数据:
mysql select 'xx1','xx2' union select xx1,xx2 from xx into outfile '/atmd/aa/bb.csv' fields terminated by '\t'
总的数据量有2500w
1在导出时,指定limit或者where条件,将数据在导出时就分别放在不同的文件里
2直接导出一个大的文件里的情况:
1使用spark分别读取再写文件,因为不需要做处理,这种方式有点大材小用
2 在excel可以打开的情况下,可以使用excel自带的代码工具VB,按照某一列去分割为多个文件:
https://www.microsoft.com/zh-cn/download/confirmation.aspx?id=13255
https://jingyan.baidu.com/article/64d05a0219ceacde55f73bf6.html
表sheet只有一个,名为“数据源”,选择查看代码---插入--模块---写入一下内容,再回到excel 表格窗口,执行 按钮...
3 使用linux命令拆分 split命令按行或者按大小拆分为多个文件
下面为方法2excel的vb方法模块
Sub CFGZB()
Dim myRange As Variant
Dim myArray
Dim titleRange As Range
Dim title As String
Dim columnNum As Integer
myRange = Application.InputBox(prompt:="请选择标题行:", Type:=8)
myArray = WorksheetFunction.Transpose(myRange)
Set titleRange = Application.InputBox(prompt:="请选择拆分的表头,必须是第一行,且为一个单元格,如:“姓名”", Type:=8)
title = titleRange.Value
columnNum = titleRange.Column
Application.ScreenUpdating = False
Application.DisplayAlerts = False
Dim i&, Myr&, Arr, num&
Dim d, k
For i = Sheets.Count To 1 Step -1
If Sheets(i).Name <> "数据源" Then
Sheets(i).Delete
End If
Next i
Set d = CreateObject("Scripting.Dictionary")
Myr = Worksheets("数据源").UsedRange.Rows.Count
Arr = Worksheets("数据源").Range(Cells(2, columnNum), Cells(Myr, columnNum))
For i = 1 To UBound(Arr)
d(Arr(i, 1)) = ""
Next
k = d.keys
For i = 0 To UBound(k)
Set conn = CreateObject("adodb.connection")
conn.Open "provider=Microsoft.ACE.OLEDB.12.0;extended properties=Excel 8.0;data source=" & ThisWorkbook.FullName
Sql = "select * from [数据源$] where " & title & " = '" & k(i) & "'"
Dim Nowbook As Workbook
Set Nowbook = Workbooks.Add
With Nowbook
With .Sheets(1)
.Name = k(i)
For num = 1 To UBound(myArray)
.Cells(1, num) = myArray(num, 1)
Next num
.Range("A2").CopyFromRecordset conn.Execute(Sql)
End With
End With
ThisWorkbook.Activate
Sheets(1).Cells.Select
Selection.Copy
Workbooks(Nowbook.Name).Activate
ActiveSheet.Cells.Select
Selection.PasteSpecial Paste:=xlPasteFormats, Operation:=xlNone,SkipBlanks:=False, Transpose:=False
Application.CutCopyMode = False
Nowbook.SaveAs ThisWorkbook.Path & "\" & k(i)
Nowbook.Close True
Set Nowbook = Nothing
Next i
conn.Close
Set conn = Nothing
Application.DisplayAlerts = True
Application.ScreenUpdating = True
End Sub