使用Excel OleDb按图纸顺序获取图纸名称

你能不能不从0到名字计数-1的循环表?这样你就可以把它们按正确的顺序排列。

编辑

/// <summary>
/// This method retrieves the excel sheet names from 
/// an excel workbook.
/// </summary>
/// <param name="excelFile">The excel file.</param>
/// <returns>String[]</returns>
private String[] GetExcelSheetNames(string excelFile)
{
    OleDbConnection objConn = null;
    System.Data.DataTable dt = null;

    try
    {
        // Connection String. Change the excel file to the file you
        // will search.
        String connString = "Provider=Microsoft.Jet.OLEDB.4.0;" + 
          "Data Source=" + excelFile + ";Extended Properties=Excel 8.0;";
        // Create connection object by using the preceding connection string.
        objConn = new OleDbConnection(connString);
        // Open connection with the database.
        objConn.Open();
        // Get the data table containg the schema guid.
        dt = objConn.GetOleDbSchemaTable(OleDbSchemaGuid.Tables, null);

        if(dt == null)
        {
           return null;
        }

        String[] excelSheets = new String[dt.Rows.Count];
        int i = 0;

        // Add the sheet name to the string array.
        foreach(DataRow row in dt.Rows)
        {
           excelSheets[i] = row["TABLE_NAME"].ToString();
           i++;
        }

        // Loop through all of the sheets if you want too...
        for(int j=0; j < excelSheets.Length; j++)
        {
            // Query each excel sheet.
        }

        return excelSheets;
   }
   catch(Exception ex)
   {
       return null;
   }
   finally
   {
      // Clean up.
      if(objConn != null)
      {
          objConn.Close();
          objConn.Dispose();
      }
      if(dt != null)
      {
          dt.Dispose();
      }
   }
}

摘自 Article 在这个项目上。

由于上述代码不包括提取Excel 2007工作表名称列表的过程,以下代码也适用于Excel(97-2003)和Excel 2007:

public List<string> ListSheetInExcel(string filePath)
{
   OleDbConnectionStringBuilder sbConnection = new OleDbConnectionStringBuilder();
   String strExtendedProperties = String.Empty;
   sbConnection.DataSource = filePath;
   if (Path.GetExtension(filePath).Equals(".xls"))//for 97-03 Excel file
   {
      sbConnection.Provider = "Microsoft.Jet.OLEDB.4.0";
      strExtendedProperties = "Excel 8.0;HDR=Yes;IMEX=1";//HDR=ColumnHeader,IMEX=InterMixed
   }
   else if (Path.GetExtension(filePath).Equals(".xlsx"))  //for 2007 Excel file
   {
      sbConnection.Provider = "Microsoft.ACE.OLEDB.12.0";
      strExtendedProperties = "Excel 12.0;HDR=Yes;IMEX=1";
   }
   sbConnection.Add("Extended Properties",strExtendedProperties);
   List<string> listSheet = new List<string>();
   using (OleDbConnection conn = new OleDbConnection(sbConnection.ToString()))
   {
     conn.Open();
     DataTable dtSheet = conn.GetOleDbSchemaTable(OleDbSchemaGuid.Tables, null);         
     foreach (DataRow drSheet in dtSheet.Rows)
     {
        if (drSheet["TABLE_NAME"].ToString().Contains("$"))//checks whether row contains '_xlnm#_FilterDatabase' or sheet name(i.e. sheet name always ends with $ sign)
        {
             listSheet.Add(drSheet["TABLE_NAME"].ToString());
        } 
     }
  }
 return listSheet;
}

上述函数返回两种excel类型(9720032007)的特定excel文件中的工作表列表。

在实际的MSDN文档中找不到这个,但论坛的一位版主说

恐怕OLEDB不能像在Excel中那样保留图纸顺序

Excel Sheet Names in Sheet Order

似乎这将是一个足够普遍的要求,有一个体面的解决办法。

这是简短、快速、安全和可用的。。。

public static List<string> ToExcelsSheetList(string excelFilePath)
{
    List<string> sheets = new List<string>();
    using (OleDbConnection connection = 
            new OleDbConnection((excelFilePath.TrimEnd().ToLower().EndsWith("x")) 
            ? "Provider=Microsoft.ACE.OLEDB.12.0;Data Source='" + excelFilePath + "';" + "Extended Properties='Excel 12.0 Xml;HDR=YES;'"
            : "provider=Microsoft.Jet.OLEDB.4.0;Data Source='" + excelFilePath + "';Extended Properties=Excel 8.0;"))
    {
        connection.Open();
        DataTable dt = connection.GetOleDbSchemaTable(OleDbSchemaGuid.Tables, null);
        foreach (DataRow drSheet in dt.Rows)
            if (drSheet["TABLE_NAME"].ToString().Contains("$"))
            {
                string s = drSheet["TABLE_NAME"].ToString();
                sheets.Add(s.StartsWith("'")?s.Substring(1, s.Length - 3): s.Substring(0, s.Length - 1));
            }
        connection.Close();
    }
    return sheets;
}

