Python script to parse operations from OTP bank statement

OTP.py

# This script extracts operations from the statement (saved from online.otpbank.ru),
# and prints only the ones with bonuses

# Setup:
# a) install Python3
# b) pip install BeautifulSoup4

# Guide:
# 1. Go to online.otpbank.ru
# 2. Select the card
# 3. Select the period
# 4. Scroll to the bottom, so all operations are loaded
# 5. Save the page as 'OTP.html' (you can use any name)
# 6. Run this script: 'OTP.py OTP.html'

import argparse
import datetime
import decimal

from bs4        import BeautifulSoup        # pip install BeautifulSoup4
from functools  import reduce

def parse_statement(html_content):
    months = \
        (' января ',    '.01.'), \
        (' февраля ',   '.02.'), \
        (' марта ',     '.03.'), \
        (' апреля ',    '.04.'), \
        (' мая ',       '.05.'), \
        (' июня ',      '.06.'), \
        (' июля ',      '.07.'), \
        (' августа ',   '.08.'), \
        (' сентября ',  '.09.'), \
        (' октября ',   '.10.'), \
        (' ноября ',    '.11.'), \
        (' декабря ',   '.12.'), 

    history = []

    soup = BeautifulSoup(html_content, 'html.parser')

    operations = soup.find_all('div', attrs={'data-name': 'accordion-item'})
    for op in operations:

        if not op.find('span', string='Бонусные рубли'):
            continue
        
        history.append({})

        sum_span = op.find('span', attrs={'data-testid': 'operation-sum'})
        history[-1]['sum'] = sum_span.get_text(strip=True)[:-2].replace(' ', '')
        
        bonus_span = op.find('span', attrs={'data-testid': 'operation-bonus'})
        history[-1]['bonus'] = bonus_span.get_text(strip=True)
        
        container = op.find('div', attrs={'data-name': 'statistic-container'})
        
        items = container.find_all('div', attrs={'data-name': 'statistic-item'}, recursive=False)
        for item in items:
            type_span = item.find('span')
            if not type_span:
                continue
            type = type_span.get_text(strip=True)
                
            value_span = item.find('span', attrs={'data-id': lambda x: x and x.startswith('statistic-item-value-')})
            value = value_span.get_text(strip=True)
            match type:
                # case 'Бонусные рубли':
                #    history[-1]['bonus'] = value
                case 'Дата':
                    # history[-1]['date'] = value
                    # (c) https://stackoverflow.com/a/9479972/536172
                    timestamp = reduce(lambda a, kv: a.replace(*kv), months, value)
                    history[-1]['date'] = datetime.datetime.strptime(timestamp, '%d.%m.%Y %H:%M:%S')
                    
    return history

def main():
    parser = argparse.ArgumentParser(description='Prints bonus operations from the statement saved from online.otpbank.ru')
    parser.add_argument('source', nargs='?', default='OTP.html', help='Source HTML file with statement')
    args = parser.parse_args()

    with open(args.source, 'r', encoding='utf-8') as file:
        html_content = file.read()

    history = parse_statement(html_content)
    
    total_sum = 0
    total_bonus = 0
    for op in history:
        print(f"{op['date']} {op['sum']:>8} {op['bonus']:>8}")
        total_sum += decimal.Decimal(op['sum'])
        total_bonus += decimal.Decimal(op['bonus'])
    print(f"TOTAL              {total_sum}   {total_bonus}")

if __name__ == "__main__":
    main()