我使用的是 Visual Studio 2008，我需要使用 Open XML SDK 2.0 从 Excel 工作表创建
DataTable有人有示例代码或链接可以帮助我做到这一点吗？
我认为这应该满足你的要求。另一个函数只是为了处理您是否有共享字符串，我假设您在列标题中这样做。不确定这是否完美，但我希望它有所帮助。
static void Main(string[] args)
{
DataTable dt = new DataTable();
using (SpreadsheetDocument spreadSheetDocument = SpreadsheetDocument.Open(@"..\..\example.xlsx", false))
{
WorkbookPart workbookPart = spreadSheetDocument.WorkbookPart;
IEnumerable<Sheet> sheets = spreadSheetDocument.WorkbookPart.Workbook.GetFirstChild<Sheets>().Elements<Sheet>();
string relationshipId = sheets.First().Id.Value;
WorksheetPart worksheetPart = (WorksheetPart)spreadSheetDocument.WorkbookPart.GetPartById(relationshipId);
Worksheet workSheet = worksheetPart.Worksheet;
SheetData sheetData = workSheet.GetFirstChild<SheetData>();
IEnumerable<Row> rows = sheetData.Descendants<Row>();
foreach (Cell cell in rows.ElementAt(0))
{
dt.Columns.Add(GetCellValue(spreadSheetDocument, cell));
}
foreach (Row row in rows) //this will also include your header row...
{
DataRow tempRow = dt.NewRow();
for (int i = 0; i < row.Descendants<Cell>().Count(); i++)
{
tempRow[i] = GetCellValue(spreadSheetDocument, row.Descendants<Cell>().ElementAt(i-1));
}
dt.Rows.Add(tempRow);
}
}
dt.Rows.RemoveAt(0); //...so i'm taking it out here.
}
public static string GetCellValue(SpreadsheetDocument document, Cell cell)
{
SharedStringTablePart stringTablePart = document.WorkbookPart.SharedStringTablePart;
string value = cell.CellValue.InnerXml;
if (cell.DataType != null && cell.DataType.Value == CellValues.SharedString)
{
return stringTablePart.SharedStringTable.ChildElements[Int32.Parse(value)].InnerText;
}
else
{
return value;
}
}
嗨，除了一处更改之外，上面的代码工作正常
替换以下代码行
tempRow[i] = GetCellValue(spreadSheetDocument, row.Descendants<Cell>().ElementAt(i-1));
与
tempRow[i] = GetCellValue(spreadSheetDocument, row.Descendants<Cell>().ElementAt(i));
如果你使用(i-1)，它会抛出异常：
specified argument was out of the range of valid values. parameter name index.
此解决方案适用于没有空单元格的电子表格。
要处理空单元格，您需要替换此行：
tempRow[i] = GetCellValue(spreadSheetDocument, row.Descendants<Cell>().ElementAt(i-1));
像这样：
Cell cell = row.Descendants<Cell>().ElementAt(i);
int index = CellReferenceToIndex(cell);
tempRow[index] = GetCellValue(spreadSheetDocument, cell);
并添加这个方法：
private static int CellReferenceToIndex(Cell cell)
{
int index = -1;
string reference = cell.CellReference.ToString().ToUpper();
foreach (char ch in reference)
{
if (Char.IsLetter(ch))
{
int value = (int)ch - (int)'A';
index = (index + 1) * 26 + value;
}
else
return index;
}
return index;
}
这是我的完整解决方案，其中还考虑了空单元格。
public static class ExcelHelper
{
//To get the value of the cell, even it's empty. Unable to use loop by index
private static string GetCellValue(WorkbookPart wbPart, List<Cell> theCells, string cellColumnReference)
{
Cell theCell = null;
string value = "";
foreach (Cell cell in theCells)
{
if (cell.CellReference.Value.StartsWith(cellColumnReference))
{
theCell = cell;
break;
}
}
if (theCell != null)
{
value = theCell.InnerText;
// If the cell represents an integer number, you are done.
