【发布时间】：2012-11-11 17:09:49
【问题描述】：
我想使用 NPOI 读取 Excel Tables 2010 xlsx，然后将数据导出到 DataTables，但不知道如何使用它。谁能逐步告诉我如何将 Excel 导出到 Datatable？我已经下载了 NPOI.dll，添加到参考，但不知道还有什么...
【问题讨论】：
【发布时间】：2012-11-11 17:09:49
【问题描述】：
以下是您可以使用 NPOI 将 Excel 文件转换为 DataSet 的最少代码：
IWorkbook workbook;
using (var stream = new FileStream(excelFilePath, FileMode.Open, FileAccess.Read))
{
workbook = new HSSFWorkbook(stream); // XSSFWorkbook for XLSX
}
var sheet = workbook.GetSheetAt(0); // zero-based index of your target sheet
var dataTable = new DataTable(sheet.SheetName);
// write the header row
var headerRow = sheet.GetRow(0);
foreach (var headerCell in headerRow)
{
dataTable.Columns.Add(headerCell.ToString());
}
// write the rest
for(int i = 1; i< sheet.PhysicalNumberOfRows; i++)
{
var sheetRow = sheet.GetRow(i);
var dtRow = dataTable.NewRow();
dtRow.ItemArray = dataTable.Columns
.Cast<DataColumn>()
.Select(c => sheetRow.GetCell(c.Ordinal, MissingCellPolicy.CREATE_NULL_AS_BLANK).ToString())
.ToArray();
dataTable.Rows.Add(dtRow);
}
【讨论】：
-
不适用于不同行中的不同列大小，因此如果您有疯狂的 excel 文件，则“2015 年 9 月 4 日 9:19 LuckyS 回答”代码更好。
-
@Roger Deep 是对的，它会跳过 NULL 单元格，因此它们将具有不同的列索引，然后将被放置到不同的列中。
-
已更新以处理 NULL 单元格。
-
@SaebAmini 还有其他更快的解决方案吗？循环遍历行需要很长时间来解析 20,000 条记录。
private static ISheet GetFileStream(string fullFilePath)
{
var fileExtension = Path.GetExtension(fullFilePath);
string sheetName;
ISheet sheet = null;
switch (fileExtension)
{
case ".xlsx":
using (var fs = new FileStream(fullFilePath, FileMode.Open, FileAccess.Read))
{
var wb = new XSSFWorkbook(fs);
sheetName = wb.GetSheetAt(0).SheetName;
sheet = (XSSFSheet) wb.GetSheet(sheetName);
}
break;
case ".xls":
using (var fs = new FileStream(fullFilePath, FileMode.Open, FileAccess.Read))
{
var wb = new HSSFWorkbook(fs);
sheetName = wb.GetSheetAt(0).SheetName;
sheet = (HSSFSheet) wb.GetSheet(sheetName);
}
break;
}
return sheet;
}
private static DataTable GetRequestsDataFromExcel(string fullFilePath)
{
try
{
var sh = GetFileStream(fullFilePath);
var dtExcelTable = new DataTable();
dtExcelTable.Rows.Clear();
dtExcelTable.Columns.Clear();
var headerRow = sh.GetRow(0);
int colCount = headerRow.LastCellNum;
for (var c = 0; c < colCount; c++)
dtExcelTable.Columns.Add(headerRow.GetCell(c).ToString());
var i = 1;
var currentRow = sh.GetRow(i);
while (currentRow != null)
{
var dr = dtExcelTable.NewRow();
for (var j = 0; j < currentRow.Cells.Count; j++)
{
var cell = currentRow.GetCell(j);
if (cell != null)
switch (cell.CellType)
{
case CellType.Numeric:
dr[j] = DateUtil.IsCellDateFormatted(cell)
? cell.DateCellValue.ToString(CultureInfo.InvariantCulture)
: cell.NumericCellValue.ToString(CultureInfo.InvariantCulture);
break;
case CellType.String:
