IMDb Scraper: Access Movie Metadata and Content Performance Insights

import requests
from bs4 import BeautifulSoup

HEADERS = {
    "User-Agent": "Mozilla/5.0",
    "Accept-Language": "en-US,en;q=0.8"
}

def fetch_imdb_movie_data(movie_url):
    page = requests.get(movie_url, headers=HEADERS)

    if page.status_code != 200:
        return {"error": "Unable to retrieve movie information"}

    soup = BeautifulSoup(page.text, "html.parser")

    movie_data = {
        "Movie_Title": soup.select_one("h1").get_text(strip=True) if soup.select_one("h1") else "N/A",
        "IMDb_Rating": soup.select_one("[data-testid='hero-rating-bar__aggregate-rating__score']").get_text(strip=True) if soup.select_one("[data-testid='hero-rating-bar__aggregate-rating__score']") else "N/A",
        "Release_Year": soup.select_one("a[href*='releaseinfo']").get_text(strip=True) if soup.select_one("a[href*='releaseinfo']") else "N/A",
        "Genre": ", ".join([g.get_text(strip=True) for g in soup.select("span.ipc-chip__text")[:3]]),
        "Runtime": soup.select_one("li[data-testid='title-techspec_runtime'] span").get_text(strip=True) if soup.select_one("li[data-testid='title-techspec_runtime'] span") else "N/A"
    }

    return movie_data

# Example IMDb Movie URL
imdb_movie_url = "https://www.imdb.com/title/tt0111161/"
movie_details = fetch_imdb_movie_data(imdb_movie_url)

print(movie_details)