parser

import requests
from bs4 import BeautifulSoup
from loguru import logger

PAGE_URL = "https://filmix.zone/filmy/page/{page_num}"


class FilmZone:
    def __init__(self):
        self.session = requests.Session()

    def get_html(self, url):
        res = self.session.get(url)
        res.encoding = 'windows-1251'
        if res.status_code == 200:
            return res.text
        else:
            logger.warning(res.content)

    def get_movie_info(self, movie_url):
        res = self.get_html(movie_url)
        soup = BeautifulSoup(res, 'lxml')
        name = soup.find('h1', {'class': 'name'}).text
        description = soup.find('div', {'class': 'full-story'}).text
        country = soup.find('div', {'class': 'item contry'}).find('a').text
        genre = soup.find('a', {'itemprop': 'genre'}).text
        year = soup.find('a', {'itemprop': 'copyrightYear'}).text
        video_url = soup.find('video')  # Проблема тут

    def get_movies_in_page(self, page_num=0):
        res = self.get_html(PAGE_URL.format(page_num=page_num))
        soup = BeautifulSoup(res, 'lxml')
        urls = soup.find_all('a', {'itemprop': 'url'})
        for x in urls:
            self.get_movie_info(x['href'])
            break  # Для теста парсим один фильм


if __name__ == '__main__':
    film = FilmZone()
    film.get_movies_in_page()