Reading Excel files from C#

Question

var fileName = string.Format("{0}\\fileNameHere", Directory.GetCurrentDirectory());
var connectionString = string.Format("Provider=Microsoft.Jet.OLEDB.4.0; data source={0}; Extended Properties=Excel 8.0;", fileName);

var adapter = new OleDbDataAdapter("SELECT * FROM [workSheetNameHere$]", connectionString);
var ds = new DataSet();

adapter.Fill(ds, "anyNameHere");

DataTable data = ds.Tables["anyNameHere"];

This is what I usually use. It is a little different because I usually stick a AsEnumerable() at the edit of the tables:

var data = ds.Tables["anyNameHere"].AsEnumerable();

as this lets me use LINQ to search and build structs from the fields.

var query = data.Where(x => x.Field<string>("phoneNumber") != string.Empty).Select(x =>
                new MyContact
                    {
                        firstName= x.Field<string>("First Name"),
                        lastName = x.Field<string>("Last Name"),
                        phoneNumber =x.Field<string>("Phone Number"),
                    });

If it is just simple data contained in the Excel file you can read the data via ADO.NET. See the connection strings listed here:

http://www.connectionstrings.com/?carrier=excel2007 or http://www.connectionstrings.com/?carrier=excel

-Ryan

Update: then you can just read the worksheet via something like select * from [Sheet1$]

The ADO.NET approach is quick and easy, but it has a few quirks which you should be aware of, especially regarding how DataTypes are handled.

This excellent article will help you avoid some common pitfalls: http://blog.lab49.com/archives/196

This is what I used for Excel 2003:

Dictionary<string, string> props = new Dictionary<string, string>();
props["Provider"] = "Microsoft.Jet.OLEDB.4.0";
props["Data Source"] = repFile;
props["Extended Properties"] = "Excel 8.0";

StringBuilder sb = new StringBuilder();
foreach (KeyValuePair<string, string> prop in props)
{
    sb.Append(prop.Key);
    sb.Append('=');
    sb.Append(prop.Value);
    sb.Append(';');
}
string properties = sb.ToString();

using (OleDbConnection conn = new OleDbConnection(properties))
{
    conn.Open();
    DataSet ds = new DataSet();
    string columns = String.Join(",", columnNames.ToArray());
    using (OleDbDataAdapter da = new OleDbDataAdapter(
        "SELECT " + columns + " FROM [" + worksheet + "$]", conn))
    {
        DataTable dt = new DataTable(tableName);
        da.Fill(dt);
        ds.Tables.Add(dt);
    }
}

How about Excel Data Reader?

http://exceldatareader.codeplex.com/

I've used in it anger, in a production environment, to pull large amounts of data from a variety of Excel files into SQL Server Compact. It works very well and it's rather robust.

Here's some code I wrote in C# using .NET 1.1 a few years ago. Not sure if this would be exactly what you need (and may not be my best code :)).

using System;
using System.Data;
using System.Data.OleDb;

namespace ExportExcelToAccess
{
    /// <summary>
    /// Summary description for ExcelHelper.
    /// </summary>
    public sealed class ExcelHelper
    {
        private const string CONNECTION_STRING = "Provider=Microsoft.Jet.OLEDB.4.0;Data Source=<FILENAME>;Extended Properties=\"Excel 8.0;HDR=Yes;\";";

        public static DataTable GetDataTableFromExcelFile(string fullFileName, ref string sheetName)
        {
            OleDbConnection objConnection = new OleDbConnection();
            objConnection = new OleDbConnection(CONNECTION_STRING.Replace("<FILENAME>", fullFileName));
            DataSet dsImport = new DataSet();

            try
            {
                objConnection.Open();

                DataTable dtSchema = objConnection.GetOleDbSchemaTable(OleDbSchemaGuid.Tables, null);

                if( (null == dtSchema) || ( dtSchema.Rows.Count <= 0 ) )
                {
                    //raise exception if needed
                }

                if( (null != sheetName) && (0 != sheetName.Length))
                {
                    if( !CheckIfSheetNameExists(sheetName, dtSchema) )
                    {
                        //raise exception if needed
                    }
                }
                else
                {
                    //Reading the first sheet name from the Excel file.
                    sheetName = dtSchema.Rows[0]["TABLE_NAME"].ToString();
                }

                new OleDbDataAdapter("SELECT * FROM [" + sheetName + "]", objConnection ).Fill(dsImport);
            }
            catch (Exception)
            {
                //raise exception if needed
            }
            finally
            {
                // Clean up.
                if(objConnection != null)
                {
                    objConnection.Close();
                    objConnection.Dispose();
                }
            }


            return dsImport.Tables[0];
            #region Commented code for importing data from CSV file.
            //              string strConnectionString = "Provider=Microsoft.Jet.OLEDB.4.0;" +"Data Source=" + System.IO.Path.GetDirectoryName(fullFileName) +";" +"Extended Properties=\"Text;HDR=YES;FMT=Delimited\"";
            //
            //              System.Data.OleDb.OleDbConnection conText = new System.Data.OleDb.OleDbConnection(strConnectionString);
            //              new System.Data.OleDb.OleDbDataAdapter("SELECT * FROM " + System.IO.Path.GetFileName(fullFileName).Replace(".", "#"), conText).Fill(dsImport);
            //              return dsImport.Tables[0];

            #endregion
        }

        /// <summary>
        /// This method checks if the user entered sheetName exists in the Schema Table
        /// </summary>
        /// <param name="sheetName">Sheet name to be verified</param>
        /// <param name="dtSchema">schema table </param>
        private static bool CheckIfSheetNameExists(string sheetName, DataTable dtSchema)
        {
            foreach(DataRow dataRow in dtSchema.Rows)
            {
                if( sheetName == dataRow["TABLE_NAME"].ToString() )
                {
                    return true;
                }   
            }
            return false;
        }
    }
}

Koogra is an open-source component written in C# that reads and writes Excel files.