// For dates, this code returns the serialized value that represents the date. The code handles strings and
// Booleans individually. For shared strings, the code looks up the corresponding value in the shared string table. For Booleans, the code converts the value into the words TRUE or FALSE.
if (theCell.DataType != null)
{
switch (theCell.DataType.Value)
{
case CellValues.SharedString:
// For shared strings, look up the value in the shared strings table.
var stringTable = wbPart.GetPartsOfType<SharedStringTablePart>().FirstOrDefault();
// If the shared string table is missing, something is wrong. Return the index that is in the cell. Otherwise, look up the correct text in the table.
if (stringTable != null)
{
value = stringTable.SharedStringTable.ElementAt(int.Parse(value)).InnerText;
}
break;
case CellValues.Boolean:
switch (value)
{
case "0":
value = "FALSE";
break;
default:
value = "TRUE";
break;
}
break;
}
}
}
return value;
}
private static string GetCellValue(WorkbookPart wbPart, List<Cell> theCells, int index)
{
return GetCellValue(wbPart, theCells, GetExcelColumnName(index));
}
private static string GetExcelColumnName(int columnNumber)
{
int dividend = columnNumber;
string columnName = String.Empty;
int modulo;
while (dividend > 0)
{
modulo = (dividend - 1) % 26;
columnName = Convert.ToChar(65 + modulo).ToString() + columnName;
dividend = (int)((dividend - modulo) / 26);
}
return columnName;
}
//Only xlsx files
public static DataTable GetDataTableFromExcelFile(string filePath, string sheetName = "")
{
DataTable dt = new DataTable();
try
{
using (SpreadsheetDocument document = SpreadsheetDocument.Open(filePath, false))
{
WorkbookPart wbPart = document.WorkbookPart;
IEnumerable<Sheet> sheets = document.WorkbookPart.Workbook.GetFirstChild<Sheets>().Elements<Sheet>();
string sheetId = sheetName != "" ? sheets.Where(q => q.Name == sheetName).First().Id.Value : sheets.First().Id.Value;
WorksheetPart wsPart = (WorksheetPart)wbPart.GetPartById(sheetId);
SheetData sheetdata = wsPart.Worksheet.Elements<SheetData>().FirstOrDefault();
int totalHeaderCount = sheetdata.Descendants<Row>().ElementAt(0).Descendants<Cell>().Count();
//Get the header
for (int i = 1; i <= totalHeaderCount; i++)
{
dt.Columns.Add(GetCellValue(wbPart, sheetdata.Descendants<Row>().ElementAt(0).Elements<Cell>().ToList(), i));
}
foreach (Row r in sheetdata.Descendants<Row>())
{
if (r.RowIndex > 1)
{
DataRow tempRow = dt.NewRow();
//Always get from the header count, because the index of the row changes where empty cell is not counted
for (int i = 1; i <= totalHeaderCount; i++)
{
tempRow[i - 1] = GetCellValue(wbPart, r.Elements<Cell>().ToList(), i);
}
dt.Rows.Add(tempRow);
}
}
}
}
catch (Exception ex)
{
}
return dt;
}
}
首先将 ExcelUtility.cs 添加到您的项目中：
ExcelUtility.cs
using System.Data;
using System.Linq;
using DocumentFormat.OpenXml.Packaging;
using DocumentFormat.OpenXml.Spreadsheet;
namespace Core_Excel.Utilities
{
static class ExcelUtility
{
public static DataTable Read(string path)
{
var dt = new DataTable();
using (var ssDoc = SpreadsheetDocument.Open(path, false))
{
var sheets = ssDoc.WorkbookPart.Workbook.GetFirstChild<Sheets>().Elements<Sheet>();
var relationshipId = sheets.First().Id.Value;
var worksheetPart = (WorksheetPart) ssDoc.WorkbookPart.GetPartById(relationshipId);
var workSheet = worksheetPart.Worksheet;
var sheetData = workSheet.GetFirstChild<SheetData>();
var rows = sheetData.Descendants<Row>().ToList();
foreach (var row in rows) //this will also include your header row...
