Sony LIV Scraper: Streamline Streaming Content Research and Monitoring

import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin

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

def get_text(soup, selector):
element = soup.select_one(selector)
return element.get_text(" ", strip=True) if element else "N/A"

def scrape_sonyliv_content(page_url):
try:
response = requests.get(
page_url,
headers=HEADERS,
timeout=15
)
response.raise_for_status()
except requests.RequestException:
return None

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

content = {
"Title": get_text(soup, "h1"),
"Genre": get_text(soup, ".genre"),
"Language": get_text(soup, ".language"),
"Rating": get_text(soup, ".rating"),
"Release_Date": get_text(soup, ".release-date"),
"Description": get_text(soup, ".description"),
"Content_URL": page_url
}
return content

# Example publicly accessible Sony LIV content URL
sonyliv_url = "https://www.sonyliv.com/example-content"
result = scrape_sonyliv_content(sonyliv_url)

if result:
for field, value in result.items():
print(f"{field}: {value}")
else:
print("Content data could not be retrieved.")