使用NOPI读取Word、Excel文档内容

使用NOPI读取Excel的例子很多，读取Word的例子不多。

Excel的解析方式有多中，可以使用ODBC查询，把Excel作为一个数据集对待。也可以使用文档结构模型的方式进行解析，即解析Workbook（工作簿）、Sheet、Row、Column。

Word的解析比较复杂，因为Word的文档结构模型定义较为复杂。解析Word或者Excel，关键是理解Word、Excel的文档对象模型。

Word、Excel文档对象模型的解析，可以通过COM接口调用，此类方式使用较广。（可以录制宏代码，然后替换为对应的语言）

也可以使用XML模型解析，尤其是对于2007、2010版本的文档的解析。

 using NPOI.POIFS.FileSystem;
 using NPOI.SS.UserModel;
 using NPOI.XSSF.UserModel;
 using NPOI.XWPF.UserModel;
 using System;
 using System.Collections.Generic;
 using System.Configuration;
 using System.IO;
 using System.Text;

 namespace eyuan
 {
     public static class NOPIHandler
     {
         /// <summary>
         ///
         /// </summary>
         /// <param name="fileName"></param>
         /// <returns></returns>
         public static List<List<List<string>>> ReadExcel(string fileName)
         {
             //打开Excel工作簿
             XSSFWorkbook hssfworkbook = null;
             try
             {
                 using (FileStream file = new FileStream(fileName, FileMode.Open, FileAccess.Read))
                 {
                     hssfworkbook = new XSSFWorkbook(file);
                 }
             }
             catch (Exception e)
             {
                 LogHandler.LogWrite(string.Format("文件{0}打开失败，错误：{1}", new string[] { fileName, e.ToString() }));
             }
             //循环Sheet页
             int sheetsCount = hssfworkbook.NumberOfSheets;
             List<List<List<string>>> workBookContent = new List<List<List<string>>>();
             for (int i = ; i < sheetsCount; i++)
             {
                 //Sheet索引从0开始
                 ISheet sheet = hssfworkbook.GetSheetAt(i);
                 //循环行
                 List<List<string>> sheetContent = new List<List<string>>();
                 int rowCount = sheet.PhysicalNumberOfRows;
                 for (int j = ; j < rowCount; j++)
                 {
                     //Row（逻辑行）的索引从0开始
                     IRow row = sheet.GetRow(j);
                     //循环列（各行的列数可能不同）
                     List<string> rowContent = new List<string>();
                     int cellCount = row.PhysicalNumberOfCells;
                     for (int k = ; k < cellCount; k++)
                     {
                         //ICell cell = row.GetCell(k);
                         ICell cell = row.Cells[k];
                         if (cell == null)
                         {
                             rowContent.Add("NIL");
                         }
                         else
                         {
                             rowContent.Add(cell.ToString());
                             //rowContent.Add(cell.StringCellValue);
                         }
                     }
                     //添加行到集合中
                     sheetContent.Add(rowContent);
                 }
                 //添加Sheet到集合中
                 workBookContent.Add(sheetContent);
             }

             return workBookContent;
         }

         /// <summary>
         ///
         /// </summary>
         /// <param name="fileName"></param>
         /// <returns></returns>
         public static string ReadExcelText(string fileName)
         {
             string ExcelCellSeparator = ConfigurationManager.AppSettings["ExcelCellSeparator"];
             string ExcelRowSeparator = ConfigurationManager.AppSettings["ExcelRowSeparator"];
             string ExcelSheetSeparator = ConfigurationManager.AppSettings["ExcelSheetSeparator"];
             //
             List<List<List<string>>> excelContent = ReadExcel(fileName);
             string fileText = string.Empty;
             StringBuilder sbFileText = new StringBuilder();
             //循环处理WorkBook中的各Sheet页
             List<List<List<string>>>.Enumerator enumeratorWorkBook = excelContent.GetEnumerator();
             while (enumeratorWorkBook.MoveNext())
             {

                 //循环处理当期Sheet页中的各行
                 List<List<string>>.Enumerator enumeratorSheet = enumeratorWorkBook.Current.GetEnumerator();
                 while (enumeratorSheet.MoveNext())
                 {

                     string[] rowContent = enumeratorSheet.Current.ToArray();
                     sbFileText.Append(string.Join(ExcelCellSeparator, rowContent));
                     sbFileText.Append(ExcelRowSeparator);
                 }
                 sbFileText.Append(ExcelSheetSeparator);
             }
             //
             fileText = sbFileText.ToString();
             return fileText;
         }

