From Excel to DataTable in C# with Open XML
I think this should do what you're asking. The other function is there just to deal with if you have shared strings, which I assume you do in your column headers. Not sure this is perfect, but I hope it helps.
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;
}
}
Hi The above code is working fine except one change
replace the below line of code
tempRow[i] = GetCellValue(spreadSheetDocument, row.Descendants<Cell>().ElementAt(i-1));
with
tempRow[i] = GetCellValue(spreadSheetDocument, row.Descendants<Cell>().ElementAt(i));
If you use (i-1) it will throw an exception:
specified argument was out of the range of valid values. parameter name index.
This solution works for spreadsheets without empty cells.
To handle empty cells, you will need to replace this line:
tempRow[i] = GetCellValue(spreadSheetDocument, row.Descendants<Cell>().ElementAt(i-1));
with something like this:
Cell cell = row.Descendants<Cell>().ElementAt(i);
int index = CellReferenceToIndex(cell);
tempRow[index] = GetCellValue(spreadSheetDocument, cell);
And add this method:
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;
}