我想在我的项目中实现openXml sdk 2.5。我在这个link
中做了一切using DocumentFormat.OpenXml;
using DocumentFormat.OpenXml.Packaging;
using DocumentFormat.OpenXml.Spreadsheet;
using System.IO.Packaging;
static void Main(string[] args)
{
String fileName = @"C:\OPENXML\BigData.xlsx";
// Comment one of the following lines to test the method separately.
ReadExcelFileDOM(fileName); // DOM
//ReadExcelFileSAX(fileName); // SAX
}
// The DOM approach.
// Note that the code below works only for cells that contain numeric values.
//
static void ReadExcelFileDOM(string fileName)
{
using (SpreadsheetDocument spreadsheetDocument = SpreadsheetDocument.Open(fileName, false))
{
WorkbookPart workbookPart = spreadsheetDocument.WorkbookPart;
WorksheetPart worksheetPart = workbookPart.WorksheetParts.First();
SheetData sheetData = worksheetPart.Worksheet.Elements<SheetData>().First();
string text;
int rowCount= sheetData.Elements<Row>().Count();
foreach (Row r in sheetData.Elements<Row>())
{
foreach (Cell c in r.Elements<Cell>())
{
text = c.CellValue.Text;
Console.Write(text + " ");
}
}
Console.WriteLine();
Console.ReadKey();
}
}
但我没有得到任何排。它没有进入循环。注意：我还设置了openXml sdk 2.5我的电脑
我发现下面的代码对数值有用。对于字符串值，它写0 1 2 ...
private static void Main(string[] args)
{
var filePath = @"C:/OPENXML/BigData.xlsx";
using (var document = SpreadsheetDocument.Open(filePath, false))
{
var workbookPart = document.WorkbookPart;
var workbook = workbookPart.Workbook;
var sheets = workbook.Descendants<Sheet>();
foreach (var sheet in sheets)
{
var worksheetPart = (WorksheetPart)workbookPart.GetPartById(sheet.Id);
var sharedStringPart = workbookPart.SharedStringTablePart;
//var values = sharedStringPart.SharedStringTable.Elements<SharedStringItem>().ToArray();
string text;
var rows = worksheetPart.Worksheet.Descendants<Row>();
foreach (var row in rows)
{
Console.WriteLine();
int count = row.Elements<Cell>().Count();
foreach (Cell c in row.Elements<Cell>())
{
text = c.CellValue.InnerText;
Console.Write(text + " ");
}
}
}
}
Console.ReadLine();
}
答案 0 :(得分：51)
你的方法似乎对我有用 - 因为它确实“进入循环”。 不过你也可以尝试以下内容：
void Main()
{
string fileName = @"c:\path\to\my\file.xlsx";
using (FileStream fs = new FileStream(fileName, FileMode.Open, FileAccess.Read, FileShare.ReadWrite))
{
using (SpreadsheetDocument doc = SpreadsheetDocument.Open(fs, false))
{
WorkbookPart workbookPart = doc.WorkbookPart;
SharedStringTablePart sstpart = workbookPart.GetPartsOfType<SharedStringTablePart>().First();
SharedStringTable sst = sstpart.SharedStringTable;
WorksheetPart worksheetPart = workbookPart.WorksheetParts.First();
Worksheet sheet = worksheetPart.Worksheet;
var cells = sheet.Descendants<Cell>();
var rows = sheet.Descendants<Row>();
Console.WriteLine("Row count = {0}", rows.LongCount());
Console.WriteLine("Cell count = {0}", cells.LongCount());
// One way: go through each cell in the sheet
foreach (Cell cell in cells)
{
if ((cell.DataType != null) && (cell.DataType == CellValues.SharedString))
{
int ssid = int.Parse(cell.CellValue.Text);
string str = sst.ChildElements[ssid].InnerText;
Console.WriteLine("Shared string {0}: {1}", ssid, str);
}
else if (cell.CellValue != null)
{
Console.WriteLine("Cell contents: {0}", cell.CellValue.Text);
}
}
// Or... via each row
foreach (Row row in rows)
{
foreach (Cell c in row.Elements<Cell>())
{
if ((c.DataType != null) && (c.DataType == CellValues.SharedString))
{
int ssid = int.Parse(c.CellValue.Text);
string str = sst.ChildElements[ssid].InnerText;
Console.WriteLine("Shared string {0}: {1}", ssid, str);
}
else if (c.CellValue != null)
{
Console.WriteLine("Cell contents: {0}", c.CellValue.Text);
}
}
}
}
}
}