{
var tempRow = dt.NewRow();
var colCount = row.Descendants<Cell>().Count();
foreach (var cell in row.Descendants<Cell>())
{
var index = GetIndex(cell.CellReference);
// Add Columns
for (var i = dt.Columns.Count; i <= index; i++)
dt.Columns.Add();
tempRow[index] = GetCellValue(ssDoc, cell);
}
dt.Rows.Add(tempRow);
}
}
return dt;
}
private static string GetCellValue(SpreadsheetDocument document, Cell cell)
{
var stringTablePart = document.WorkbookPart.SharedStringTablePart;
var value = cell.CellValue.InnerXml;
if (cell.DataType != null && cell.DataType.Value == CellValues.SharedString)
return stringTablePart.SharedStringTable.ChildElements[int.Parse(value)].InnerText;
return value;
}
public static int GetIndex(string name)
{
if (string.IsNullOrWhiteSpace(name))
return -1;
int index = 0;
foreach (var ch in name)
{
if (char.IsLetter(ch))
{
int value = ch - 'A' + 1;
index = value + index * 26;
}
else
break;
}
return index - 1;
}
}
}
用途：
var path = "D:\\Documents\\test.xlsx";
var dt = ExcelUtility.Read(path);
那就尽情享受吧！
Public Shared Function ExcelToDataTable(filename As String) As DataTable
Try
Dim dt As New DataTable()
Using doc As SpreadsheetDocument = SpreadsheetDocument.Open(filename, False)
Dim workbookPart As WorkbookPart = doc.WorkbookPart
Dim sheets As IEnumerable(Of Sheet) = doc.WorkbookPart.Workbook.GetFirstChild(Of Sheets)().Elements(Of Sheet)()
Dim relationshipId As String = sheets.First().Id.Value
Dim worksheetPart As WorksheetPart = DirectCast(doc.WorkbookPart.GetPartById(relationshipId), WorksheetPart)
Dim workSheet As Worksheet = worksheetPart.Worksheet
Dim sheetData As SheetData = workSheet.GetFirstChild(Of SheetData)()
Dim rows As IEnumerable(Of Row) = sheetData.Descendants(Of Row)()
For Each cell As Cell In rows.ElementAt(0)
dt.Columns.Add(GetCellValue(doc, cell))
Next
For Each row As Row In rows
'this will also include your header row...
Dim tempRow As DataRow = dt.NewRow()
For i As Integer = 0 To row.Descendants(Of Cell)().Count() - 1
tempRow(i) = GetCellValue(doc, row.Descendants(Of Cell)().ElementAt(i))
Next
dt.Rows.Add(tempRow)
Next
End Using
dt.Rows.RemoveAt(0)
Return dt
Catch ex As Exception
Throw ex
End Try
End Function
Public Shared Function GetCellValue(document As SpreadsheetDocument, cell As Cell) As String
Try
If IsNothing(cell.CellValue) Then
Return ""
End If
Dim value As String = cell.CellValue.InnerXml
If cell.DataType IsNot Nothing AndAlso cell.DataType.Value = CellValues.SharedString Then
Dim stringTablePart As SharedStringTablePart = document.WorkbookPart.SharedStringTablePart
Return stringTablePart.SharedStringTable.ChildElements(Int32.Parse(value)).InnerText
Else
Return value
End If
Catch ex As Exception
Return ""
End Try
End Function
我知道这个帖子开始已经很久了。然而，上述解决方案对我来说都不起作用。空单元格问题等。
我在 GitHub 上找到了一个非常好的带有“MIT”许可证的解决方案： https://github.com/ExcelDataReader/ExcelDataReader 这对于 C# 和 VBnet 应用程序都适用。 来自 VBNET 的示例调用（C# 的示例代码位于 GitHub 上）：
Using stream As FileStream = New FileStream(DataPath & "\" & fName.Name, FileMode.Open, FileAccess.Read, FileShare.ReadWrite)
Using reader As IExcelDataReader = ExcelReaderFactory.CreateReader(stream)
