poi 读取Excel,Word文件

package excelReader;

import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStream;
import java.util.Iterator;

import org.apache.poi.hssf.usermodel.HSSFCell;
import org.apache.poi.hssf.usermodel.HSSFWorkbook;
import org.apache.poi.ss.usermodel.Cell;
import org.apache.poi.ss.usermodel.Row;
import org.apache.poi.ss.usermodel.Sheet;
import org.apache.poi.ss.usermodel.Workbook;
import org.apache.poi.xssf.usermodel.XSSFWorkbook;

/**
 * 读取Excel文件
 * 
 * @author 李波
 *         <p>
 *         2010-08-04
 *         </p>
 */
public class PrintExcelTest {

	public static void main(String[] args) throws Exception {

		// String inputfile =
		// "D:/Documents and Settings/Administrator/桌面/a.xlsx";

		String inputfile = "D:/Documents and Settings/Administrator/桌面/test.xlsx";

		// String inputfile =
		// "D:/Documents and Settings/Administrator/桌面/把一个excel写进数据库/2.xls";

		showFile(inputfile);

	}

	private static Row topRow;

	/**
	 * 显示excel文档
	 * 
	 * @param inputfile
	 *            excel文档的路径
	 * @return excel文档的内容
	 * @throws IOException
	 * @throws FileNotFoundException
	 * @throws Exception
	 */
	public static StringBuffer showFile(String inputfile) throws IOException,
			FileNotFoundException, Exception {
		// 判断参数是否为空或没有意义
		if (inputfile == null || inputfile.trim().equals("")) {
			throw new IOException("no input file specified");
		}

		// excel文档
		Workbook workbook = getWorkBook(inputfile);

		// Sheet数量
		int numOfSheets = workbook.getNumberOfSheets();

		StringBuffer sb = new StringBuffer();

		// 循环获取所有的表
		for (int i = 0; i < numOfSheets; i++) {

			// 表
			Sheet sheet = workbook.getSheetAt(i);

			// 显示表
			sb.append(showSheet(sheet));
		}

		// Sheet sheet = workbook.getSheetAt(2);
		//
		// // 显示表
		// sb.append(showSheet(sheet));

		return sb;
	}

	/**
	 * 显示表
	 * 
	 * @param sheet
	 *            表实体
	 * @return 表的内容
	 * @throws Exception
	 */
	public static StringBuffer showSheet(Sheet sheet) throws Exception {

		StringBuffer sb = new StringBuffer();

		Iterator<Row> rows = sheet.rowIterator();

		// 显示行
		while (rows.hasNext()) {
			Row rowUser = (Row) rows.next();

			if (rowUser.getRowNum() == 0) {
				topRow = rowUser;
				continue;
			}

			sb.append(showRow(rowUser) + "\n");

		}

		return sb;
	}

	/**
	 * 显示行
	 * 
	 * @param rowUser
	 *            行实体
	 * @return 行的内容
	 * @throws Exception
	 */
	public static StringBuffer showRow(Row rowUser) throws Exception {

		StringBuffer sb = new StringBuffer();

		Iterator<Cell> iterUser = rowUser.cellIterator();

		while (iterUser.hasNext()) {

			Cell cell = iterUser.next();

			String cellValue = getCell(cell);

			if (cellValue.indexOf(",") != -1 || cellValue.indexOf("\n") != -1
					|| cellValue.indexOf(":") != -1) {
				throw new Exception("文件中存在  ‘,’ , ‘:’ 或  ‘\n’  ");
			}

			int columnIndex = cell.getColumnIndex();

			Cell topRowCell = topRow.getCell(columnIndex);

			String topRowCellValue = getCell(topRowCell);

			sb.append(topRowCellValue + ":" + cellValue + ",");
		}

		if (sb.length() > 1) {
			sb.setLength(sb.length() - 1);
		}

		return sb;
	}

	public static Workbook getWorkBook(String inputfile)
			throws FileNotFoundException, IOException, Exception {

		Workbook workbook = null;
		File file = new File(inputfile);
		InputStream fint = new FileInputStream(file);

