35

我正在尝试将 Excel 文件读入 Data.DataTable 列表，尽管使用我当前的方法可能需要很长时间。我基本上是逐个工作表，逐个单元格地去工作，而且往往需要很长时间。有没有更快的方法来做到这一点？这是我的代码：

    List<DataTable> List = new List<DataTable>();

    // Counting sheets
    for (int count = 1; count < WB.Worksheets.Count; ++count)
    {
        // Create a new DataTable for every Worksheet
        DATA.DataTable DT = new DataTable();

        WS = (EXCEL.Worksheet)WB.Worksheets.get_Item(count);

        textBox1.Text = count.ToString();

        // Get range of the worksheet
        Range = WS.UsedRange;


        // Create new Column in DataTable
        for (cCnt = 1; cCnt <= Range.Columns.Count; cCnt++)
        {
            textBox3.Text = cCnt.ToString();


                Column = new DataColumn();
                Column.DataType = System.Type.GetType("System.String");
                Column.ColumnName = cCnt.ToString();
                DT.Columns.Add(Column);

            // Create row for Data Table
            for (rCnt = 0; rCnt <= Range.Rows.Count; rCnt++)
            {
                textBox2.Text = rCnt.ToString();

                try
                {
                    cellVal = (string)(Range.Cells[rCnt, cCnt] as EXCEL.Range).Value2;
                }
                catch (Microsoft.CSharp.RuntimeBinder.RuntimeBinderException)
                {
                    ConvertVal = (double)(Range.Cells[rCnt, cCnt] as EXCEL.Range).Value2;
                    cellVal = ConvertVal.ToString();
                }

                // Add to the DataTable
                if (cCnt == 1)
                {

                    Row = DT.NewRow();
                    Row[cCnt.ToString()] = cellVal;
                    DT.Rows.Add(Row);
                }
                else
                {

                    Row = DT.Rows[rCnt];
                    Row[cCnt.ToString()] = cellVal;

                }
            }
        }
        // Add DT to the list. Then go to the next sheet in the Excel Workbook
        List.Add(DT);
    }
4

7 回答 7

23

校准.Value2是一项昂贵的操作，因为它是一个 COM 互操作调用。相反，我会将整个范围读入一个数组，然后遍历该数组：

object[,] data = Range.Value2;

// Create new Column in DataTable
for (int cCnt = 1; cCnt <= Range.Columns.Count; cCnt++)
{
    textBox3.Text = cCnt.ToString();

    var Column = new DataColumn();
    Column.DataType = System.Type.GetType("System.String");
    Column.ColumnName = cCnt.ToString();
    DT.Columns.Add(Column);

    // Create row for Data Table
    for (int rCnt = 1; rCnt <= Range.Rows.Count; rCnt++)
    {
        textBox2.Text = rCnt.ToString();

        string CellVal = String.Empty;
        try
        {
            cellVal = (string)(data[rCnt, cCnt]);
        }
        catch (Microsoft.CSharp.RuntimeBinder.RuntimeBinderException)
        {
            ConvertVal = (double)(data[rCnt, cCnt]);
            cellVal = ConvertVal.ToString();
        }

        DataRow Row;

        // Add to the DataTable
        if (cCnt == 1)
        {

            Row = DT.NewRow();
            Row[cCnt.ToString()] = cellVal;
            DT.Rows.Add(Row);
        }
        else
        {

            Row = DT.Rows[rCnt + 1];
            Row[cCnt.ToString()] = cellVal;

        }
    }
}
于 2013-07-10T17:40:04.487 回答
8

以防其他人使用 EPPlus。这个实现非常幼稚，但是有一些评论引起了人们的注意。如果您要GetWorkbookAsDataSet()在顶部再添加一种方法，它将满足 OP 的要求。

    /// <summary>
    /// Assumption: Worksheet is in table format with no weird padding or blank column headers.
    /// 
    /// Assertion: Duplicate column names will be aliased by appending a sequence number (eg. Column, Column1, Column2)
    /// </summary>
    /// <param name="worksheet"></param>
    /// <returns></returns>
    public static DataTable GetWorksheetAsDataTable(ExcelWorksheet worksheet)
    {
        var dt = new DataTable(worksheet.Name);
        dt.Columns.AddRange(GetDataColumns(worksheet).ToArray());
        var headerOffset = 1; //have to skip header row
        var width = dt.Columns.Count;
        var depth = GetTableDepth(worksheet, headerOffset);
        for (var i = 1; i <= depth; i++)
        {
            var row = dt.NewRow();
            for (var j = 1; j <= width; j++)
            {
                var currentValue = worksheet.Cells[i + headerOffset, j].Value;

