search.py

import requests
import pandas as pd
import time
import os

# ✅ Retrieve the API key from Hugging Face secrets
API_KEY = os.getenv("SERPAPI_API_KEY", "")  # This will get the API key from Hugging Face secrets

# ✅ Check if the API_KEY is set
if not API_KEY:
    raise ValueError("API key is missing. Please set the SERPAPI_API_KEY environment variable.")

def get_collaboration_data(competitors, target="Virgin Media"):
    results = []
    
    # Iterate over each competitor to search for collaborations with Virgin Media
    for comp in competitors:
        query = f"{comp} {target} partnership OR collaboration"
        params = {
            "q": query,
            "api_key": API_KEY,
            "engine": "google",  # You can switch to other engines if needed
            "num": 5  # Number of results to return per query
        }

        print(f"Searching: {query}")  # Log the query for tracking
        try:
            # Make a request to the SERP API
            response = requests.get("https://serpapi.com/search", params=params)
            response.raise_for_status()  # Check for request errors (e.g., 4xx, 5xx)
            
            # Parse the JSON response
            data = response.json()

            # Extract the organic results
            for item in data.get("organic_results", []):
                results.append({
                    "Competitor": comp,
                    "Title": item.get("title", "No title available"),
                    "Link": item.get("link", "No link available"),
                    "Snippet": item.get("snippet", "No snippet available")
                })
        except requests.exceptions.RequestException as e:
            print(f"Error fetching data for {comp}: {e}")
        except ValueError as e:
            print(f"Error parsing JSON response for {comp}: {e}")
        
        time.sleep(1)  # ✅ Respect API rate limits

    # Return results as a DataFrame
    return pd.DataFrame(results)