python實現excel轉txt代碼

python實現excel轉txt代碼

excel_to_txt.py

from datetime import datetime, timedelta
import os
import pytz
import pandas as pd

def excel_to_txt(name, date):
    # Read Excel file into a DataFrame
    # df = pd.read_excel(f'/opt/module/data/excel/{name}.xlsx', header=None,skiprows=1)
    # df = pd.read_excel(f'hdfs://mycluster:8020/origin_data/hr_cn/db/is_gs_recruitment_data_full/excel/{name}.xlsx', header=None,skiprows=1)
    df = pd.read_excel(f'C:/Users/SARAH.X/PycharmProjects/pythonProject/data/excel/{name}.xlsx', header=None, skiprows=1)

    # Define output directory and path
    # output_directory = os.path.join('/opt/module/data', 'txt', date)
    output_directory = os.path.join('C:/Users/SARAH.X/PycharmProjects/pythonProject/data/', 'txt', date)
    os.makedirs(output_directory, exist_ok=True)  # Create directory if it doesn't exist
    output_path = os.path.join(output_directory, f'{name}.txt')

    # Check if the file already exists, if so, remove it
    if os.path.exists(output_path):
        os.remove(output_path)
        print(f'Existing file {output_path} removed.')

    # Write DataFrame to a new text file
    print('开始写入txt文件')
    df.to_csv(output_path, header=None, sep='\t', index=False)
    print('文件写入成功!')
    return output_path

if __name__ == '__main__':
    current_time = datetime.now(pytz.timezone('Asia/Shanghai'))
    one_day_ago = (current_time - timedelta(days=1)).strftime('%Y-%m-%d')
    local_file_path = excel_to_txt('example4', one_day_ago)
    print(local_file_path)