Question

我发现this code使用python拆分CSV文件。

当A列发生变化时，我需要拆分3,000,000条记录CSV文件。我还需要在表格中再添加2个字段

空白（在每行旁边添加逗号）。
在最后一个字段中添加日期，但它应该向我询问日期。

是否有人能够帮助我为此代码添加2件事。

添加更多字段的提示

提示该字段应该是什么

我正在复制前面包含的链接中的代码

#!/usr/bin/env python3
import binascii
import csv
import os.path
import sys
from tkinter.filedialog import askopenfilename, askdirectory
from tkinter.simpledialog import askinteger

def split_csv_file(f, dst_dir, keyfunc):
    csv_reader = csv.reader(f)
    csv_writers = {}
    for row in csv_reader:
        k = keyfunc(row)
        if k not in csv_writers:
                    csv_writers[k] = csv.writer(open(os.path.join(dst_dir, k),
                                             mode='w', newline=''))
        csv_writers[k].writerow(row)

def get_args_from_cli():
    input_filename = sys.argv[1]
    column = int(sys.argv[2])
    dst_dir = sys.argv[3]
    return (input_filename, column, dst_dir)

def get_args_from_gui():
    input_filename = askopenfilename(
        filetypes=(('CSV', '.csv'),),
        title='Select CSV Input File')
    column = askinteger('Choose Table Column', 'Table column')
    dst_dir = askdirectory(title='Select Destination Directory')
    return (input_filename, column, dst_dir)

if __name__ == '__main__':
    if len(sys.argv) == 1:
        input_filename, column, dst_dir = get_args_from_gui()
    elif len(sys.argv) == 4:
        input_filename, column, dst_dir = get_args_from_cli()
    else:
        raise Exception("Invalid number of arguments")
    with open(input_filename, mode='r', newline='') as f:
        split_csv_file(f, dst_dir, lambda r: r[column-1]+'.csv')
        # if the column has funky values resulting in invalid filenames
        # replace the line from above with:
        # split_csv_file(f, dst_dir, lambda r: binascii.b2a_hex(r[column-1].encode('utf-8')).decode('utf-8')+'.csv')

谢谢

Answer 1

用VBS写的

basename = "csv_split_"
hasHeader = True    'Change to False if there is no header.

argCnt = WScript.Arguments.Count
If argCnt < 1 Then
    WScript.Echo "Drag a CSV over this script to edit it."
    WScript.Quit
End If
flnm = WScript.Arguments.Item(0)

set fs = WScript.CreateObject("Scripting.FileSystemObject")
set cv = fs.OpenTextFile (WScript.Arguments.Item(0))
If Not fs.FileExists(flnm) Or LCase(fs.GetExtensionName(flnm)) <> "csv" Then
    WScript.Echo "This script is meant for CSV only."
    WScript.Quit
End If
fol = fs.GetParentFolderName(flnm)
customValue = InputBox("What should the last column contain?", "Column Info")

Set pat = New RegExp
pat.Global = True
pat.IgnoreCase = True
pat.Pattern = "^(""[^""]*""|[^,]*)?,"
recentCol = ""
csvCount = 1
header = ""
cnt = 0

While Not cv.AtEndOfStream
    cnt = cnt + 1
    row = cv.ReadLine
    If Right(row,1) <> "," Then: comma = ",": Else: comma = "": End If
    Set col1 = pat.Execute(row)
    col = col1.Item(0).Value
    sameFile = true
    If recentCol <> "" Then
        If col <> recentCol And cnt > 2 Then
            csvCount = csvCount + 1
            sameFile = false
        End If
    Else
        header = row & comma & """Off Peak"",""Effective Date""" 
        Set csv = fs.OpenTextFile(fol & "\" & basename & csvcount & ".csv", 8, True)    
    End If
    recentCol = col
    If Not samefile Then
        csv.close
        Set csv = fs.OpenTextFile(fol & "\" & basename & csvcount & ".csv", 8, True)
    End If
    If hasHeader And (1 = cnt or Not samefile) Then
        csv.WriteLine(header)
    Else
        csv.WriteLine(row & comma & ",""" & customValue & """")
    End if
Wend

csv.Close

很棒！

使用python prompt为数据添加列到csv

1 个答案: