download_expenses.py

import os
import requests
import pandas as pd

def download_expense(link, file_name, folder):
    response = requests.get(link)
    
    if response.status_code == 200:
        os.makedirs(folder, exist_ok=True)
        with open(os.path.join(folder, file_name), 'wb') as f:
            f.write(response.content)
    else:
        print(f"Failed to download file from {link}")

def parse_and_download_expenses(file_path):
    df = pd.read_excel(file_path)
    root_folder = "Expenses"

    for _, row in df.iterrows():
        try:
            document_date = pd.to_datetime(row.iloc[4])
        except:
            document_date = pd.to_datetime(row.iloc[3])

        expense_description = row.iloc[9].replace('.', '_')
        total_amount = str(row.iloc[6]).replace('.', '_')
        link = row.iloc[18]

        file_name = f"{document_date.strftime('%Y-%m-%d')}_{expense_description}_{total_amount}.jpg"
        folder = os.path.join(root_folder, document_date.strftime('%Y-%m'))

        download_expense(link, file_name, folder)
        print(f"Downloaded: {file_name} to folder {folder}")

if __name__ == "__main__":
    file_path = "path/to/your/xlsx/file.xlsx"
    parse_and_download_expenses(file_path)