目录
pom代码结果pom
<dependency><groupId>org.apache.poi</groupId><artifactId>poi</artifactId><version>3.8</version></dependency><dependency><groupId>org.apache.poi</groupId><artifactId>poi-scratchpad</artifactId><version>3.8</version></dependency><dependency><groupId>org.apache.poi</groupId><artifactId>poi-ooxml</artifactId><version>3.8</version></dependency><dependency><groupId>org.apache.poi</groupId><artifactId>poi-ooxml-schemas</artifactId><version>3.8</version></dependency><dependency><groupId>org.apache.poi</groupId><artifactId>ooxml-schemas</artifactId><version>1.1</version></dependency><dependency><groupId>org.apache.pdfbox</groupId><artifactId>pdfbox</artifactId><version>2.0.9</version></dependency><dependency><groupId>com.itextpdf</groupId><artifactId>itextpdf</artifactId><version>5.5.3</version></dependency>
代码
import org.apache.pdfbox.io.RandomAccess;import org.apache.pdfbox.io.RandomAccessFile;import org.apache.pdfbox.pdfparser.PDFParser;import org.apache.pdfbox.pdmodel.PDDocument;import org.apache.pdfbox.text.PDFTextStripper;import org.apache.poi.hslf.HSLFSlideShow;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.HSSFWorkbook;import org.apache.poi.hwpf.extractor.WordExtractor;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.xslf.extractor.XSLFPowerPointExtractor;import org.apache.poi.xslf.usermodel.XMLSlideShow;import org.apache.poi.xssf.usermodel.XSSFWorkbook;import org.apache.poi.xwpf.extractor.XWPFWordExtractor;import org.apache.poi.xwpf.usermodel.XWPFDocument;import org.dom4j.Document;import org.dom4j.io.SAXReader;import java.io.File;import java.io.FileInputStream;import java.io.IOException;import java.io.InputStream;import java.text.SimpleDateFormat;import java.util.Date;/*** 获取文件中的文本** @author 明快de玄米61* @date /12/8 23:50*/public class Test {public static void main(String[] args) {// 测试获取doc中的文本System.out.println(extractDoc("C:\\test\\1115\\222.doc"));// 测试获取docx中的文本System.out.println(extractDocx("C:\\test\\1115\\111.docx"));// 测试获取xls中的文本System.out.println(extractXls("C:\\test\\1115\\444.xls"));// 测试获取xlsx中的文本System.out.println(extractXlsx("C:\\test\\1115\\333.xlsx"));// 测试获取ppt中的文本System.out.println(extractPpt("C:\\test\\1115\\555.ppt"));// 测试获取pptx中的文本System.out.println(extractPptx("C:\\test\\1115\\555.pptx"));// 测试获取pdf中的文本System.out.println(extractPdf("C:\\test\\1115\\888.pdf"));// 测试获取xml中的文本System.out.println(extractXml("C:\\test\\1115\\1000.xml"));}/*** 获取doc中的文本** @param filePath 文件全路径* @return 文本* @author 明快de玄米61* @date /12/18 23:22**/private static String extractDoc(String filePath) {try (InputStream in = new FileInputStream(filePath)) {WordExtractor extractor = new WordExtractor(in);return extractor.getText();} catch (Exception e) {e.printStackTrace();}return null;}/*** 获取docx中的文本** @param filePath 文件全路径* @return 文本* @author 明快de玄米61* @date /12/18 23:22**/private static String extractDocx(String filePath) {try (InputStream in = new FileInputStream(filePath)) {XWPFDocument xdoc = new XWPFDocument(in);XWPFWordExtractor extractor = new XWPFWordExtractor(xdoc);return extractor.getText();} catch (Exception e) {e.printStackTrace();}return null;}/*** 获取xls中的文本** @param filePath 文件全路径* @return 文本* @author 明快de玄米61* @date /12/18 23:22**/private static String extractXls(String filePath) {try (InputStream in = new FileInputStream(filePath)) {Workbook workbook = new HSSFWorkbook(in);return workbook2String(workbook);} catch (Exception e) {e.printStackTrace();}return null;}/*** 获取xlsx中的文本** @param filePath 文件全路径* @return 文本* @author 明快de玄米61* @date /12/18 23:22**/private static String extractXlsx(String filePath) {try (InputStream in = new FileInputStream(filePath)) {Workbook workbook = new XSSFWorkbook(in);return workbook2String(workbook);} catch (Exception e) {e.printStackTrace();}return null;}private static String workbook2String(Workbook workbook) {StringBuffer sb = new StringBuffer();if (workbook != null) {for (int sheetNum = 0; sheetNum < workbook.getNumberOfSheets(); sheetNum++) {// 获得当前sheet工作表Sheet sheet = workbook.getSheetAt(sheetNum);if (sheet == null) {continue;}// 获得当前sheet的开始行int firstRowNum = sheet.getFirstRowNum();// 获得当前sheet的结束行int lastRowNum = sheet.getLastRowNum();// 循环除了第一行的所有行sb.append(sheet.getSheetName() + "\n");for (int rowNum = firstRowNum; rowNum <= lastRowNum; rowNum++) {// 获得当前行Row row = sheet.getRow(rowNum);if (row == null || row.getPhysicalNumberOfCells() == 0) {/* String[] a=new String[0]; list.add(a); */// sb.append("\r\n");continue;} // 获得当前行的开始列int firstCellNum = row.getFirstCellNum();// 获得当前行的列数int lastCellNum = row.getLastCellNum();// String[] cells = new// String[row.getPhysicalNumberOfCells()];// 循环当前行for (int cellNum = firstCellNum; cellNum < lastCellNum; cellNum++) {Cell cell = row.getCell(cellNum);String value = cellValue(cell);if (!"".equals(value)) {sb.append(value);sb.append(",");}}}sb.append("\n");}}return sb.toString();}/*** 获得Excel格子里的内容** @param cell 每个格子* @return*/private static String cellValue(Cell cell) {String cellValue = "";if (cell == null) {return cellValue;}// 把数字当成String来读，避免出现1读成1.0的情况// if (cell.getCellType() == Cell.CELL_TYPE_NUMERIC) {// // cell.setCellType(Cell.CELL_TYPE_STRING);//// }// 判断数据的类型switch (cell.getCellType()) {case Cell.CELL_TYPE_NUMERIC: // 数字// cellValue = String.valueOf(cell.getNumericCellValue());short format = cell.getCellStyle().getDataFormat();SimpleDateFormat sdf = null;if (format == 14 || format == 31 || format == 57 || format == 58|| (176 <= format && format <= 178)|| (182 <= format && format <= 196)|| (210 <= format && format <= 213) || (208 == format)) {if (format == 14) {sdf = new SimpleDateFormat("yyyy/MM/dd");} else {sdf = new SimpleDateFormat("yyyy年MM月dd日");}double value = cell.getNumericCellValue();Date date = org.apache.poi.ss.usermodel.DateUtil.getJavaDate(value);if (date == null || "".equals(date)) {cellValue = "";}try {cellValue = (sdf.format(date));} catch (Exception e) {e.printStackTrace();cellValue = "";}} else {// 不是日期格式cell.setCellType(Cell.CELL_TYPE_STRING);String temp = cell.getStringCellValue();// 判断是否包含小数点，如果不含小数点，则以字符串读取，如果含小数点，则转换为Double类型的字符串if (temp.indexOf(".") > -1) {cellValue = (String.valueOf(new Double(temp)).trim());} else {cellValue = (temp.trim());}}break;case Cell.CELL_TYPE_STRING: // 字符串cellValue = String.valueOf(cell.getStringCellValue());break;case Cell.CELL_TYPE_BOOLEAN: // BooleancellValue = String.valueOf(cell.getBooleanCellValue());break;case Cell.CELL_TYPE_FORMULA: // 公式cellValue = String.valueOf(cell.getCellFormula());break;case Cell.CELL_TYPE_BLANK: // 空值cellValue = "";break;case Cell.CELL_TYPE_ERROR: // 故障cellValue = "";// 非法字符break;default:cellValue = "";// 未知类型break;}return cellValue;}/*** 获取ppt中的文本** @param filePath 文件全路径* @return 文本* @author 明快de玄米61* @date /12/18 23:22**/private static String extractPpt(String filePath) {try (InputStream in = new FileInputStream(filePath)) {StringBuffer content = new StringBuffer();SlideShow ss = new SlideShow(new HSLFSlideShow(in));Slide[] slides = ss.getSlides();// 获得每一张幻灯片for (int i = 0; i < slides.length; i++) {TextRun[] t = slides[i].getTextRuns();// 为了取得幻灯片的文字内容，建立TextRunfor (int j = 0; j < t.length; j++) {content.append(t[j].getText());// 这里会将文字内容加到content中去}content.append(slides[i].getTitle());}return content.toString();} catch (Exception e) {e.printStackTrace();}return null;}/*** 获取pptx中的文本** @param filePath 文件全路径* @return 文本* @author 明快de玄米61* @date /12/18 23:22**/private static String extractPptx(String filePath) {try (InputStream in = new FileInputStream(filePath)) {XMLSlideShow slide = new XMLSlideShow(in);XSLFPowerPointExtractor extractor = new XSLFPowerPointExtractor(slide);return extractor.getText();} catch (Exception e) {e.printStackTrace();}return null;}/*** 获取pdf中的文本** @param filePath 文件全路径* @return 文本* @author 明快de玄米61* @date /12/18 23:22**/private static String extractPdf(String filePath) {RandomAccess rf = null;PDDocument document = null;try {rf = new RandomAccessFile(new File(filePath), "r");PDFParser parser = new PDFParser(rf);parser.parse();document = parser.getPDDocument();PDFTextStripper stripper = new PDFTextStripper();String text = stripper.getText(document);document.close();return text;} catch (Exception e) {e.printStackTrace();} finally {if (document != null) {try {document.close();} catch (IOException e) {e.printStackTrace();}}if (rf != null) {try {rf.close();} catch (IOException e) {e.printStackTrace();}}}return null;}/*** 获取xml中的文本** @param filePath 文件全路径* @return 文本* @author 明快de玄米61* @date /12/18 23:22**/private static String extractXml(String filePath) {try (InputStream in = new FileInputStream(filePath)) {Document doc = new SAXReader().read(in);return doc.asXML();} catch (Exception e) {e.printStackTrace();}return null;}}
