Google Maps F&B Market Research via API

import requests, os

HEADERS = {"x-api-key": os.environ["SCAVIO_API_KEY"]}

def scan_fb_market(city: str, cuisine_types: list) -> dict:
    """Scan F&B market density and quality by cuisine type."""
    market_data = {}

    for cuisine in cuisine_types:
        resp = requests.post(
            "https://api.scavio.dev/api/v1/search",
            headers=HEADERS,
            json={
                "query": f"{cuisine} restaurants in {city}",
                "search_engine": "google_maps",
                "num_results": 20,
            },
            timeout=10,
        )
        results = resp.json().get("local_results", [])

        ratings = [r.get("rating", 0) for r in results if r.get("rating")]
        reviews = [r.get("reviews", 0) for r in results if r.get("reviews")]

        market_data[cuisine] = {
            "count": len(results),
            "avg_rating": sum(ratings) / len(ratings) if ratings else 0,
            "avg_reviews": sum(reviews) / len(reviews) if reviews else 0,
            "high_rated": len([r for r in ratings if r >= 4.5]),
            "price_levels": [r.get("price", "") for r in results],
        }

    return market_data

# Research 10 cuisine types in one city: 10 queries = $0.05
market = scan_fb_market("Austin TX", [
    "thai", "mexican", "italian", "japanese", "korean",
    "indian", "vietnamese", "mediterranean", "bbq", "vegan",
])

def competitive_density(city: str, target_cuisine: str, neighborhoods: list) -> list:
    """Map competitive density by neighborhood for a specific cuisine."""
    density_map = []

    for neighborhood in neighborhoods:
        resp = requests.post(
            "https://api.scavio.dev/api/v1/search",
            headers=HEADERS,
            json={
                "query": f"{target_cuisine} restaurant in {neighborhood} {city}",
                "search_engine": "google_maps",
                "num_results": 20,
            },
            timeout=10,
        )
        results = resp.json().get("local_results", [])
        ratings = [r.get("rating", 0) for r in results if r.get("rating")]

        density_map.append({
            "neighborhood": neighborhood,
            "restaurant_count": len(results),
            "avg_rating": sum(ratings) / len(ratings) if ratings else 0,
            "gap_indicator": "underserved" if len(results) < 5 else "saturated" if len(results) > 15 else "moderate",
        })

    return sorted(density_map, key=lambda x: x["restaurant_count"])

# Check 8 neighborhoods: 8 queries = $0.04
density = competitive_density("Austin TX", "korean", [
    "North Austin", "South Austin", "East Austin", "Downtown",
    "West Campus", "Mueller", "Domain", "Cedar Park",
])

def review_intelligence(city: str, cuisine: str) -> dict:
    """Extract market intelligence from review patterns."""
    resp = requests.post(
        "https://api.scavio.dev/api/v1/search",
        headers=HEADERS,
        json={
            "query": f"best {cuisine} restaurant {city}",
            "search_engine": "google_maps",
            "num_results": 20,
        },
        timeout=10,
    )
    results = resp.json().get("local_results", [])

    # Segment by performance
    top_performers = [r for r in results if r.get("rating", 0) >= 4.5 and r.get("reviews", 0) > 200]
    struggling = [r for r in results if r.get("rating", 0) < 4.0]
    new_entries = [r for r in results if r.get("reviews", 0) < 50]

    return {
        "total_market": len(results),
        "top_performers": [{
            "name": r.get("title"),
            "rating": r.get("rating"),
            "reviews": r.get("reviews"),
            "price": r.get("price", "unknown"),
        } for r in top_performers],
        "struggling_count": len(struggling),
        "new_entries_count": len(new_entries),
        "market_maturity": "mature" if len(top_performers) > 5 else "growing" if len(new_entries) > 5 else "stable",
    }

def full_fb_market_report(city: str, target_cuisine: str, neighborhoods: list) -> dict:
    """Generate comprehensive F&B market report for a target cuisine and city."""
    report = {
        "city": city,
        "cuisine": target_cuisine,
        "date": str(__import__("datetime").date.today()),
    }

    # Overall market scan
    report["market_overview"] = scan_fb_market(city, [target_cuisine])

    # Neighborhood density
    report["density_analysis"] = competitive_density(city, target_cuisine, neighborhoods)

    # Review intelligence
    report["review_intel"] = review_intelligence(city, target_cuisine)

    # Identify opportunity
    underserved = [n for n in report["density_analysis"] if n["gap_indicator"] == "underserved"]
    report["opportunity"] = {
        "underserved_neighborhoods": underserved,
        "recommendation": f"Consider {underserved[0]['neighborhood']}" if underserved else "Market appears saturated",
    }

    return report

# Full report: ~30 queries = $0.15 per city-cuisine combination
report = full_fb_market_report("Austin TX", "korean", [
    "North Austin", "South Austin", "East Austin", "Downtown",
    "West Campus", "Mueller", "Domain", "Cedar Park",
])
print(f"Opportunity: {report['opportunity']['recommendation']}")