dr[j] = cell.StringCellValue;
break;
case CellType.Blank:
dr[j] = string.Empty;
break;
}
}
dtExcelTable.Rows.Add(dr);
i++;
currentRow = sh.GetRow(i);
}
return dtExcelTable;
}
catch (Exception e)
{
throw;
}
}
【讨论】：
-
读取 Excel 文件并根据扩展名 xls 或 xlsx 将其转换为 DataTable
-
小心具有多列的 excel 文件，因为这会创建具有多列的数据表 "for (var c = 0; c
-
这个例子在处理多个不同的列总计的一些更改后完美地工作。谢谢拉蒂。
-
我没有分析代码，但我认为您应该缓存
currentRow.Cells.Count部分，因为 Row 对象的属性 Cells在每次调用时从内部 Dictionary 数据创建一个List<ICell>对象。事实上，该属性并非来自 Java 中的原始 Apache POI。
您可以通过 NPOI 尝试这种简单的方法：
private DataTable GetDataTableFromExcel(String Path)
{
XSSFWorkbook wb;
XSSFSheet sh;
String Sheet_name;
using (var fs = new FileStream(Path, FileMode.Open, FileAccess.Read))
{
wb = new XSSFWorkbook(fs);
Sheet_name= wb.GetSheetAt(0).SheetName; //get first sheet name
}
DataTable DT = new DataTable();
DT.Rows.Clear();
DT.Columns.Clear();
// get sheet
sh = (XSSFSheet)wb.GetSheet(Sheet_name);
int i = 0;
while (sh.GetRow(i) != null)
{
// add neccessary columns
if (DT.Columns.Count < sh.GetRow(i).Cells.Count)
{
for (int j = 0; j < sh.GetRow(i).Cells.Count; j++)
{
DT.Columns.Add("", typeof(string));
}
}
// add row
DT.Rows.Add();
// write row value
for (int j = 0; j < sh.GetRow(i).Cells.Count; j++)
{
var cell = sh.GetRow(i).GetCell(j);
if (cell != null)
{
// TODO: you can add more cell types capatibility, e. g. formula
switch (cell.CellType)
{
case NPOI.SS.UserModel.CellType.Numeric:
DT.Rows[i][j] = sh.GetRow(i).GetCell(j).NumericCellValue;
//dataGridView1[j, i].Value = sh.GetRow(i).GetCell(j).NumericCellValue;
break;
case NPOI.SS.UserModel.CellType.String:
DT.Rows[i][j] = sh.GetRow(i).GetCell(j).StringCellValue;
break;
}
}
}
i++;
}
return DT;
}
【讨论】：
-
这也很有效，它具有“添加必要的列”检查，这对于列多于其他行的行是绝对必要的。谢谢 LuckyS，很棒的代码。
你可以通过这样做来完成你的任务。
using NPOI.SS.UserModel;
using NPOI.XSSF.UserModel;
using NPOI.Util.Collections;
using NPOI;
using System.Collections.Generic;
using NPOI.OpenXmlFormats.Spreadsheet;
using NPOI.HSSF.UserModel;
using NPOI.SS.Util;
public DataTable xlsxToDT(Stream str)
{
XSSFWorkbook hssfworkbook = new XSSFWorkbook(str);
ISheet sheet = hssfworkbook.GetSheetAt(0);
str.Close();
DataTable dt = new DataTable();
IRow headerRow = sheet.GetRow(0);
IEnumerator rows = sheet.GetRowEnumerator();
int colCount = headerRow.LastCellNum;
int rowCount = sheet.LastRowNum;
for (int c = 0; c < colCount; c++)
dt.Columns.Add(headerRow.GetCell(c).ToString());
while (rows.MoveNext())
{
IRow row = (XSSFRow)rows.Current;
DataRow dr = dt.NewRow();
for (int i = 0; i < colCount; i++)
{
ICell cell = row.GetCell(i);
if (cell != null)
dr[i] = cell.ToString();
}
dt.Rows.Add(dr);
}
return dt;
}
【讨论】：
NPOI 是一种很好的免费读取 Excel 文件的方法，现在在第 2 版中，您可以读取 XLS 和 XLSX 文件类型。
