public string readWORD(object filepath){string filename = Convert.ToString(filepath);Microsoft.Office.Interop.Word.Application wordapp = new Microsoft.Office.Interop.Word.Application();object isreadonly = true;object nullobj = System.Reflection.Missing.Value;object missingValue = Type.Missing;object miss = System.Reflection.Missing.Value;object saveChanges = WdSaveOptions.wdDoNotSaveChanges;Microsoft.Office.Interop.Word._Document doc = wordapp.Documents.Open(ref filename, ref nullobj, ref isreadonly);string content = doc.Content.Text;doc.Close(ref saveChanges, ref missingValue, ref missingValue);wordapp.Quit(ref saveChanges, ref miss, ref miss);wordapp = null;return content;}

public DataSet ExcelToDS(string Path)
{
string strConn = "Provider=Microsoft.Jet.OLEDB.4.0;" +"Data Source="+ Path +";"+"Extended Properties=Excel 8.0;";
OleDbConnection conn = new OleDbConnection(strConn);
conn.Open();
string strExcel = "";
OleDbDataAdapter myCommand = null;
DataSet ds = null;
strExcel="select * from [sheet1$]";
myCommand = new OleDbDataAdapter(strExcel, strConn);
ds = new DataSet();
myCommand.Fill(ds,"table1");
return ds;
} 对于EXCEL中的表即sheet([sheet1$])如果不是固定的可以使用下面的方法得到
string strConn = "Provider=Microsoft.Jet.OLEDB.4.0;" +"Data Source="+ Path +";"+"Extended Properties=Excel 8.0;";
OleDbConnection conn = new OleDbConnection(strConn);
DataTable schemaTable = objConn.GetOleDbSchemaTable(System.Data.OleDb.OleDbSchemaGuid.Tables,null);
string tableName=schemaTable.Rows[0][2].ToString().Trim();   

        public string readPPT(object filepath){string file = filepath.ToString();Microsoft.Office.Interop.PowerPoint.Application pa = new Microsoft.Office.Interop.PowerPoint.Application();Microsoft.Office.Interop.PowerPoint.Presentation pp = pa.Presentations.Open(file, Microsoft.Office.Core.MsoTriState.msoTrue, Microsoft.Office.Core.MsoTriState.msoFalse, Microsoft.Office.Core.MsoTriState.msoFalse);string content = "";foreach (Microsoft.Office.Interop.PowerPoint.Slide slide in pp.Slides){foreach (Microsoft.Office.Interop.PowerPoint.Shape shape in slide.Shapes)content += shape.TextFrame.TextRange.Text.ToString();}pa.Quit();pp.Close();pa = null;return content;}

        /// <summary>/// 读取各类文档内容/// </summary>/// <param name="filepath">文档路径</param>/// <param name="filename">文档名称</param>/// <returns></returns>public string textToreader(string filepath, object filename){string content = null;FileInfo file = new FileInfo(filename.ToString());switch (file.Extension.ToLower()){case ".txt":content = readTXT(filepath);break;case ".doc":content = readWORD(filepath);break;case ".docx":content = readWORDX(filepath);break;case ".xls":content = readEXCEL(filepath);break;case ".xlsx":content = readEXCELX(filepath);break;case ".pdf":content = readPDF(filepath);break;case ".ppt":content = readPPT(filepath);break;}return content;}/// <summary>/// 读取txt/// </summary>/// <param name="filepath"></param>/// <returns></returns>public string readTXT(string filepath){StreamReader st = new StreamReader(filepath, Encoding.GetEncoding("gb2312"));string content = st.ReadToEnd();return content;}/// <summary>/// 读取word2003/// </summary>/// <param name="filepath"></param>/// <returns></returns>public string readWORD(string filepath){FileInputStream fs = new FileInputStream(filepath);HWPFDocument doc = new HWPFDocument(fs);string content = doc.getDocumentText();return content;}/// <summary>/// 读取word2007/// </summary>/// <param name="filepath"></param>/// <returns></returns>public string readWORDX(string filepath){FileInputStream fs = new FileInputStream(filepath);XWPFDocument XDocument = new XWPFDocument(fs);XWPFWordExtractor doc = new XWPFWordExtractor(XDocument);string content = doc.getText();return content;}/// <summary>/// 读取excel2003/// </summary>/// <param name="filepath"></param>/// <returns></returns>public string readEXCEL(object filepath){string filename = filepath.ToString();FileStream fs = new FileStream(filename, FileMode.Open, FileAccess.Read, FileShare.ReadWrite);//读取流POIFSFileSystem ps = new POIFSFileSystem(fs);HSSFWorkbook hwb = new HSSFWorkbook(ps);ExcelExtractor extractor = new ExcelExtractor(hwb);extractor.FormulasNotResults = true;extractor.IncludeSheetNames = true;string content = extractor.Text;return content;}/// <summary>/// 读取excel2007/// </summary>/// <param name="filepath"></param>/// <returns></returns>public string readEXCELX(string filepath){//FileStream fs = new FileStream(filepath, FileMode.Open, FileAccess.Read, FileShare.ReadWrite);//读取流FileInputStream fis = new FileInputStream(filepath);//POIFSFileSystem ps = new POIFSFileSystem(fs);XSSFWorkbook hwb = new XSSFWorkbook(fis);XSSFExcelExtractor extractor = new XSSFExcelExtractor(hwb);string content = extractor.getText();return content;}/// <summary>/// 读取pdf/// </summary>/// <param name="filepath"></param>/// <returns></returns>public string readPDF(string filepath){PDDocument doc = PDDocument.load(filepath);PDFTextStripper pdfStripper = new PDFTextStripper();string content = pdfStripper.getText(doc);doc.close();return content;}/// <summary>/// 读取ppt2003/// </summary>/// <param name="filepath"></param>/// <returns></returns>public string readPPT(string filepath){FileInputStream fs = new FileInputStream(filepath);SlideShow ss = new SlideShow(new HSLFSlideShow(fs));Slide[] slides = ss.getSlides();// 获得每一张幻灯片string content = "";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 += t[j].getText();}}return content;}

        /// <summary>/// 读取word2007,excel2003/2007,ppt2003/2007/// </summary>/// <param name="filepath"></param>/// <returns></returns>public  string ReadOfficeText(string filepath){//docx 、pptx 、xlsx、 ppt 、xlsFileInputStream fs = new FileInputStream(filepath);POITextExtractor extractor = ExtractorFactory.createExtractor(fs);string text = extractor.getText();return text;}