ds = reader.AsDataSet(New ExcelDataSetConfiguration() With {
.UseColumnDataType = False,
.ConfigureDataTable = Function(tableReader) New ExcelDataTableConfiguration() With {
.UseHeaderRow = True
}
})
End Using
End Using
结果是一个数据集，工作簿中的每张工作表都有一个表。
我真的很喜欢自己编译用 C# 编写的 dll，而不是使用现成的 dll。这样我就可以控制向客户交付的内容。
根据我的要求，我从 D.L.MAN 的最佳答案中修改了“ExcelUtility”Read() 的几部分代码。
还添加了 saveDataTablesToExcel() 和 ExportDataSet() 方法以将多个 DataTable 保存在 xlsx 文件中。
以下是新的“ExcelUtility”类的完整代码及其用法。
using System;
using System.Collections.Generic;
using System.Data;
using System.Linq;
using System.Text;
using System.Threading.Tasks;
using DocumentFormat.OpenXml.Packaging;
using DocumentFormat.OpenXml.Spreadsheet;
namespace myNamespace
{
static class ExcelUtility
{
// SS Note: isHeaderOnTopRow functionality is to set column names as the first row of 'sheet'
public static DataTable[] Read(string path, bool isHeaderOnTopRow = false)
{
try
{
using (var ssDoc = SpreadsheetDocument.Open(path, false))
{
var sheets = ssDoc.WorkbookPart.Workbook.GetFirstChild<Sheets>().Elements<Sheet>();
DataTable[] dtArray = new DataTable[sheets.ToList().Count];
int counti = 0;
foreach (Sheet sheet in sheets)
{
var dt = new DataTable();
var relationshipId = sheet.Id.Value;
var worksheetPart = (WorksheetPart)ssDoc.WorkbookPart.GetPartById(relationshipId);
var workSheet = worksheetPart.Worksheet;
var sheetData = workSheet.GetFirstChild<SheetData>();
var rows = sheetData.Descendants<Row>().ToList();
int rowIndex = 0;
foreach (var row in rows) //this will also include your header row...
{
var tempRow = dt.NewRow();
var colCount = row.Descendants<Cell>().Count();
int colIndex = 0;
foreach (var cell in row.Descendants<Cell>())
{
var index = GetIndex(cell.CellReference);
// SS Note: ADDED next line as we were getting cell.CellReference (or index) as -1 in our provided xlsx file.
index = (index < 0 ? colIndex++ : index);
// Add Columns
for (var i = dt.Columns.Count; i <= index; i++)
dt.Columns.Add();
if (isHeaderOnTopRow && rowIndex == 0)
{
string heading = GetCellValue(ssDoc, cell);
heading = (heading.Length > 0 ? heading : $"Column{index + 1}");
dt.Columns[index].ColumnName = heading;
}
else
{
tempRow[index] = GetCellValue(ssDoc, cell);
}
}
if (rowIndex > 0 || isHeaderOnTopRow == false)
{
dt.Rows.Add(tempRow);
}
rowIndex++;
}
dtArray[counti++] = dt;
}
return dtArray;
}
}
catch (Exception e)
{
Console.WriteLine(e);
}
return null;
}
private static string GetCellValue(SpreadsheetDocument document, Cell cell)
{
var stringTablePart = document.WorkbookPart.SharedStringTablePart;
var value = cell.CellValue.InnerXml;
if (cell.DataType != null && cell.DataType.Value == CellValues.SharedString)
return stringTablePart.SharedStringTable.ChildElements[int.Parse(value)].InnerText;
return value;
}
public static int GetIndex(string name)
{
if (string.IsNullOrWhiteSpace(name))
return -1;
int index = 0;
foreach (var ch in name)
{
if (char.IsLetter(ch))
{
int value = ch - 'A' + 1;
index = value + index * 26;
}
else
break;
}
return index - 1;
}
public static void ExportDataSet(DataSet ds, string destination)
{
try
{
