imdb.com/top scraping

imdb_scrap.py

from typing import final
import requests
import pprint
from bs4 import BeautifulSoup

def get_recent():
    URL = f"https://www.imdb.com/chart/top/"
    r = requests.get(URL)
    
    soup = BeautifulSoup(r.content, 'lxml')
    items = soup.find_all('tbody', {'class': 'lister-list'})

    final_data = []

    for item in items:
        for list in item.find_all('tr'):
            for poster_column in list.find_all('td', {'class': 'posterColumn'}):
                rank = poster_column.find('span', {'name': 'rk'})['data-value']
                poster = poster_column.a.img['src']

            for title_column in list.find_all('td', {'class': 'titleColumn'}):
                link = title_column.a.get('href')
                title = title_column.a.text
                release_year = title_column.find('span', {'class': 'secondaryInfo'}).text.strip('(,)')

            for rating_column in list.find_all('td', {'class': 'ratingColumn imdbRating'}):
                rating = rating_column.text.strip()

                data = {'rank': rank, 'poster': poster, 'link': f'https://imdb.com{link}', 'id': link[7:-1], 'title': title, 'release_year': release_year, 'rating': rating}
                final_data.append(data)

    return pprint.pprint(final_data)

get_recent()

Result : https://nekobin.com/tolibirufo