		// 取得文件名的后缀名赋值给filetype
		String filetype = inputfile.substring(inputfile.lastIndexOf(".") + 1);

		// 如果是Excel文件则创建HSSFWorkbook读取
		if (filetype.equalsIgnoreCase("xls")) {
			// Excel2003

			// 另一种方式创建HSSFWorkbook
			// POIFSFileSystem poiFileSystem = new POIFSFileSystem(fint);
			// workbook = new HSSFWorkbook(poiFileSystem);

			workbook = new HSSFWorkbook(fint);

		} else if (filetype.equalsIgnoreCase("xlsx")) {

			// Excel2007

			workbook = new XSSFWorkbook(fint);

		} else {
			throw new Exception("不是Excel文件");
		}
		return workbook;
	}

	/**
	 * 根据单元格的类型显示值
	 * 
	 * @param cell
	 *            单元格的实体
	 * @return 单元格的内容
	 */
	public static String getCell(Cell cell) {
		if (cell == null)
			return "";
		switch (cell.getCellType()) {
		case HSSFCell.CELL_TYPE_NUMERIC:
			return cell.getNumericCellValue() + "";
		case HSSFCell.CELL_TYPE_STRING:
			return cell.getStringCellValue();
		case HSSFCell.CELL_TYPE_FORMULA:
			return cell.getCellFormula();
		case HSSFCell.CELL_TYPE_BLANK:
			return "";
		case HSSFCell.CELL_TYPE_BOOLEAN:
			return cell.getBooleanCellValue() + "";
		case HSSFCell.CELL_TYPE_ERROR:
			return cell.getErrorCellValue() + "";
		}
		return "";
	}
}

 

 

package wordReader;

/**   
 * 需要的jar包：  
 * poi-3.0.2-FINAL-20080204.jar  
 * poi-contrib-3.0.2-FINAL-20080204.jar  
 * poi-scratchpad-3.0.2-FINAL-20080204.jar 
 * poi-3.5-beta6-20090622.jar   
 * geronimo-stax-api_1.0_spec-1.0.jar 
 * ooxml-schemas-1.0.jar   
 * openxml4j-bin-beta.jar   
 * poi-ooxml-3.5-beta6-20090622.jar   
 * xmlbeans-2.3.0.jar   
 * dom4j-1.6.1.jar  
 * 
 */
import java.io.IOException;
import java.io.InputStream;

import org.apache.poi.POIXMLDocument;
import org.apache.poi.POIXMLTextExtractor;
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.extractor.WordExtractor;
import org.apache.poi.openxml4j.exceptions.OpenXML4JException;
import org.apache.poi.openxml4j.opc.OPCPackage;
import org.apache.poi.xssf.usermodel.XSSFCell;
import org.apache.poi.xssf.usermodel.XSSFRow;
import org.apache.poi.xssf.usermodel.XSSFSheet;
import org.apache.poi.xssf.usermodel.XSSFWorkbook;
import org.apache.poi.xwpf.extractor.XWPFWordExtractor;
import org.apache.xmlbeans.XmlException;

/**
 * 读取word文件
 * 
 * @author 李波
 *         <p>
 *         2010-08-04
 *         </p>
 */
public class WordAndExcelExtractor {
	public static void main(String[] args) {
		try {

			// String wordFile =
			// "D:/Documents and Settings/Administrator/桌面/xxxx.docx";

			String wordFile = "D:/Documents and Settings/Administrator/桌面/javaPOI.doc";

			String wordText2007 = WordAndExcelExtractor
					.extractTextFromDOC2007(wordFile);
			System.out.println("wordText2007=======" + wordText2007);

			// InputStream is = new FileInputStream("D:/XXX研发中心技术岗位职位需求.xls");
			// String excelText = WordAndExcelExtractor.extractTextFromXLS(is);
			// System.out.println("text2003==========" + excelText);
			// String excelFile = "D:/Hello2007.xlsx";
			// String excelText2007 = WordAndExcelExtractor
			// .extractTextFromXLS2007(excelFile);
			// System.out.println("excelText2007==========" + excelText2007);