using (var workbook = SpreadsheetDocument.Create(destination, DocumentFormat.OpenXml.SpreadsheetDocumentType.Workbook))
{
var workbookPart = workbook.AddWorkbookPart();
workbook.WorkbookPart.Workbook = new DocumentFormat.OpenXml.Spreadsheet.Workbook();
workbook.WorkbookPart.Workbook.Sheets = new DocumentFormat.OpenXml.Spreadsheet.Sheets();
foreach (System.Data.DataTable table in ds.Tables)
{
var sheetPart = workbook.WorkbookPart.AddNewPart<WorksheetPart>();
var sheetData = new DocumentFormat.OpenXml.Spreadsheet.SheetData();
sheetPart.Worksheet = new DocumentFormat.OpenXml.Spreadsheet.Worksheet(sheetData);
DocumentFormat.OpenXml.Spreadsheet.Sheets sheets = workbook.WorkbookPart.Workbook.GetFirstChild<DocumentFormat.OpenXml.Spreadsheet.Sheets>();
string relationshipId = workbook.WorkbookPart.GetIdOfPart(sheetPart);
uint sheetId = 1;
if (sheets.Elements<DocumentFormat.OpenXml.Spreadsheet.Sheet>().Count() > 0)
{
sheetId =
sheets.Elements<DocumentFormat.OpenXml.Spreadsheet.Sheet>().Select(s => s.SheetId.Value).Max() + 1;
}
DocumentFormat.OpenXml.Spreadsheet.Sheet sheet = new DocumentFormat.OpenXml.Spreadsheet.Sheet() { Id = relationshipId, SheetId = sheetId, Name = table.TableName };
sheets.Append(sheet);
DocumentFormat.OpenXml.Spreadsheet.Row headerRow = new DocumentFormat.OpenXml.Spreadsheet.Row();
List<String> columns = new List<string>();
foreach (System.Data.DataColumn column in table.Columns)
{
columns.Add(column.ColumnName);
DocumentFormat.OpenXml.Spreadsheet.Cell cell = new DocumentFormat.OpenXml.Spreadsheet.Cell();
cell.DataType = DocumentFormat.OpenXml.Spreadsheet.CellValues.String;
cell.CellValue = new DocumentFormat.OpenXml.Spreadsheet.CellValue(column.ColumnName);
headerRow.AppendChild(cell);
}
sheetData.AppendChild(headerRow);
foreach (System.Data.DataRow dsrow in table.Rows)
{
DocumentFormat.OpenXml.Spreadsheet.Row newRow = new DocumentFormat.OpenXml.Spreadsheet.Row();
foreach (String col in columns)
{
DocumentFormat.OpenXml.Spreadsheet.Cell cell = new DocumentFormat.OpenXml.Spreadsheet.Cell();
cell.DataType = DocumentFormat.OpenXml.Spreadsheet.CellValues.String;
cell.CellValue = new DocumentFormat.OpenXml.Spreadsheet.CellValue(dsrow[col].ToString()); //
newRow.AppendChild(cell);
}
sheetData.AppendChild(newRow);
}
}
}
}
catch (Exception e)
{
Console.WriteLine(e);
}
}
public static void saveDataTablesToExcel(DataTable[] dataTables, string saveToFilePath)
{
// Create a DataSet
DataSet dataSet = new DataSet("Tables");
// We can add multiple DataTable to DataSet
foreach (DataTable dt in dataTables)
{
dataSet.Tables.Add(dt);
}
ExportDataSet(dataSet, saveToFilePath);
}
}
}
用途：
// save three datatables in xlsx file
DataTable[] dataTables = new DataTable[3];
dataTables[0] = firstDataTable;
dataTables[1] = secondDataTable;
dataTables[2] = thirdDataTable;
string fileName = "saved.xlsx";
saveDataTablesToExcel(dataTables, $"{ExcelFileSaveFolder}{fileName}");
// retrieve data from first sheet and set it to 'returnTable'
DataTable returnTable = null;
var path = $"{ExcelFileSaveFolder}{fileName}";
DataTable[] getDataTables = ExcelUtility.Read(path, true);
