【问题标题】:Reading Excel files using OpenXML使用 OpenXML 读取 Excel 文件
【发布时间】:2016-07-25 21:27:58
【问题描述】:

我正在尝试通过 OpenXML 读取 Excel 文件并希望输出到 CSV。目前它在单独的行(由于 writeline)或单行(使用 write 时)读取每个单元格。以 Excel 等表格格式读取和输出的最佳方法是什么?我可以利用 OpenXML 中的内置功能吗?

static void Main(string[] args)
{
        String xlDocName = @"C:\Users\xlp111\source.xlsx";

        using (SpreadsheetDocument spreadsheetDocument = SpreadsheetDocument.Open(xlDocName, false))
        {
            WorkbookPart workbookPart = spreadsheetDocument.WorkbookPart;
            string cellValue = string.Empty;
            foreach(WorksheetPart worksheetPart in workbookPart.WorksheetParts)
            {
                OpenXmlReader reader = OpenXmlReader.Create(worksheetPart);

                while (reader.Read())
                {
                if (reader.ElementType == typeof(Row))
                {
                    reader.ReadFirstChild();

                    do
                    {
                    if (reader.ElementType == typeof(Cell))
                    {
                        Cell c = (Cell)reader.LoadCurrentElement();

                        if (c.DataType != null && c.DataType == CellValues.SharedString)
                        {
                        SharedStringItem ssi = workbookPart.SharedStringTablePart.SharedStringTable.Elements<SharedStringItem>().ElementAt(int.Parse(c.CellValue.InnerText));
                        cellValue = ssi.Text.Text;
                        Console.WriteLine(cellValue);
                        }
                    }
                    }                      
                    while (reader.ReadNextSibling());
                }
                }
            }
            Console.ReadLine();
        }
    }
}

【问题讨论】:

标签: c# excel openxml-sdk


【解决方案1】:

编辑:

使用适用于 Microsoft Office 的 Open XML SDK

从 :https://www.microsoft.com/en-eg/download/details.aspx?id=5124&wa=wsignin1.0 安装 V2

(或 V2.5)

以下类将excel表格转换为带分隔符的CSV文件

 //reference library
 using DocumentFormat.OpenXml.Packaging;
 using DocumentFormat.OpenXml.Spreadsheet;


public class OpenXmlExcel
{
public void ExcelToCsv(string source, string target, string delimiter = ";", bool firstRowIsHeade = true)
{
    var dt = ReadExcelSheet(source, firstRowIsHeade);
    DatatableToCsv(dt, target, delimiter);

}

private void DatatableToCsv(DataTable dt, string fname, string delimiter = ";")
{

    using (StreamWriter writer = new StreamWriter(fname))
    {
        foreach (DataRow row in dt.AsEnumerable())
        {
            writer.WriteLine(string.Join(delimiter, row.ItemArray.Select(x => x.ToString())) + delimiter);
        }
    }

}

List<string> Headers = new List<string>();


private DataTable ReadExcelSheet(string fname, bool firstRowIsHeade)
{

    DataTable dt = new DataTable();
    using (SpreadsheetDocument doc = SpreadsheetDocument.Open(fname, false))
    {
        //Read the first Sheets 
        Sheet sheet = doc.WorkbookPart.Workbook.Sheets.GetFirstChild<Sheet>();
        Worksheet worksheet = (doc.WorkbookPart.GetPartById(sheet.Id.Value) as WorksheetPart).Worksheet;
        IEnumerable<Row> rows = worksheet.GetFirstChild<SheetData>().Descendants<Row>();

        foreach (Row row in rows)
        {
            //Read the first row as header
            if (row.RowIndex.Value == 1)
            {
                var j = 1;
                foreach (Cell cell in row.Descendants<Cell>())
                {
                    var colunmName = firstRowIsHeade ? GetCellValue(doc, cell) : "Field" + j++;
                    Console.WriteLine(colunmName);
                    Headers.Add(colunmName);
                    dt.Columns.Add(colunmName);
                }
            }
            else
            {
                dt.Rows.Add();
                int i = 0;
                foreach (Cell cell in row.Descendants<Cell>())
                {
                    dt.Rows[dt.Rows.Count - 1][i] = GetCellValue(doc, cell);
                    i++;
                }
            }
        }

    }
    return dt;
}

private string GetCellValue(SpreadsheetDocument doc, Cell cell)
{
    string value = cell.CellValue.InnerText;
    if (cell.DataType != null && cell.DataType.Value == CellValues.SharedString)
    {
        return doc.WorkbookPart.SharedStringTablePart.SharedStringTable.ChildElements.GetItem(int.Parse(value)).InnerText;
    }
    return value;
 }
}

使用方法:

new OpenXmlExcel().ExcelToCsv("f1.xlsx","f1.csv",";",true);
or
//use default: separator=";" ,first row is header
new OpenXmlExcel().ExcelToCsv("f1.xlsx","f1.csv");

【讨论】:

  • 我正在寻找一个 OpenXML 解决方案。谢谢!
  • 它在每行的末尾添加一个分隔符。对处理有什么建议吗?
  • 代码假设 NEWLINE 字符是行尾。你需要这个分隔符吗?
  • 您的代码假定每行末尾都有一个换行符?
  • 另外,我应该如何处理空白/空单元格?当前空白/空单元格被以下单元格值替换。有什么建议吗?
猜你喜欢
  • 1970-01-01
  • 1970-01-01
  • 1970-01-01
  • 2023-03-26
  • 2018-12-18
  • 1970-01-01
  • 2020-06-29
  • 1970-01-01
相关资源
最近更新 更多