另一种方式:

xls(x)文件只是存储在*.zip容器中的*.xml文件的集合。 解压文件夹docProps中的文件“app.xml”。

<?xml version="1.0" encoding="UTF-8" standalone="true"?>
-<Properties xmlns:vt="http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes" xmlns="http://schemas.openxmlformats.org/officeDocument/2006/extended-properties">
<TotalTime>0</TotalTime>
<Application>Microsoft Excel</Application>
<DocSecurity>0</DocSecurity>
<ScaleCrop>false</ScaleCrop>
-<HeadingPairs>
  -<vt:vector baseType="variant" size="2">
    -<vt:variant>
      <vt:lpstr>Arbeitsblätter</vt:lpstr>
    </vt:variant>
    -<vt:variant>
      <vt:i4>4</vt:i4>
    </vt:variant>
  </vt:vector>
</HeadingPairs>
-<TitlesOfParts>
  -<vt:vector baseType="lpstr" size="4">
    <vt:lpstr>Tabelle3</vt:lpstr>
    <vt:lpstr>Tabelle4</vt:lpstr>
    <vt:lpstr>Tabelle1</vt:lpstr>
    <vt:lpstr>Tabelle2</vt:lpstr>
  </vt:vector>
</TitlesOfParts>
<Company/>
<LinksUpToDate>false</LinksUpToDate>
<SharedDoc>false</SharedDoc>
<HyperlinksChanged>false</HyperlinksChanged>
<AppVersion>14.0300</AppVersion>
</Properties>

该文件为德语文件(Arbeitsbl·tter=工作表)。 表名(表3等)的顺序正确。您只需要阅读这些标记;)

当做

我使用@kraeppy的答案中提供的信息创建了以下函数( https://stackoverflow.com/a/19930386/2617732 )。这需要使用.net framework v4.5,并且需要对System.IO.Compression的引用。这仅适用于xlsx文件,而不适用于较旧的xls文件。

    using System.IO.Compression;
    using System.Xml;
    using System.Xml.Linq;

    static IEnumerable<string> GetWorksheetNamesOrdered(string fileName)
    {
        //open the excel file
        using (FileStream data = new FileStream(fileName, FileMode.Open))
        {
            //unzip
            ZipArchive archive = new ZipArchive(data);

            //select the correct file from the archive
            ZipArchiveEntry appxmlFile = archive.Entries.SingleOrDefault(e => e.FullName == "docProps/app.xml");

            //read the xml
            XDocument xdoc = XDocument.Load(appxmlFile.Open());

            //find the titles element
            XElement titlesElement = xdoc.Descendants().Where(e => e.Name.LocalName == "TitlesOfParts").Single();

            //extract the worksheet names
            return titlesElement
                .Elements().Where(e => e.Name.LocalName == "vector").Single()
                .Elements().Where(e => e.Name.LocalName == "lpstr")
                .Select(e => e.Value);
        }
    }

Sub Macro1()
'
' Macro1 Macro
'

'
Dim i As Integer
For i = 1 To Sheets.Count
 Dim prefix As String
 prefix = i
 If Len(prefix) < 4 Then
  prefix = "000"
 ElseIf Len(prefix) < 3 Then
  prefix = "00"
 ElseIf Len(prefix) < 2 Then
  prefix = "0"
 End If
 Dim sheetName As String
 sheetName = Sheets(i).Name
 Dim names
 names = Split(sheetName, "-")
 If (UBound(names) > 0) And IsNumeric(names(0)) Then
  'do nothing
 Else
  Sheets(i).Name = prefix & i & "-" & Sheets(i).Name
 End If
Next

End Sub

更新: 在阅读了@SidHoland关于BIFF的评论后,一个想法闪现出来。以下步骤可以通过代码完成。不知道您是否真的想这样做,以获得相同顺序的工作表名称。让我知道,如果你需要帮助,通过代码来做到这一点。

1. Consider XLSX as a zip file. Rename *.xlsx into *.zip
2. Unzip
3. Go to unzipped folder root and open /docprops/app.xml
4. This xml contains the sheet name in the same order of what you see.
5. Parse the xml and get the sheet names

