在网上百度,然后自己终结写了这篇文章
package cn.rjxh.utils;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.FileReader;
import java.io.IOException;
import java.io.InputStream;
import java.util.ArrayList;
import javax.swing.text.BadLocationException;
import javax.swing.text.DefaultStyledDocument;
import javax.swing.text.rtf.RTFEditorKit;
import org.apache.pdfbox.pdfparser.PDFParser;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.util.PDFTextStripper;
import org.apache.poi.hslf.HSLFSlideShow;
import org.apache.poi.hslf.extractor.PowerPointExtractor;
import org.apache.poi.hslf.model.Slide;
import org.apache.poi.hslf.model.TextRun;
import org.apache.poi.hslf.usermodel.SlideShow;
import org.apache.poi.hssf.usermodel.HSSFCell;
import org.apache.poi.hssf.usermodel.HSSFRow;
import org.apache.poi.hssf.usermodel.HSSFSheet;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.usermodel.Range;
import com.lowagie.text.Document;
import com.lowagie.text.DocumentException;
import com.lowagie.text.pdf.PdfCopy;
import com.lowagie.text.pdf.PdfImportedPage;
import com.lowagie.text.pdf.PdfReader;
public class ControlOfficeFile {
// 读取world文档里面的内容
public String getDocContext(String filePath) throws Exception {
File f = new File(filePath);
FileInputStream fis = new FileInputStream(f);
HWPFDocument doc = new HWPFDocument(fis);
Range rang = doc.getRange();
String text = rang.text();
fis.close();
return text;
}
// 读取excel里面的内容
public String getExcelFile(String filePath) throws Exception {
StringBuffer buff = new StringBuffer();
try {
// 创建对Excel工作簿文件的引用
HSSFWorkbook wb = new HSSFWorkbook(new FileInputStream(filePath));
// 创建对工作表的引用。
for (int numSheets = 0; numSheets < wb.getNumberOfSheets(); numSheets++) { // 读取sheet的个数
if (null != wb.getSheetAt(numSheets)) { // 如果sheet有内容的话
HSSFSheet aSheet = wb.getSheetAt(numSheets);// 获得一个sheet
for (int rowNumOfSheet = 0; rowNumOfSheet <= aSheet
.getLastRowNum(); rowNumOfSheet++) {
if (null != aSheet.getRow(rowNumOfSheet)) {
HSSFRow aRow = aSheet.getRow(rowNumOfSheet); // 获得一个行
for (int cellNumOfRow = 0; cellNumOfRow <= aRow
.getLastCellNum(); cellNumOfRow++) {
if (null != aRow.getCell(cellNumOfRow)) {
HSSFCell aCell = aRow.getCell(cellNumOfRow);// 获得列值
switch (aCell.getCellType()) {
case HSSFCell.CELL_TYPE_FORMULA:
break;
case HSSFCell.CELL_TYPE_NUMERIC:
buff.append(aCell.getNumericCellValue())
.append('\t');
break;
case HSSFCell.CELL_TYPE_STRING:
buff.append(aCell.getStringCellValue())
.append('\t');
break;
}
}
}
buff.append('\n');
}
}
}
}
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
return buff.toString();
}
private static final int N= 10; //规定的分多少份
//*********************************************************************
//拆分pdf文件
public static void partitionPdfFile(String filepath) throws Exception {
ControlOfficeFile controlOfficeFile = new ControlOfficeFile();
Document document = null;
PdfCopy copy = null;
try {
PdfReader reader = new PdfReader(filepath);
int n = reader.getNumberOfPages(); //获取一共有多少页
System.out.println("n))))))))))))))))))))))))"+n);
if (n < N) {
System.out.println(controlOfficeFile.getPdfContext(filepath)); //将里面的数据显示出来
return;
}
int size = n / N;
String staticpath = filepath.substring(0, filepath
.lastIndexOf("\\") + 1); //获取路径,不包含pdf文件名的路径,到它的上面一层
System.out.println("staticpath:>>>>>>>>>>>>>>>>>>>>"+staticpath);
String savepath = null;
ArrayList<String> savepaths = new ArrayList<String>();
for (int i = 1; i <= N; i++) { //处理pdf文件分割后的文件名
if (i < 10) {
savepath = filepath.substring(
