tg-channels-parser/start.py

import requests
from bs4 import BeautifulSoup as bs
from datetime import datetime
import logging

logfile = 'data.log'

logging.basicConfig(filename=logfile,
                    format='%(asctime)s %(levelname)-2s %(message)s',
                    filemode='w',
                    datefmt='%Y-%m-%d %H:%M:%S',
                    level=logging.INFO)


def get_data(url):

    r = requests.get(url)
    html = bs(r.text, 'html.parser')
    title_channel = html.title.string
    try:
        last_post_date = html.find_all('time')[-1]['datetime']
    except IndexError:
        return
    else:
        # 2021-12-24T09:42:43+00:00
        last_post_date = datetime.strptime(
            last_post_date, "%Y-%m-%dT%H:%M:%S%z")
        title_channel = title_channel.split(' – ')[0]
    return {
        'title_channel': title_channel,
        'last_post_date': datetime.strftime(last_post_date, '%Y-%m-%d %H:%M')
    }


print("СТАРТ. Добываю информацию. Подождите немного...")
with open('channels.txt', 'r') as file:
    links = file.readlines()
    links = [link.rstrip() for link in links]

for link in links:
    data = get_data(link)
    if data:
        logging.info(
            f"{data['title_channel']} | Самый новый пост: {data['last_post_date']}")
    else:
        logging.error(f'Не удалось получить данные по ссылке {link}')

print(f"====\nВЫПОЛНЕНО. Результат смотрите в файле {logfile}")