- 在他们的网站上获取最新版本的 NPOI：https://npoi.codeplex.com/
- 在您的项目中添加对以下文件的引用：NPOI.dll、NPOI.OOXML.dll 和 NPOI.OpenXml4Net.dll。
- 添加以下使用：使用 NPOI.SS.UserModel；使用 NPOI.HSSF.UserModel；使用 NPOI.XSSF.UserModel；
现在下面的代码可以解决问题了，cmets 是西班牙语，抱歉：-p
private DataTable Excel_To_DataTable(string pRutaArchivo, int pHojaIndex)
{
// --------------------------------- //
/* REFERENCIAS:
* NPOI.dll
* NPOI.OOXML.dll
* NPOI.OpenXml4Net.dll */
// --------------------------------- //
/* USING:
* using NPOI.SS.UserModel;
* using NPOI.HSSF.UserModel;
* using NPOI.XSSF.UserModel; */
// --------------------------------- //
DataTable Tabla = null;
try
{
if (System.IO.File.Exists(pRutaArchivo))
{
IWorkbook workbook = null; //IWorkbook determina se es xls o xlsx
ISheet worksheet = null;
string first_sheet_name = "";
using (FileStream FS = new FileStream(pRutaArchivo, FileMode.Open, FileAccess.Read))
{
workbook = WorkbookFactory.Create(FS); //Abre tanto XLS como XLSX
worksheet = workbook.GetSheetAt(pHojaIndex); //Obtener Hoja por indice
first_sheet_name = worksheet.SheetName; //Obtener el nombre de la Hoja
Tabla = new DataTable(first_sheet_name);
Tabla.Rows.Clear();
Tabla.Columns.Clear();
// Leer Fila por fila desde la primera
for (int rowIndex = 0; rowIndex <= worksheet.LastRowNum; rowIndex++)
{
DataRow NewReg = null;
IRow row = worksheet.GetRow(rowIndex);
IRow row2 = null;
if (row != null) //null is when the row only contains empty cells
{
if (rowIndex > 0) NewReg = Tabla.NewRow();
//Leer cada Columna de la fila
foreach (ICell cell in row.Cells)
{
object valorCell = null;
string cellType = "";
if (rowIndex == 0) //Asumo que la primera fila contiene los titlos:
{
row2 = worksheet.GetRow(rowIndex + 1); //Si es la rimera fila, obtengo tambien la segunda para saber los tipos:
ICell cell2 = row2.GetCell(cell.ColumnIndex);
switch (cell2.CellType)
{
case CellType.Boolean: cellType = "System.Boolean"; break;
case CellType.String: cellType = "System.String"; break;
case CellType.Numeric:
if (HSSFDateUtil.IsCellDateFormatted(cell2)) { cellType = "System.DateTime"; }
else { cellType = "System.Double"; } break;
case CellType.Formula:
switch (cell2.CachedFormulaResultType)
{
case CellType.Boolean: cellType = "System.Boolean"; break;
case CellType.String: cellType = "System.String"; break;
case CellType.Numeric:
if (HSSFDateUtil.IsCellDateFormatted(cell2)) { cellType = "System.DateTime"; }
else { cellType = "System.Double"; } break;
}
break;
default:
cellType = "System.String"; break;
}
//Agregar los campos de la tabla:
DataColumn codigo = new DataColumn(cell.StringCellValue, System.Type.GetType(cellType));
Tabla.Columns.Add(codigo);
}
else
{
//Las demas filas son registros:
switch (cell.CellType)
{
