import requests
from bs4 import BeautifulSoup
import pandas as pd
import time
# Define the URL
url = 'https://www.imdb.com/list/ls053501318/'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
    'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.3',
    'Accept-Encoding': 'none',
    'Accept-Language': 'en-US,en;q=0.8',
    'Connection': 'keep-alive'
    }
# Send a GET request to the URL
response = requests.get(url, headers=headers)
# Parse the HTML content using BeautifulSoup
soup = BeautifulSoup(response.content, 'html.parser')
# Find the list items containing actor information
actor_items = soup.find_all('li', class_='ipc-metadata-list-summary-item')
# Extract details for each actor
actors = []
for item in actor_items:
    # Ensure the element for name exists
    name_element = item.find('span', class_='ipc-title__text')
    name = name_element.text.strip() 
    
    # Ensure the element for details exists
    details_element = item.find('span', class_='ipc-html-content-inner-div')
    details = details_element.text.strip()
    
    actors.append({
        'name': name,
        'details': details
    })

 # Add a delay to avoid overwhelming the server
time.sleep(1)