BritBox Scraper: Comprehensive OTT Series, Movies, and Streaming Insights

import requests
from bs4 import BeautifulSoup

# Headers to mimic a real browser
HEADERS = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)",
"Accept-Language": "en-US,en;q=0.8",
}

def scrape_britbox_content(url):
    response = requests.get(url, headers=HEADERS)
    
    if response.status_code != 200:
        print("Failed to fetch page:", response.status_code)
        return None

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

    # Helper function to safely extract text
    def extract_text(tag, attrs):
        element = soup.find(tag, attrs)
        return element.get_text(strip=True) if element else "N/A"

    # Extracting content details
    content_data = {
        "Title": extract_text("h1", {"class": "content-title"}),
        "Content_Type": extract_text("span", {"class": "content-format"}),
        "Genre": extract_text("span", {"class": "content-genre"}),
        "Seasons": extract_text("span", {"class": "season-count"}),
        "Availability_Status": extract_text("div", {"class": "availability-info"})
    }

    return content_data

# Example BritBox content URL (Replace with actual URL)
britbox_content_url = "https://www.britbox.com/example-show"
data_output = scrape_britbox_content(britbox_content_url)

# Print extracted data
print(data_output)