case CellType.Blank: valorCell = DBNull.Value; break;
case CellType.Boolean: valorCell = cell.BooleanCellValue; break;
case CellType.String: valorCell = cell.StringCellValue; break;
case CellType.Numeric:
if (HSSFDateUtil.IsCellDateFormatted(cell)) { valorCell = cell.DateCellValue; }
else { valorCell = cell.NumericCellValue; } break;
case CellType.Formula:
switch (cell.CachedFormulaResultType)
{
case CellType.Blank: valorCell = DBNull.Value; break;
case CellType.String: valorCell = cell.StringCellValue; break;
case CellType.Boolean: valorCell = cell.BooleanCellValue; break;
case CellType.Numeric:
if (HSSFDateUtil.IsCellDateFormatted(cell)) { valorCell = cell.DateCellValue; }
else { valorCell = cell.NumericCellValue; }
break;
}
break;
default: valorCell = cell.StringCellValue; break;
}
NewReg[cell.ColumnIndex] = valorCell;
}
}
}
if (rowIndex > 0) Tabla.Rows.Add(NewReg);
}
Tabla.AcceptChanges();
}
}
else
{
throw new Exception("ERROR 404: El archivo especificado NO existe.");
}
}
catch (Exception ex)
{
throw ex;
}
return Tabla;
}
上面的代码假设工作表的第一行有列名。 该代码还确定每个单元格的数据类型，并尝试将其转换为 ADO 数据类型。空白单元格被转换为 null。
希望这对您和处于相同情况的其他人有所帮助。
【讨论】：
我编辑了@Saeb Amini 代码以允许空白单元格。
IWorkbook workbook;
using (FileStream stream = new FileStream(excelFilePath, FileMode.Open, FileAccess.Read))
{
workbook = new HSSFWorkbook(stream);
}
ISheet sheet = workbook.GetSheetAt(0);
DataTable dt = new DataTable(sheet.SheetName);
// write header row
IRow headerRow = sheet.GetRow(0);
foreach (ICell headerCell in headerRow)
{
dt.Columns.Add(headerCell.ToString());
}
// write the rest
int rowIndex = 0;
foreach (IRow row in sheet)
{
// skip header row
if (rowIndex++ == 0) continue;
// add row into datatable
var cells = new List<ICell>();
for (int i = 0; i < dt.Columns.Count; i++)
{
cells.Add(row.GetCell(i, MissingCellPolicy.CREATE_NULL_AS_BLANK));
}
// Columns formatted as DateTime will be printed as '01-Jul-2005',
// which can be converted to datetime in the SQL server.
// select cast('01-Jul-2005' as DateTime).
// In SQL Server we can convert DateTime to whatever string we want, for example
// select convert(nvarchar(255), cast('01-Jul-2005' as datetime), 112) will print '20050701'.
// http://www.sqlusa.com/bestpractices/datetimeconversion/
dt.Rows.Add(cells.Select(c => c.ToString()).ToArray());
// Datetimes also can be reformatted directly like this :
// dt.Rows.Add(cells.Select(c =>
// c.CellType == CellType.Numeric && DateUtil.IsCellDateFormatted(c)
// ? c.DateCellValue.ToString("yyyyMMdd")
// : c.ToString()
// ).ToArray());
}
//return dt;
【讨论】：
在 Codeplex 网站 here 的下载部分有 example package - 一组 C# 示例。如果您还没有尝试过，请尝试一下。
这是最简单的例子 -
using NPOI.HSSF.UserModel;
using NPOI.SS.UserModel;
//.....