更新: 另一个解决方案-NPOI在这里可能会有所帮助 http://npoi.codeplex.com/

 FileStream file = new FileStream(@"yourexcelfilename", FileMode.Open, FileAccess.Read);

      HSSFWorkbook  hssfworkbook = new HSSFWorkbook(file);
        for (int i = 0; i < hssfworkbook.NumberOfSheets; i++)
        {
            Console.WriteLine(hssfworkbook.GetSheetName(i));
        }
        file.Close();

此解决方案适用于xls。我没有尝试xlsx。

谢谢

埃森

这对我有用。从这里偷来的: How do you get the name of the first page of an excel workbook?

object opt = System.Reflection.Missing.Value;
Excel.Application app = new Microsoft.Office.Interop.Excel.Application();
Excel.Workbook workbook = app.Workbooks.Open(WorkBookToOpen,
                                         opt, opt, opt, opt, opt, opt, opt,
                                         opt, opt, opt, opt, opt, opt, opt);
Excel.Worksheet worksheet = workbook.Worksheets[1] as Microsoft.Office.Interop.Excel.Worksheet;
string firstSheetName = worksheet.Name;

试试这个。以下是按顺序获取图纸名称的代码。

private Dictionary<int, string> GetExcelSheetNames(string fileName)
{
    Excel.Application _excel = null;
    Excel.Workbook _workBook = null;
    Dictionary<int, string> excelSheets = new Dictionary<int, string>();
    try
    {
        object missing = Type.Missing;
        object readOnly = true;
        Excel.XlFileFormat.xlWorkbookNormal
        _excel = new Excel.ApplicationClass();
        _excel.Visible = false;
        _workBook = _excel.Workbooks.Open(fileName, 0, readOnly, 5, missing,
            missing, true, Excel.XlPlatform.xlWindows, "\\t", false, false, 0, true, true, missing);
        if (_workBook != null)
        {
            int index = 0;
            foreach (Excel.Worksheet sheet in _workBook.Sheets)
            {
                // Can get sheet names in order they are in workbook
                excelSheets.Add(++index, sheet.Name);
            }
        }
    }
    catch (Exception e)
    {
        return null;
    }
    finally
    {
        if (_excel != null)
        {

            if (_workBook != null)
                _workBook.Close(false, Type.Missing, Type.Missing);
            _excel.Application.Quit();
        }
        _excel = null;
        _workBook = null;
    }
    return excelSheets;
}

根据MSDN,对于Excel中的电子表格,它可能无法工作,因为Excel文件不是真实的数据库。因此,您将无法按工作表在工作簿中的可视化顺序获取工作表名称。

使用interop根据图纸的视觉外观获取图纸名称的代码:

添加对Microsoft Excel 12.0对象库的引用。

以下代码将按照工作簿中存储的实际顺序给出工作表名称,而不是排序后的名称。

示例代码:

using Microsoft.Office.Interop.Excel;

string filename = "C:\\romil.xlsx";

object missing = System.Reflection.Missing.Value;

Microsoft.Office.Interop.Excel.Application excel = new Microsoft.Office.Interop.Excel.Application();

Microsoft.Office.Interop.Excel.Workbook wb =excel.Workbooks.Open(filename,  missing,  missing,  missing,  missing,missing,  missing,  missing,  missing,  missing,  missing,  missing,  missing,  missing,  missing);

ArrayList sheetname = new ArrayList();

foreach (Microsoft.Office.Interop.Excel.Worksheet  sheet in wb.Sheets)
{
    sheetname.Add(sheet.Name);
}

另一方面,workbook.xml文件包含sheetId属性,该属性确定从1到工作表数量的顺序。这符合OOXML规范。xml被描述为保存工作表顺序的地方。

因此,我建议在从XLSX中提取工作簿.xml后再阅读它。不是app.xml。不要使用docProps/app.xml,而是使用xl/workbook.xml并查看元素,如下所示-

`

<workbook xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships">
  <fileVersion appName="xl" lastEdited="5" lowestEdited="5" rupBuild="9303" /> 
  <workbookPr defaultThemeVersion="124226" /> 
- <bookViews>
  <workbookView xWindow="120" yWindow="135" windowWidth="19035" windowHeight="8445" /> 
  </bookViews>
- <sheets>
  <sheet name="By song" sheetId="1" r:id="rId1" /> 
  <sheet name="By actors" sheetId="2" r:id="rId2" /> 
  <sheet name="By pit" sheetId="3" r:id="rId3" /> 
  </sheets>
- <definedNames>
  <definedName name="_xlnm._FilterDatabase" localSheetId="0" hidden="1">'By song'!$A$1:$O$59</definedName> 
  </definedNames>
  <calcPr calcId="145621" /> 
  </workbook>