		} catch (Exception e) {
			e.printStackTrace();
		}
	}

	/**
	 * @Method: extractTextFromDOCX
	 * @Description: 从word 2003文档中提取纯文本
	 * @param
	 * @return String
	 * @throws
	 */
	public static String extractTextFromDOC(InputStream is) throws IOException {
		WordExtractor ex = new WordExtractor(is); // is是WORD文件的InputStream
		return ex.getText();
	}

	/**
	 * @Method: extractTextFromDOCX
	 * @Description: 从word 2007文档中提取纯文本
	 * @param
	 * @return String
	 * @throws
	 */
	public static String extractTextFromDOC2007(String fileName)
			throws IOException, OpenXML4JException, XmlException {
		OPCPackage opcPackage = POIXMLDocument.openPackage(fileName);
		POIXMLTextExtractor ex = new XWPFWordExtractor(opcPackage);

		return ex.getText();
	}

	/**
	 * 
	 * @Method: extractTextFromXLS
	 * 
	 * @Description: 从excel 2003文档中提取纯文本
	 * @param
	 * 
	 * @return String
	 * 
	 * @throws
	 */
	@SuppressWarnings("deprecation")
	private static String extractTextFromXLS(InputStream is) throws IOException {
		StringBuffer content = new StringBuffer();
		HSSFWorkbook workbook = new HSSFWorkbook(is); // 创建对Excel工作簿文件的引用
		for (int numSheets = 0; numSheets < workbook.getNumberOfSheets(); numSheets++) {
			if (null != workbook.getSheetAt(numSheets)) {
				HSSFSheet aSheet = workbook.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); // 获得一行
						for (short cellNumOfRow = 0; cellNumOfRow <= aRow
								.getLastCellNum(); cellNumOfRow++) {
							if (null != aRow.getCell(cellNumOfRow)) {
								HSSFCell aCell = aRow.getCell(cellNumOfRow); // 获得列值
								if (aCell.getCellType() == HSSFCell.CELL_TYPE_NUMERIC) {
									content.append(aCell.getNumericCellValue());
								} else if (aCell.getCellType() == HSSFCell.CELL_TYPE_BOOLEAN) {
									content.append(aCell.getBooleanCellValue());
								} else {
									content.append(aCell.getStringCellValue());
								}
							}
						}
					}
				}
			}
		}
		return content.toString();
	}

	/**
	 * @Method: extractTextFromXLS2007
	 * @Description: 从excel 2007文档中提取纯文本
	 * @param
	 * 
	 * @return String * @throws
	 */
	private static String extractTextFromXLS2007(String fileName)
			throws Exception {
		StringBuffer content = new StringBuffer(); // 构造 XSSFWorkbook 对象，strPath
		// 传入文件路径
		XSSFWorkbook xwb = new XSSFWorkbook(fileName); // 循环工作表Sheet
		for (int numSheet = 0; numSheet < xwb.getNumberOfSheets(); numSheet++) {
			XSSFSheet xSheet = xwb.getSheetAt(numSheet);
			if (xSheet == null) {
				continue;
			} // 循环行Row
			for (int rowNum = 0; rowNum <= xSheet.getLastRowNum(); rowNum++) {
				XSSFRow xRow = xSheet.getRow(rowNum);
				if (xRow == null) {
					continue;
				}
				// 循环列Cell
				for (int cellNum = 0; cellNum <= xRow.getLastCellNum(); cellNum++) {
					XSSFCell xCell = xRow.getCell(cellNum);
					if (xCell == null) {
						continue;
					}
					if (xCell.getCellType() == XSSFCell.CELL_TYPE_BOOLEAN) {
						content.append(xCell.getBooleanCellValue());
					} else if (xCell.getCellType() == XSSFCell.CELL_TYPE_NUMERIC) {
						content.append(xCell.getNumericCellValue());
					} else {
						content.append(xCell.getStringCellValue());
					}
				}
			}
		}
		return content.toString();

	}
}