如何使用 Python 自动命名刚刚从 csv 文件生成的 Excel 文件

Question

我需要以自动方式将 csv 文件转换为 Excel 文件。我无法用相应的 csv 文件的名称命名 Excel 文件。 我将 csv 文件保存为“Trials_1”、“Trials_2”、“Trilas_3”，但是使用我编写的 Python 代码给了我一个错误，并要求我提供名为“Trials_4”的 csv 文件。然后，如果我将 csv 文件“Trials_1”重命名为“Trials_4”，程序将运行并生成一个名为“Trials_1”的 Excel 文件。 如何更正我的代码？

'''

import csv

import openpyxl as xl

import os, os.path

directory=r'C:\\Users\\PycharmProjects\\input\\'

folder=r'C:\\Users\\PycharmProjects\\output\\'

for csv_file in os.listdir(directory):

def csv_to_excel(csv_file, excel_file):

    csv_data=[]

    with open(os.path.join(directory, csv_file)) as file_obj:

        reader=csv.reader(file_obj)

        for row in reader:

            csv_data.append(row)

    workbook= xl.Workbook()

    sheet=workbook.active

    for row in csv_data:

        sheet.append(row)

        workbook.save(os.path.join(folder,excel_file))


if __name__=="__main__":
    m = sum(1 for f in os.listdir(directory) if os.path.isfile(os.path.join(directory, f)))
    new_name = "{}Trial_{}.csv".format(directory, m + 1)
    k = sum(1 for file in os.listdir(folder) if os.path.isfile(os.path.join(folder, file)))
    new_name_e = "{}Trial_{}.xlsx".format(folder, k + 1)
    csv_to_excel(new_name,new_name_e)

'''

谢谢。

Answer 1

您好 Annachiara，欢迎来到 StackOverflow，

我将只使用 pandas 来修改“csv_to_excel”函数。

在此之前，您应该安装“xlsxwriter”：

pip install XlsxWriter

那么函数应该是这样的：

def csv_to_excel(csv_file,excel_file,csv_sep=';'):

    # read the csv file with pandas
    df=pd.read_csv(csv_file,sep=csv_sep)
    # create the excel file
    writer=pd.ExcelWriter(excel_file, engine='xlsxwriter')
    # copy the csv content (df) into the excel file
    df.to_excel(writer,index=False)
    # save the excel file
    writer.save()
    # print what you converted for reference
    print(f'csv file {csv_file} saved as excel in {excel_file}')

只需确保正确读取 csv：我只添加了分隔符参数，但您可能想要添加所有其他参数（如解析日期等）

然后你可以用for循环转换csv文件列表（我用了更多的步骤让它更清晰）

dir_in=r'C:\\Users\\PycharmProjects\\input\\'

dir_out=r'C:\\Users\\PycharmProjects\\output\\'

csvs_to_convert=os.listdir(dir_in)

for csv_file_in in csvs_to_convert:
    
    # remove extension from csv files
    file_name_no_extension=os.path.splitext(csv_file_in)[0]
    # add excel extension .xlsx
    excel_name_out=file_name_no_extension+'.xlsx'
    # write names with their directories
    complete_excel_name_out=os.path.join(dir_out,excel_name_out)
    complete_csv_name_in=os.path.join(dir_in,csv_file_in)
    # convert csv file to excel file
    csv_to_excel(complete_csv_name_in,complete_excel_name_out,csv_sep=';')

Answer 2

每个 csv 作为单独的 excel 文件

import glob
import pandas as pd
import os

csv_files = glob.glob('*.csv')
for filename in csv_files:
    sheet_name = os.path.split(filename)[-1].replace('.csv', '.xlsx')
    df = pd.read_csv(filename)
    df.to_excel(sheet_name, index=False)

不同工作表中同一excel中的所有csv

import glob
import pandas as pd
import os

# Create excel file
writer = pd.ExcelWriter('all_csv.xlsx')

csv_files = glob.glob('*.csv')
for filename in csv_files:
    sheet_name = os.path.split(filename)[-1].replace('.csv', '')
    df = pd.read_csv(filename)
    # Append each csv as sheet
    df.to_excel(writer, sheet_name=sheet_name, index=False)
writer.save()

Answer 3

假设您希望保持代码的相同结构，我只是修复了代码中的一些技术问题以使其正常工作（请将文件夹路径更改为您自己的）：

import csv

import openpyxl as xl

import glob, os, os.path

directory= 'input'

folder= '../output' # Since 'input' would be my cwd, need to step back a directory to reach 'output'

# Using your function, just passing different arguments for convinient.
def csv_to_excel(f_path, f_name):

    csv_data=[]

    with open(f_path, 'r') as file_obj:

        reader=csv.reader(file_obj)

        for row in reader:

            csv_data.append(row)

    workbook= xl.Workbook()

    sheet=workbook.active

    for row in csv_data:

        sheet.append(row)

        workbook.save(os.path.join(folder, f_name + ".xlsx"))


def main():
    os.chdir(directory) # Defining input directory as your cwd
    # Searching for all files with csv extention and sending each to your function
    for file in glob.glob("*.csv"):
        f_path = os.getcwd() + '\\' + file # Saving the absolute path to the file
        f_name = (os.path.splitext(file)[0]) # Saving the name of the file
        csv_to_excel(f_path, f_name) 

if __name__=="__main__":
    main()

附注： 请避免迭代函数的定义，因为您只需要定义一次函数。