通过swfTools将pdf文件转换成swf格式的文件;
3.通过FlexPaper文档组件在页面上进行展示。
当然如果装了Adobe Reader XI,那把pdf直接拖到浏览器页面就可以直接打开预览,这样就不需要步骤2、3了,前提就是客户装了Adobe Reader XI这个pdf阅读器。
当然,本篇文章主要介绍的POI,所以,可以通过POI实现word、excel、ppt转html,这样就可以放在页面上了。
2.1、word转html
package wordToHtml;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.InputStream;
import java.util.List;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import org.apache.commons.io.FileUtils;
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.Picture;
import org.apache.poi.hwpf.usermodel.PictureType;
import org.w3c.dom.Document;
public class PoiWordToHtml {
public static void main(String[] args) throws Throwable {
final String path = "D:\\poi-test\\wordToHtml\\";
final String file = "人员选择系分.doc";
InputStream input = new FileInputStream(path + file);
HWPFDocument wordDocument = new HWPFDocument(input);
WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
DocumentBuilderFactory.newInstance().newDocumentBuilder()
.newDocument());
wordToHtmlConverter.setPicturesManager(new PicturesManager() {
public String savePicture(byte[] content, PictureType pictureType,
String suggestedName, float widthInches, float heightInches) {
return suggestedName;
}
});
wordToHtmlConverter.processDocument(wordDocument);
List pics = wordDocument.getPicturesTable().getAllPictures();
if (pics != null) {
for (int i = 0; i < pics.size(); i++) {
Picture pic = (Picture) pics.get(i);
try {
pic.writeImageContent(new FileOutputStream(path
+ pic.suggestFullFileName()));
} catch (FileNotFoundException e) {
e.printStackTrace();
}
}
}
Document htmlDocument = wordToHtmlConverter.getDocument();
ByteArrayOutputStream outStream = new ByteArrayOutputStream();
DOMSource domSource = new DOMSource(htmlDocument);
StreamResult streamResult = new StreamResult(outStream);
TransformerFactory tf = TransformerFactory.newInstance();
Transformer serializer = tf.newTransformer();
serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
serializer.setOutputProperty(OutputKeys.INDENT, "yes");
serializer.setOutputProperty(OutputKeys.METHOD, "html");
serializer.transform(domSource, streamResult);
outStream.close();
String content = new String(outStream.toByteArray());
FileUtils.writeStringToFile(new File(path, "人员选择系分.html"), content, "utf-8");
}
}
2.2、excel转html
package excelToHtml;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.List;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import org.apache.commons.io.FileUtils;
import org.apache.poi.hssf.converter.ExcelToHtmlConverter;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.hwpf.converter.PicturesManager;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.hwpf.usermodel.Picture;
import org.apache.poi.hwpf.usermodel.PictureType;
import org.w3c.dom.Document;
public class PoiExcelToHtml {
final static String path = "D:\\poi-test\\excelToHtml\\";
final static String file = "exportExcel.xls";
public static void main(String args[]) throws Exception {
InputStream input=new FileInputStream(path+file);
HSSFWorkbook excelBook=new HSSFWorkbook(input);
ExcelToHtmlConverter excelToHtmlConverter = new ExcelToHtmlConverter (DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument() );
excelToHtmlConverter.processWorkbook(excelBook);
List pics = excelBook.getAllPictures();
if (pics != null) {
for (int i = 0; i < pics.size(); i++) {
Picture pic = (Picture) pics.get (i);
try {
pic.writeImageContent (new FileOutputStream (path + pic.suggestFullFileName() ) );
} catch (FileNotFoundException e) {
e.printStackTrace();
}
}
}
Document htmlDocument =excelToHtmlConverter.getDocument();
ByteArrayOutputStream outStream = new ByteArrayOutputStream();
DOMSource domSource = new DOMSource (htmlDocument);
StreamResult streamResult = new StreamResult (outStream);
TransformerFactory tf = TransformerFactory.newInstance();
Transformer serializer = tf.newTransformer();
serializer.setOutputProperty (OutputKeys.ENCODING, "utf-8");
serializer.setOutputProperty (OutputKeys.INDENT, "yes");
serializer.setOutputProperty (OutputKeys.METHOD, "html");
serializer.transform (domSource, streamResult);
outStream.close();
String content = new String (outStream.toByteArray() );
FileUtils.writeStringToFile(new File (path, "exportExcel.html"), content, "utf-8");
}
}
2.3、ppt转html
其实只是ppt转图片,有了图片后放到页面上去,点击下一页就一张张显示就可以了。这里只介绍ppt转图片的过程。ppt转图片有个缺陷,就是ppt里不是宋体的字有些可能会变成框框。以上都需要引入poi的jar包。要实现在线预览,只需把转换得到的html在新标签页打开或者镶嵌到某块区域就可以展现了。
package pptToImg;
import java.awt.Dimension;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.awt.Color;
import java.awt.Dimension;
import java.awt.Graphics2D;
import java.awt.geom.Rectangle2D;
import java.awt.image.BufferedImage;
import org.apache.poi.hslf.model.TextRun;
import org.apache.poi.hslf.record.Slide;
import org.apache.poi.hslf.usermodel.RichTextRun;
import org.apache.poi.hslf.usermodel.SlideShow;
public class PPTtoImage {
public static void main(String[] args) {
// 读入PPT文件
File file = new File("D:/poi-test/pptToImg/test.ppt");
doPPTtoImage(file);
}
public static boolean doPPTtoImage(File file) {
boolean isppt = checkFile(file);
if (!isppt) {
System.out.println("The image you specify don't exit!");
return false;
}
try {
FileInputStream is = new FileInputStream(file);
SlideShow ppt = new SlideShow(is);
is.close();
Dimension pgsize = ppt.getPageSize();
org.apache.poi.hslf.model.Slide[] slide = ppt.getSlides();
for (int i = 0; i < slide.length; i++) {
System.out.print("第" + i + "页。");
TextRun[] truns = slide[i].getTextRuns();
for ( int k=0;k<truns.length;k++){
RichTextRun[] rtruns = truns[k].getRichTextRuns();
for(int l=0;l<rtruns.length;l++){
int index = rtruns[l].getFontIndex();
String name = rtruns[l].getFontName();
rtruns[l].setFontIndex(1);
rtruns[l].setFontName("宋体");
// System.out.println(rtruns[l].getText());
}
}
BufferedImage img = new BufferedImage(pgsize.width,pgsize.height, BufferedImage.TYPE_INT_RGB);
Graphics2D graphics = img.createGraphics();
graphics.setPaint(Color.BLUE);
graphics.fill(new Rectangle2D.Float(0, 0, pgsize.width, pgsize.height));
slide[i].draw(graphics);
// 这里设置图片的存放路径和图片的格式(jpeg,png,bmp等等),注意生成文件路径
FileOutputStream out = new FileOutputStream("D:/poi-test/pptToImg/pict_"+ (i + 1) + ".jpeg");
javax.imageio.ImageIO.write(img, "jpeg", out);
out.close();
}
System.out.println("success!!");
return true;
} catch (FileNotFoundException e) {
System.out.println(e);
// System.out.println("Can't find the image!");
} catch (IOException e) {
}
return false;
}
// function 检查文件是否为PPT
public static boolean checkFile(File file) {
boolean isppt = false;
String filename = file.getName();
String suffixname = null;
if (filename != null && filename.indexOf(".") != -1) {
suffixname = filename.substring(filename.indexOf("."));
if (suffixname.equals(".ppt")) {
isppt = true;
}
return isppt;
} else {
return isppt;
}
}
}
参考文章
百度百科