java读取office文档demo

import java.io.BufferedReader; import java.io.File; import java.io.FileInputStream; import java.io.IOException; import java.io.InputStreamReader; import java.io.UnsupportedEncodingException; import org.apache.pdfbox.pdmodel.PDDocument; import org.apache.pdfbox.text.PDFTextStripper; import org.apache.poi.POITextExtractor; import org.apache.poi.extractor.ExtractorFactory; import org.apache.poi.hssf.extractor.ExcelExtractor; import org.apache.poi.hssf.usermodel.HSSFWorkbook; import org.apache.poi.hwpf.extractor.WordExtractor; import org.apache.poi.poifs.filesystem.POIFSFileSystem; import org.apache.poi.xssf.extractor.XSSFExcelExtractor; import org.apache.poi.xssf.usermodel.XSSFWorkbook; import org.apache.poi.xwpf.extractor.XWPFWordExtractor; import org.apache.poi.xwpf.usermodel.XWPFDocument; public class StartPoi { public static String textToreader(String strFilePath) { String content = ""; String strPostFix = strFilePath.substring(strFilePath.lastIndexOf(".")+1); if (strPostFix.equalsIgnoreCase("doc")) { content = readWORD(strFilePath); } else if (strPostFix.equalsIgnoreCase("docx")) { content = readWORDX(strFilePath); } else if (strPostFix.equalsIgnoreCase("xls")) { content = readEXCEL(strFilePath); } else if (strPostFix.equalsIgnoreCase("xlsx")) { content = readEXCELX(strFilePath); } else if (strPostFix.equalsIgnoreCase("pdf")) { content = readPDF(strFilePath); } else if (strPostFix.equalsIgnoreCase("ppt")) { content = readPPT(strFilePath); } else if (strPostFix.equalsIgnoreCase("pptx")) { content = readPPTX(strFilePath); } else { content = "invalid file type!\n"; } return content; } //xml or html public static String readXMLorHTML(String strFilePath) { BufferedReader br = null; try { br = new BufferedReader(new InputStreamReader(new FileInputStream(strFilePath))); StringBuffer sb = new StringBuffer(); String data = null; while ((data = br.readLine()) != null) { sb.append(data); } return sb.toString(); } catch (IOException e) { //e.printStackTrace(); } finally { try { br.close(); } catch (Exception e) { e.printStackTrace(); } } return "error"; } // txt public static String readTXT(String strFilePath) { BufferedReader br = null; try { br = new BufferedReader(new InputStreamReader(new FileInputStream(strFilePath), "gbk")); StringBuffer sb = new StringBuffer(); String data = null; while ((data = br.readLine()) != null) { sb.append(data); } System.out.println(sb.length()); return sb.toString(); } catch (IOException e) { //e.printStackTrace(); } finally { try { br.close(); } catch (Exception e) { e.printStackTrace(); } } return "error"; } // doc public static String readWORD(String strFilePath) { FileInputStream fs = null; WordExtractor word = null; //String content = ""; try { fs = new FileInputStream(strFilePath); word = new WordExtractor(fs); String text = word.getText(); text = text.replaceAll("(\\r\\n){2,}", "\r\n"); text = text.replaceAll("(\\n){2,}", "\n"); fs.close(); return text; } catch (Exception e) { //e.printStackTrace(); } finally { if (word != null) { try { word.close(); } catch (IOException e) { e.printStackTrace(); } } if (fs != null) { try { fs.close(); } catch (IOException e) { e.printStackTrace(); } } } return "error"; } // docx public static String readWORDX(String strFilePath) { FileInputStream fs = null; XWPFWordExtractor doc = null; try { fs = new FileInputStream(strFilePath); XWPFDocument XDocument = new XWPFDocument(fs); doc = new XWPFWordExtractor(XDocument); String str = doc.getText(); doc.close(); return str; } catch (Exception e) { //e.printStackTrace(); } finally { if (doc != null) { try { doc.close(); } catch (IOException e) { e.printStackTrace(); } } if (fs != null) { try { fs.close(); } catch (IOException e) { e.printStackTrace(); } } } return "error"; } //xls public static String readEXCEL(String strFilePath) { FileInputStream fs = null; HSSFWorkbook wb = null; ExcelExtractor extractor = null; //String content = ""; try { fs = new FileInputStream(strFilePath); wb = new HSSFWorkbook(new POIFSFileSystem(fs)); extractor = new ExcelExtractor(wb); extractor.setFormulasNotResults(false); extractor.setIncludeSheetNames(true); String str = extractor.getText(); //content = changeCharSet(str, "UTF-8"); extractor.close(); return str; } catch (Exception e) { //e.printStackTrace(); } finally { if (extractor != null) { try { extractor.close(); } catch (IOException e) { e.printStackTrace(); } } if (fs != null) { try { fs.close(); } catch (IOException e) { e.printStackTrace(); } } } return "error"; } // xlsx public static String readEXCELX(String strFilePath) { FileInputStream fs = null; XSSFWorkbook hwb = null; XSSFExcelExtractor extractor = null; //String content = ""; try { fs = new FileInputStream(strFilePath); hwb = new XSSFWorkbook(fs); extractor = new XSSFExcelExtractor(hwb); String str = extractor.getText(); //content = changeCharSet(str, "UTF-8"); extractor.close(); return str; } catch (Exception e) { //e.printStackTrace(); } finally { if (extractor != null) { try { fs.close(); extractor.close(); } catch (IOException e) { e.printStackTrace(); } } if (fs != null) { try { fs.close(); } catch (IOException e) { e.printStackTrace(); } } } return "error"; } // pdf public static String readPDF(String strFilePath) { File file = new File(strFilePath); PDDocument doc = null; PDFTextStripper pdfStripper = null; try { doc = PDDocument.load(file); pdfStripper = new PDFTextStripper(); String str = pdfStripper.getText(doc); //content = changeCharSet(str, "UTF-8"); doc.close(); return str; } catch (Exception e) { //e.printStackTrace(); } finally { if (doc != null) { try { doc.close(); } catch (IOException e) { e.printStackTrace(); } } } return "error"; } // ppt public static String readPPT(String strFilePath) { FileInputStream fs = null; POITextExtractor extractor = null; //String content = ""; try { fs = new FileInputStream(strFilePath); extractor = ExtractorFactory.createExtractor(fs); String str = extractor.getText(); //content = changeCharSet(str, "UTF-8"); extractor.close(); return str; } catch (Exception e) { //e.printStackTrace(); } finally { if (extractor != null) { try { extractor.close(); } catch (IOException e) { e.printStackTrace(); } } if (fs != null) { try { fs.close(); } catch (IOException e) { e.printStackTrace(); } } } return "error"; } // pptx public static String readPPTX(String strFilePath) { FileInputStream fs = null; POITextExtractor extractor = null; //String content = ""; try { fs = new FileInputStream(strFilePath); extractor = ExtractorFactory.createExtractor(fs); String str = extractor.getText(); //content = changeCharSet(str, "UTF-8"); extractor.close(); return str; } catch (Exception e) { //e.printStackTrace(); } finally { if (extractor != null) { try { extractor.close(); } catch (IOEx