private void button1_Click(object sender, EventArgs e)
{
HSSFWorkbook hssfwb;
using (FileStream file = new FileStream(@"c:\test.xls", FileMode.Open, FileAccess.Read))
{
hssfwb= new HSSFWorkbook(file);
}
ISheet sheet = hssfwb.GetSheet("Arkusz1");
for (int row = 0; row <= sheet.LastRowNum; row++)
{
if (sheet.GetRow(row) != null) //null is when the row only contains empty cells
{
MessageBox.Show(string.Format("Row {0} = {1}", row, sheet.GetRow(row).GetCell(0).StringCellValue));
}
}
}
【讨论】：
-
我试过了，但我得到了错误：OfficeXMLFileException 而不是 HSSF 我应该使用 XSSF，所以我将 HSSFWorkbook 更改为 XSSFWorkbook 但它不起作用
基于@Sean's GREAT Answer 和example of NPOI，我将方法写到Convert all worksheets in xls file to DataSet 和Convert DataSet back to xls file：
public static DataSet GetDataSetFromXls(string excelFilePath)
{
IWorkbook workbook;
using (FileStream stream = new FileStream(excelFilePath, FileMode.Open, FileAccess.Read))
{
workbook = new HSSFWorkbook(stream); //2003 xls
//workbook = new XSSFWorkbook(); //2007 xlsx
}
DataSet ds = new DataSet();
for (int i = 0; i < workbook.NumberOfSheets; i++)
{
ISheet sheet = workbook.GetSheetAt(i); // zero-based index of your target sheet
DataTable dt = new DataTable(sheet.SheetName);
// write header row
IRow headerRow = sheet.GetRow(0);
foreach (ICell headerCell in headerRow)
{
dt.Columns.Add(headerCell.ToString());
}
// write the rest
int rowIndex = 0;
foreach (IRow row in sheet)
{
// skip header row
if (rowIndex++ == 0) continue;
DataRow dataRow = dt.NewRow();
dataRow.ItemArray = row.Cells.Select(c => c.ToString()).ToArray();
dt.Rows.Add(dataRow);
}
ds.Tables.Add(dt);
}
return ds;
}
public static void SaveDataSetToXls(DataSet ds, string savedExcelFilePath)
{
//IWorkbook workbook = new XSSFWorkbook();
IWorkbook workbook = new HSSFWorkbook();
foreach (DataTable dt in ds.Tables)
{
ISheet sheet = workbook.CreateSheet(dt.TableName);
var row0 = sheet.CreateRow(0);//header
for (int j = 0; j < dt.Columns.Count; j++)
{
row0.CreateCell(j).SetCellValue(dt.Columns[j].ColumnName);
}
for (int i = 0; i < dt.Rows.Count; i++)//rest
{
var row = sheet.CreateRow(1+i);
for (int j = 0; j < dt.Columns.Count; j++)
row.CreateCell(j).SetCellValue(dt.Rows[i][j].ToString());
}
}
FileStream sw = File.Create(savedExcelFilePath);
workbook.Write(sw);
sw.Close();
}
【讨论】：
您可以在 Toxy 项目中尝试 ToxySpreadsheet - https://github.com/nissl-lab/toxy。 ToxySpreadsheet.ToDataSet() 就是你想要的。
【讨论】：
【讨论】：
我知道我在这里有点晚了，但我认为这可能对其他人有所帮助
我开发了一个使用 NPOI 包的 excel 实用程序，它可以
- 只需获取您的数据表或集合
- 并返回您的 excel，同时在 excel 中保持所有数据表/列表数据类型不变。
Github 代码仓库：https://github.com/ansaridawood/.NET-Generic-Excel-Export-Sample/tree/master/GenericExcelExport/ExcelExport
找代码解释，可以在这里找到： https://www.codeproject.com/Articles/1241654/Export-to-Excel-using-NPOI-Csharp-and-WEB-API
它使用 NPOI DLL，它有 2 个 cs 文件要包含，然后你就可以开始了
下面是第一个参考文件AbstractDataExport.cs：
using NPOI.SS.UserModel;
using NPOI.XSSF.UserModel;
using System;
using System.Collections.Generic;
using System.IO;
using System.Net;
using System.Net.Http;
using System.Net.Http.Headers;
namespace GenericExcelExport.ExcelExport
{
public interface IAbstractDataExport
{
HttpResponseMessage Export(List exportData, string fileName, string sheetName);
}
public abstract class AbstractDataExport : IAbstractDataExport
{
protected string _sheetName;
protected string _fileName;
protected List _headers;
protected List _type;