         /// <summary>
         /// 读取Word内容
         /// </summary>
         /// <param name="fileName"></param>
         /// <returns></returns>
         public static string ReadWordText(string fileName)
         {
             string WordTableCellSeparator = ConfigurationManager.AppSettings["WordTableCellSeparator"];
             string WordTableRowSeparator = ConfigurationManager.AppSettings["WordTableRowSeparator"];
             string WordTableSeparator = ConfigurationManager.AppSettings["WordTableSeparator"];
             //
             string CaptureWordHeader = ConfigurationManager.AppSettings["CaptureWordHeader"];
             string CaptureWordFooter = ConfigurationManager.AppSettings["CaptureWordFooter"];
             string CaptureWordTable = ConfigurationManager.AppSettings["CaptureWordTable"];
             string CaptureWordImage = ConfigurationManager.AppSettings["CaptureWordImage"];
             //
             string CaptureWordImageFileName = ConfigurationManager.AppSettings["CaptureWordImageFileName"];
             //
             string fileText = string.Empty;
             StringBuilder sbFileText = new StringBuilder();

             #region 打开文档
             XWPFDocument document = null;
             try
             {
                 using (FileStream file = new FileStream(fileName, FileMode.Open, FileAccess.Read))
                 {
                     document = new XWPFDocument(file);
                 }
             }
             catch (Exception e)
             {
                 LogHandler.LogWrite(string.Format("文件{0}打开失败，错误：{1}", new string[] { fileName, e.ToString() }));
             }
             #endregion

             #region 页眉、页脚
             //页眉
             if (CaptureWordHeader == "true")
             {
                 sbFileText.AppendLine("Capture Header Begin");
                 foreach (XWPFHeader xwpfHeader in document.HeaderList)
                 {
                     sbFileText.AppendLine(string.Format("{0}", new string[] { xwpfHeader.Text }));
                 }
                 sbFileText.AppendLine("Capture Header End");
             }
             //页脚
             if (CaptureWordFooter == "true")
             {
                 sbFileText.AppendLine("Capture Footer Begin");
                 foreach (XWPFFooter xwpfFooter in document.FooterList)
                 {
                     sbFileText.AppendLine(string.Format("{0}", new string[] { xwpfFooter.Text }));
                 }
                 sbFileText.AppendLine("Capture Footer End");
             }
             #endregion

             #region 表格
             if (CaptureWordTable == "true")
             {
                 sbFileText.AppendLine("Capture Table Begin");
                 foreach (XWPFTable table in document.Tables)
                 {
                     //循环表格行
                     foreach (XWPFTableRow row in table.Rows)
                     {
                         foreach (XWPFTableCell cell in row.GetTableCells())
                         {
                             sbFileText.Append(cell.GetText());
                             //
                             sbFileText.Append(WordTableCellSeparator);
                         }

                         sbFileText.Append(WordTableRowSeparator);
                     }
                     sbFileText.Append(WordTableSeparator);
                 }
                 sbFileText.AppendLine("Capture Table End");
             }
             #endregion

             #region 图片
             if (CaptureWordImage == "true")
             {
                 sbFileText.AppendLine("Capture Image Begin");
                 foreach (XWPFPictureData pictureData in document.AllPictures)
                 {
                     string picExtName = pictureData.suggestFileExtension();
                     string picFileName = pictureData.GetFileName();
                     byte[] picFileContent = pictureData.GetData();
                     //
                     string picTempName = string.Format(CaptureWordImageFileName, new string[] { Guid.NewGuid().ToString() + "_" + picFileName + "." + picExtName });
                     //
                     using (FileStream fs = new FileStream(picTempName, FileMode.Create, FileAccess.Write))
                     {
                         fs.Write(picFileContent, , picFileContent.Length);
                         fs.Close();
                     }
                     //
                     sbFileText.AppendLine(picTempName);
                 }
                 sbFileText.AppendLine("Capture Image End");
             }
             #endregion

             //正文段落
             sbFileText.AppendLine("Capture Paragraph Begin");
             foreach (XWPFParagraph paragraph in document.Paragraphs)
             {
                 sbFileText.AppendLine(paragraph.ParagraphText);

             }
             sbFileText.AppendLine("Capture Paragraph End");
             //

             //
             fileText = sbFileText.ToString();
             return fileText;
         }

     }
 }