                //have to decrement b/c excel is 1 based and datatable is 0 based.
                row[j - 1] = currentValue == null ? null : currentValue.ToString();
            }

            dt.Rows.Add(row);
        }

        return dt;
    }

    /// <summary>
    /// Assumption: There are no null or empty cells in the first column
    /// </summary>
    /// <param name="worksheet"></param>
    /// <returns></returns>
    private static int GetTableDepth(ExcelWorksheet worksheet, int headerOffset)
    {
        var i = 1;
        var j = 1;
        var cellValue = worksheet.Cells[i + headerOffset, j].Value;
        while (cellValue != null)
        {
            i++;
            cellValue = worksheet.Cells[i + headerOffset, j].Value;
        }

        return i - 1; //subtract one because we're going from rownumber (1 based) to depth (0 based)
    }

    private static IEnumerable<DataColumn> GetDataColumns(ExcelWorksheet worksheet)
    {
        return GatherColumnNames(worksheet).Select(x => new DataColumn(x));
    }

    private static IEnumerable<string> GatherColumnNames(ExcelWorksheet worksheet)
    {
        var columns = new List<string>();

        var i = 1;
        var j = 1;
        var columnName = worksheet.Cells[i, j].Value;
        while (columnName != null)
        {
            columns.Add(GetUniqueColumnName(columns, columnName.ToString()));
            j++;
            columnName = worksheet.Cells[i, j].Value;
        }

        return columns;
    }

    private static string GetUniqueColumnName(IEnumerable<string> columnNames, string columnName)
    {
        var colName = columnName;
        var i = 1;
        while (columnNames.Contains(colName))
        {
            colName = columnName + i.ToString();
            i++;
        }

        return colName;
    }
于 2016-08-08T21:28:09.330 回答
4

请查看以下链接

http://www.codeproject.com/Questions/376355/import-MS-Excel-to-datatable（已发布 6 个解决方案）

将 Excel 工作表读入数据表的最佳/最快方法？

于 2013-07-10T17:36:13.200 回答
3

MS Office Interop 很慢，甚至微软也不推荐在服务器端使用 Interop，也不能用于导入大型 Excel 文件。有关更多详细信息，请参阅为什么不从 Microsoft 的角度使用 OLE 自动化。

相反，您可以使用任何 Excel 库，例如EasyXLS。这是一个代码示例，展示了如何读取 Excel 文件：

ExcelDocument workbook = new ExcelDocument();
DataSet ds = workbook.easy_ReadXLSActiveSheet_AsDataSet("excel.xls");
DataTable dataTable = ds.Tables[0];

如果您的 Excel 文件有多个工作表或仅用于导入单元格范围（以获得更好的性能），请查看有关如何使用 EasyXLS 将 Excel 导入 C# 中的 DataTable 的更多代码示例。

于 2014-12-17T13:05:52.463 回答
2

我知道这是一个老话题，但是MiniExcel库有一种简单快捷的方法，比如下面的代码

    var filePath = @".....demo.xlsx";
    
    List<DataTable> list = new List<DataTable>();
    var sheets = MiniExcel.GetSheetNames(filePath);
    foreach (var sheetName in MiniExcel.GetSheetNames(filePath))
        list.Add(MiniExcel.QueryAsDataTable(filePath,true,sheetName:sheetName));

此致

在此处输入图像描述

于 2022-01-22T05:58:05.570 回答
2 
Dim sSheetName As String
Dim sConnection As String
Dim dtTablesList As DataTable
Dim oleExcelCommand As OleDbCommand
Dim oleExcelReader As OleDbDataReader
Dim oleExcelConnection As OleDbConnection

sConnection = "Provider=Microsoft.ACE.OLEDB.12.0;Data Source=C:\Test.xls;Extended Properties=""Excel 12.0;HDR=No;IMEX=1"""

oleExcelConnection = New OleDbConnection(sConnection)
oleExcelConnection.Open()

dtTablesList = oleExcelConnection.GetSchema("Tables")

If dtTablesList.Rows.Count > 0 Then
    sSheetName = dtTablesList.Rows(0)("TABLE_NAME").ToString
End If

dtTablesList.Clear()
dtTablesList.Dispose()

If sSheetName <> "" Then

    oleExcelCommand = oleExcelConnection.CreateCommand()
    oleExcelCommand.CommandText = "Select * From [" & sSheetName & "]"
    oleExcelCommand.CommandType = CommandType.Text

    oleExcelReader = oleExcelCommand.ExecuteReader

    nOutputRow = 0

    While oleExcelReader.Read

    End While

    oleExcelReader.Close()

End If

oleExcelConnection.Close()
于 2016-11-28T18:44:59.730 回答
1 
 class DataReader
    {
        Excel.Application xlApp;
        Excel.Workbook xlBook;
        Excel.Range xlRange;
        Excel.Worksheet xlSheet;
        public DataTable GetSheetDataAsDataTable(String filePath, String sheetName)
        {
            DataTable dt = new DataTable();
            try
            {
                xlApp = new Excel.Application();
                xlBook = xlApp.Workbooks.Open(filePath);
                xlSheet = xlBook.Worksheets[sheetName];
                xlRange = xlSheet.UsedRange;
                DataRow row=null;
                for (int i = 1; i <= xlRange.Rows.Count; i++)
                {
                    if (i != 1)
                        row = dt.NewRow();
                    for (int j = 1; j <= xlRange.Columns.Count; j++)
                    {
                        if (i == 1)
                            dt.Columns.Add(xlRange.Cells[1, j].value);
                        else
                            row[j-1] = xlRange.Cells[i, j].value;
                    }
                    if(row !=null)
                        dt.Rows.Add(row);
                }
            }
            catch (Exception ex)
            {
                Console.WriteLine(ex.Message);
            }
            finally
            {
                xlBook.Close();
                xlApp.Quit();
            }
            return dt;
        }
    }
于 2018-11-17T13:33:38.087 回答