protected IWorkbook _workbook;
protected ISheet _sheet;
private const string DefaultSheetName = "Sheet1";
public HttpResponseMessage Export
(List exportData, string fileName, string sheetName = DefaultSheetName)
{
_fileName = fileName;
_sheetName = sheetName;
_workbook = new XSSFWorkbook(); //Creating New Excel object
_sheet = _workbook.CreateSheet(_sheetName); //Creating New Excel Sheet object
var headerStyle = _workbook.CreateCellStyle(); //Formatting
var headerFont = _workbook.CreateFont();
headerFont.IsBold = true;
headerStyle.SetFont(headerFont);
WriteData(exportData); //your list object to NPOI excel conversion happens here
//Header
var header = _sheet.CreateRow(0);
for (var i = 0; i < _headers.Count; i++)
{
var cell = header.CreateCell(i);
cell.SetCellValue(_headers[i]);
cell.CellStyle = headerStyle;
}
for (var i = 0; i < _headers.Count; i++)
{
_sheet.AutoSizeColumn(i);
}
using (var memoryStream = new MemoryStream()) //creating memoryStream
{
_workbook.Write(memoryStream);
var response = new HttpResponseMessage(HttpStatusCode.OK)
{
Content = new ByteArrayContent(memoryStream.ToArray())
};
response.Content.Headers.ContentType = new MediaTypeHeaderValue
("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet");
response.Content.Headers.ContentDisposition =
new ContentDispositionHeaderValue("attachment")
{
FileName = $"{_fileName}_{DateTime.Now.ToString("yyyyMMddHHmmss")}.xlsx"
};
return response;
}
}
//Generic Definition to handle all types of List
public abstract void WriteData(List exportData);
}
}
这是第二个也是最后一个文件AbstractDataExportBridge.cs：
using NPOI.SS.UserModel;
using System;
using System.Collections.Generic;
using System.ComponentModel;
using System.Data;
using System.Text.RegularExpressions;
namespace GenericExcelExport.ExcelExport
{
public class AbstractDataExportBridge : AbstractDataExport
{
public AbstractDataExportBridge()
{
_headers = new List<string>();
_type = new List<string>();
}
public override void WriteData<T>(List<T> exportData)
{
PropertyDescriptorCollection properties = TypeDescriptor.GetProperties(typeof(T));
DataTable table = new DataTable();
foreach (PropertyDescriptor prop in properties)
{
var type = Nullable.GetUnderlyingType(prop.PropertyType) ?? prop.PropertyType;
_type.Add(type.Name);
table.Columns.Add(prop.Name, Nullable.GetUnderlyingType(prop.PropertyType) ??
prop.PropertyType);
string name = Regex.Replace(prop.Name, "([A-Z])", " $1").Trim(); //space separated
//name by caps for header
_headers.Add(name);
}
foreach (T item in exportData)
{
DataRow row = table.NewRow();
foreach (PropertyDescriptor prop in properties)
row[prop.Name] = prop.GetValue(item) ?? DBNull.Value;
table.Rows.Add(row);
}
IRow sheetRow = null;
for (int i = 0; i < table.Rows.Count; i++)
{
sheetRow = _sheet.CreateRow(i + 1);
for (int j = 0; j < table.Columns.Count; j++)
{
ICell Row1 = sheetRow.CreateCell(j);
string type = _type[j].ToLower();
var currentCellValue = table.Rows[i][j];
if (currentCellValue != null &&
!string.IsNullOrEmpty(Convert.ToString(currentCellValue)))
{
if (type == "string")
{
Row1.SetCellValue(Convert.ToString(currentCellValue));
}
else if (type == "int32")
{
Row1.SetCellValue(Convert.ToInt32(currentCellValue));
}
else if (type == "double")
{
Row1.SetCellValue(Convert.ToDouble(currentCellValue));
}
}
else
{
Row1.SetCellValue(string.Empty);
}
}
}
}
}
}
详细解释请参考开头提供的链接。
【讨论】：