Hollywood in the CloudBox Office Analytics

import os
import json
import csv
import logging
import urllib.request
import urllib.parse
import boto3
from io import StringIO

# Configure logging
logger = logging.getLogger()
logger.setLevel(logging.INFO)

# S3 configuration
S3_BUCKET = "tmdb-data-071125"

# Dedicated prefixes for each dataset
TOP_RATED_KEY = "tmdb/raw/top_rated/top_rated_movies.csv"
UPCOMING_KEY = "tmdb/raw/upcoming/upcoming_movies.csv"
GENRES_KEY = "tmdb/raw/genres/movie_genres.csv"

# TMDB configuration
TMDB_BASE_URL = "https://api.themoviedb.org/3"
TMDB_API_TOKEN = os.getenv("TMDB_API_TOKEN")

# AWS client
s3_client = boto3.client("s3")

def _make_tmdb_request(endpoint: str, params: dict | None = None) -> dict:
    """Perform a GET request to TMDB using urllib with Bearer token auth."""
    if not TMDB_API_TOKEN:
        logger.error("TMDB_API_TOKEN environment variable is not set")
        raise RuntimeError("TMDB_API_TOKEN environment variable is required")
    
    if params is None:
        params = {}
    
    query = urllib.parse.urlencode(params)
    url = f"{TMDB_BASE_URL}{endpoint}"
    if query:
        url = f"{url}?{query}"
    
    logger.info(f"Requesting TMDB URL: {url}")
    
    headers = {
        "Authorization": f"Bearer {TMDB_API_TOKEN}",
        "Accept": "application/json"
    }
    
    request = urllib.request.Request(url, headers=headers)
    
    with urllib.request.urlopen(request) as response:
        return json.loads(response.read().decode())

def lambda_handler(event, context):
    """Main Lambda handler to fetch and store TMDB data"""
    try:
        # Fetch top rated movies
        top_rated = _make_tmdb_request("/movie/top_rated", {"page": 1})
        # Process and upload to S3...
        
        return {
            'statusCode': 200,
            'body': json.dumps('Data ingestion completed successfully')
        }
    except Exception as e:
        logger.error(f"Error: {str(e)}")
        raise