if (getDataTables != null && getDataTables.Length > 0)
returnTable = getDataTables[0];
接受的答案不适用于包含空白单元格的工作表。
此类支持空白单元格：
using DocumentFormat.OpenXml.Packaging;
using DocumentFormat.OpenXml.Spreadsheet;
using System;
using System.Data;
using System.Linq;
using System.Text.RegularExpressions;
public class ExcelOpenXMLtoDT
{
internal static DataTable ExcelToWorksheetHelper(string sWorkbookFile, string sWorksheet)
{
DataTable oDT = new DataTable();
using (SpreadsheetDocument oDoc = SpreadsheetDocument.Open(sWorkbookFile, false))
{
WorkbookPart oWBpart = oDoc.WorkbookPart;
Workbook oWB = oWBpart.Workbook;
Sheet sheet = oWB.Descendants<Sheet>().FirstOrDefault(s => s.Name == sWorksheet);
if (sheet == null)
{
throw new ArgumentException($"Sheet with name '{sWorksheet}' not found.");
}
WorksheetPart worksheetPart = (WorksheetPart)(oWBpart.GetPartById(sheet.Id));
SheetData sheetDataElement = worksheetPart.Worksheet.Elements<SheetData>().First();
foreach (Row oSheetRow in sheetDataElement.Elements<Row>())
{
//insure the DataTable has enough columns to hold the row.
int iSheetColumns = GetRowMaximumColumn(oSheetRow);
int iDTcolumns = oDT.Columns.Count;
for (int i = 0; i < iSheetColumns - iDTcolumns; i++)
oDT.Columns.Add();
//---------------------------------
//transfer sheet data to the new row, add to DT.
DataRow oRow = oDT.NewRow();
foreach (Cell oCell in oSheetRow.Elements<Cell>())
{
int iSheetColumn = CellCol(oCell); //need to pull the column from the cell attributes.
oRow[iSheetColumn - 1] = GetCellValue(oDoc, oCell);
}
oDT.Rows.Add(oRow);
}
}
return oDT;
}
private static int GetRowMaximumColumn(Row oRow)
{
int iRC = -1;
foreach (Cell oCell in oRow.Elements<Cell>())
{
int iColNo = CellCol(oCell);
if (iColNo > iRC) iRC = iColNo;
}
return iRC;
}
private static int CellCol(Cell oCell)
{
string sCellName = oCell.CellReference;
string sColString = Regex.Replace(sCellName, "[0-9]+", "");
return ExcelWorksheetHelper.ColVal(sColString);
}
private static string GetCellValue(SpreadsheetDocument document, Cell cell)
{
SharedStringTablePart sharedStringTablePart = document.WorkbookPart.SharedStringTablePart;
string value = cell.CellValue?.InnerText;
if (cell.DataType != null && cell.DataType.Value == CellValues.SharedString)
{
return sharedStringTablePart.SharedStringTable.ElementAt(int.Parse(value)).InnerText;
}
else
{
return value;
}
}
/// <summary>
/// Takes char value for Excel column (like AB) and returns
/// the column ASCII value, so A=1, B=2, AB= 26+2 = 28 ext...
/// </summary>
/// <param name="sColKey"></param>
/// <returns></returns>
private static int ColVal(string sColKey)
{
int iRC = 0;
char[] asColKey = sColKey.ToUpper().ToCharArray();
int iPlace = asColKey.Length - 1;
//the power function is because this is a base-26 numbering system
// so we just need to find the place, but instead of a 10's place, 100's place
// we have a 26's place, 676's place etc... ~mwr
for (int i = 0; i < asColKey.Length; i++)
iRC += (int)(Math.Pow(26, iPlace - i) * (asColKey[i] - 64)); // 65 = ascii a
return iRC;
}
}
如果行值为 null 或空，则获取值错误。
如果工作正常，所有列都会填充数据。但也许所有行都不是