JioCinema Scraper: Real-Time OTT Content and Streaming Data Collection

import requests
from bs4 import BeautifulSoup

HEADERS = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
    "Accept-Language": "en-US,en;q=0.9",
}

def scrape_jiocinema_content(url):
    """
    Fetches movie or series metadata from a JioCinema content page.
    Returns a structured dictionary with title, genre, release year, and rating.
    """
    response = requests.get(url, headers=HEADERS)
    if response.status_code != 200:
        return None

    soup = BeautifulSoup(response.text, "lxml")

    return {
        "Title": soup.find("h1", {"class": "content-title"}).text.strip()
            if soup.find("h1", {"class": "content-title"}) else "N/A",

        "Genre": soup.find("span", {"class": "content-genre"}).text.strip()
            if soup.find("span", {"class": "content-genre"}) else "N/A",

        "Release Year": soup.find("span", {"class": "release-year"}).text.strip()
            if soup.find("span", {"class": "release-year"}) else "N/A",

        "Rating": soup.find("div", {"class": "content-rating"}).text.strip()
            if soup.find("div", {"class": "content-rating"}) else "N/A"
    }

# Example JioCinema content URL
jiocinema_url = "https://www.jiocinema.com/movie/example"
data = scrape_jiocinema_content(jiocinema_url)

print(data)