我使用文件流方法打开工作簿，因为这允许您使用共享访问权限打开它 - 这样您就可以同时在Excel中打开工作簿。如果工作簿在其他地方打开，Spreadsheet.Open（...方法将无效。
也许这就是你的代码无效的原因。
另请注意，使用SharedStringTable在适当的位置获取单元格文本。
编辑2018-07-11：
由于这篇文章仍在获得投票，我还应该指出，在许多情况下，使用ClosedXML来操作/阅读/编辑工作簿可能要容易得多。文档示例非常用户友好，在我有限的经验中，编码更直接。请注意，它（尚未）实现所有Excel功能（例如INDEX和MATCH），这可能是也可能不是问题。 [不管怎样我想要尝试在OpenXML中处理INDEX和MATCH。]
答案 1 :(得分：10)
我和OP有同样的问题，上面的答案对我不起作用。
我认为这是问题：当您在Excel中创建文档（不是以编程方式）时，默认情况下您有3张工作表，而具有Sheet1行数据的WorksheetParts是最后一个WorksheetParts元素，而不是第一个。
我通过在Visual Studio中查看document.WorkbookPart.WorksheetParts，扩展结果，然后查看所有子元素，直到找到一个其中HasChildren = true的SheetData对象来解决这个问题。
试试这个：
// open the document read-only
SpreadSheetDocument document = SpreadsheetDocument.Open(filePath, false);
SharedStringTable sharedStringTable = document.WorkbookPart.SharedStringTablePart.SharedStringTable;
string cellValue = null;
foreach (WorksheetPart worksheetPart in document.WorkbookPart.WorksheetParts)
{
foreach (SheetData sheetData in worksheetPart.Worksheet.Elements<SheetData>())
{
if (sheetData.HasChildren)
{
foreach (Row row in sheetData.Elements<Row>())
{
foreach (Cell cell in row.Elements<Cell>())
{
cellValue = cell.InnerText;
if (cell.DataType == CellValues.SharedString)
{
Console.WriteLine("cell val: " + sharedStringTable.ElementAt(Int32.Parse(cellValue)).InnerText);
}
else
{
Console.WriteLine("cell val: " + cellValue);
}
}
}
}
}
}
document.Close();
答案 2 :(得分：1)
读取大型 Excel： openxml 有DOM 和SAX 两种方法来读取excel。 DOM 消耗更多的 RAM 资源，因为它将整个 xml 内容（Excel 文件）加载到内存中，但它的强类型方法。 另一方面，SAX 是事件基础解析。 more here
因此，如果您面对大型 Excel 文件，最好使用 SAX。
下面的代码示例使用 SAX 方法，并且还处理了 Excel 文件读取中的两个重要场景。
此函数返回当时单元格的确切实际索引并处理第一种情况。 from here
private static int CellReferenceToIndex(Cell cell)
{
int index = 0;
string reference = cell.CellReference.ToString().ToUpper();
foreach (char ch in reference)
{
if (Char.IsLetter(ch))
{
int value = (int)ch - (int)'A';
index = (index == 0) ? value : ((index + 1) * 26) + value;
}
else
return index;
}
return index;
}
读取excel萨克斯方法的代码。
//i want to import excel to data table
dt = new DataTable();
using (SpreadsheetDocument document = SpreadsheetDocument.Open(path, false))
{
WorkbookPart workbookPart = document.WorkbookPart;
WorksheetPart worksheetPart = workbookPart.WorksheetParts.First();
OpenXmlReader reader = OpenXmlReader.Create(worksheetPart);
//row counter
int rcnt = 0;
while (reader.Read())
{
//find xml row element type
//to understand the element type you can change your excel file eg : test.xlsx to test.zip
//and inside that you may observe the elements in xl/worksheets/sheet.xml
//that helps to understand openxml better
if (reader.ElementType == typeof(Row))
{
//create data table row type to be populated by cells of this row
DataRow tempRow = dt.NewRow();
//***** HANDLE THE SECOND SENARIO*****
//if row has attribute means it is not a empty row
if (reader.HasAttributes)
{
//read the child of row element which is cells
//here first element
reader.ReadFirstChild();
do
{
//find xml cell element type
if (reader.ElementType == typeof(Cell))
{
Cell c = (Cell)reader.LoadCurrentElement();
string cellValue;
int actualCellIndex = CellReferenceToIndex(c);
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;
}
else
{
cellValue = c.CellValue.InnerText;
}
//if row index is 0 its header so columns headers are added & also can do some headers check incase
if (rcnt == 0)
{
dt.Columns.Add(cellValue);
}
else
{
// instead of tempRow[c.CellReference] = cellValue;
tempRow[actualCellIndex] = cellValue;
}
}
}
while (reader.ReadNextSibling());
//if its not the header row so append rowdata to the datatable
if (rcnt != 0)
{
dt.Rows.Add(tempRow);
}
rcnt++;
}
}
}
}