filepath.lastIndexOf("\\") + 1,
filepath.length() - 4);
savepath = staticpath + savepath + "0" + i + ".pdf";
savepaths.add(savepath);
} else {
savepath = filepath.substring(
filepath.lastIndexOf("\\") + 1,
filepath.length() - 4);
savepath = staticpath + savepath + i + ".pdf";
savepaths.add(savepath);
}
}
for (int i = 0; i < N - 1; i++) {
document = new Document(reader.getPageSize(1));
copy = new PdfCopy(document, new FileOutputStream(savepaths
.get(i)));//给对应的文件赋值
document.open();
for (int j = size * i + 1; j <= size * (i + 1); j++) {
document.newPage();
PdfImportedPage page = copy.getImportedPage(reader, j);
copy.addPage(page);
}
document.close();
System.out.println("savepaths.get(i)>>>>>>>>>>>>>>>>>>>"+savepaths.get(i));
System.out.println(controlOfficeFile.getPdfContext(savepaths.get(i)));
File delFile = new File(savepaths.get(i));
delFile.delete();
}
//这是为最后一个赋值
document = new Document(reader.getPageSize(1));
copy = new PdfCopy(document, new FileOutputStream(savepaths
.get(N - 1)));
document.open();
for (int j = size * (N - 1) + 1; j <= n; j++) {
document.newPage();
PdfImportedPage page = copy.getImportedPage(reader, j);
copy.addPage(page);
}
document.close();
System.out.println(controlOfficeFile.getPdfContext(savepaths.get(N-1)));
File delFile = new File(savepaths.get(N-1));
delFile.delete();
} catch (IOException e) {
e.printStackTrace();
} catch (DocumentException e) {
e.printStackTrace();
}
}
// 读取pdf里面的内容
public String getPdfContext(String filePath) throws Exception {
File f = new File(filePath);
FileInputStream fis = new FileInputStream(f);
PDFParser p = new PDFParser(fis);
p.parse();
PDDocument pdd = p.getPDDocument();
PDFTextStripper ts = new PDFTextStripper();
String c = ts.getText(pdd);
pdd.close();
fis.close();
return c;
}
//*****************************************************************
// 读取txt文件里面的内容
public String getTxtContext(String filePath) throws Exception {
FileReader fr = new FileReader(filePath);
BufferedReader br = new BufferedReader(fr);
StringBuffer buff = new StringBuffer();
String temp = null;
while ((temp = br.readLine()) != null) {
buff.append(temp + "\r\n");
}
br.close();
return buff.toString();
}
// 读取ppt里面的内容
// 直接抽取幻灯片的全部内容
public String getPPT1(String path) throws Exception {
File file = new File(path);
FileInputStream fin = new FileInputStream(file);
PowerPointExtractor extractor = new PowerPointExtractor(fin);
return extractor.getText();
}
// 一张幻灯片一张幻灯片地读取
public void getPPT2(String path) throws Exception {
File file = new File(path);
FileInputStream fin = new FileInputStream(file);
SlideShow ss = new SlideShow(new HSLFSlideShow(fin));
Slide[] slides = ss.getSlides();
for (int i = 0; i < slides.length; i++) {
System.out.println(")))))))))))))))" + slides.length);
// 读取一张幻灯片的标题
String title = slides[i].getTitle();
System.out.println("标题:" + title);
// 读取一张幻灯片的内容(包括标题)
TextRun[] runs = slides[i].getTextRuns();
for (int j = 0; j < runs.length; j++) {
System.out.println(runs[j].getText());
}
}
}
// 读取RTF文件
public String getRTFContent(String filePath) {
String result = null;
File file = new File(filePath);
try {
DefaultStyledDocument styledDoc = new DefaultStyledDocument();
InputStream is = new FileInputStream(file);
new RTFEditorKit().read(is, styledDoc, 0);
result = new String(styledDoc.getText(0, styledDoc.getLength())
.getBytes("ISO8859_1"));
// 提取文本,读取中文需要使用ISO8859_1编码,否则会出现乱码
} catch (IOException e) {
e.printStackTrace();
} catch (BadLocationException e) {
e.printStackTrace();
}
return result;
}
}