#!/usr/bin/env python3 """ Athens Restaurant Data Generator Since TripAdvisor blocks scraping, we'll generate realistic restaurant data based on actual Athens restaurant types and Greek cuisine """ import json import os import uuid import random import time from datetime import datetime, time as dt_time from urllib.parse import quote_plus from sqlalchemy import create_engine, text from typing import List, Dict import urllib.request class AthensRestaurantGenerator: """Generate realistic Athens restaurant data""" def __init__(self): # Database connection self.DATABASE_URL = f"postgresql://postgres:{quote_plus('F@f@k0s!!')}@localhost:5432/bookbeach" self.engine = create_engine(self.DATABASE_URL) # Photo directory self.photo_dir = "restaurant_photos" os.makedirs(self.photo_dir, exist_ok=True) # Athens restaurant data self.restaurant_names = [ "Thanasis", "Dionysos", "Funky Gourmet", "Spondi", "CTC", "Hytra", "Tudor Hall", "Varoulko Seaside", "Aleria", "Boschetto", "Kuzina", "Electra Roof Garden", "GB Roof Garden", "Point a Bar", "Strofi", "Psyrri Taverna", "Plaka Garden", "Philos Athens", "Atomium", "Lefteris o Politikos", "Thanasis Kebab", "Ta Karamanlidika tou Fani", "Liondi Traditional Greek", "Nolan", "Piato", "Cookoovaya", "Mironi", "Daphne's", "Psaras Taverna", "Maiandros", "Scholarhio", "Keelings", "Athenaeum InterContinental", "Matsuhisa Athens", "Balthazar", "Orizontes", "Akrotiri Lounge", "Life Gallery Athens", "Penthouse", "Dinner in the Sky", "Blue Pine", "Premiere", "Yafka", "Kanella", "Estiatorio Milos", "Seychelles", "Jimmy & the Fish", "Island Club Restaurant", "Macelleria", "Al Convento", "L'Abreuvoir", "La Scala", "Baba au Rum", "Monsieur Paul", "Pil Poul", "Telaro", "Nobu Athens", "Catch Bar Restaurant", "Artisanal", "Cellier Le Bistrot", "Clemente VIII", "Mamacas", "Roka", "Black Duck", "Alatsi", "Bread & Roses", "Fabrica de Vino", "Manouka", "Byzantino", "Andreas Restaurant", "Ergon House Athens", "Vezene", "Kastelorizo", "Salero", "Athiri Santorini", "Klimataria", "Ammos Estiatorio", "Moorings", "Selene", "Papadakis Restaurant", "Asterias Taverna", "Archeon Gefsis", "Kollias Restaurant", "Oikeio", "Ama Laxei Sto Melathron", "Fish Point", "Seven Jokers", "The Gatsby Athens", "Vintage Wine bar & Bistro", "Kiku", "Ostria", "Sardelles", "Noel", "By the Glass", "Gazi College", "Papaioannou", "Prosopa", "Barakos Estiatorio", "Psomi & Alati", "Gold Restaurant", "Paschalis", "Kapnikarea", "Athensreproducti", "Lukumades", "Cinco Jotas", "Tivoli", "Cookoovaya Mykonos", "Black Duck Garden", "Spilia", "Epsilon Restaurant", "Soil", "Alati", "Kremmydi", "Diverdi", "Cinque Wine & Deli Bar", "Seaven Art-i-Show", "BeeRaki", "Central Park", "Lotus Lounge", "Nolan Restaurant", "Okio", "Blue Lagoon Restaurant", "Fish Tavern Kavos", "Vosporos Fish Restaurant" ] self.cuisine_types = [ "Greek", "Mediterranean", "Seafood", "Traditional Greek", "Modern Greek", "Italian", "International", "European", "Contemporary", "Fine Dining", "Taverna", "Mezze", "Souvlaki", "Grill", "Pizza", "Fusion" ] self.neighborhoods = [ "Plaka", "Monastiraki", "Psyrri", "Kolonaki", "Exarchia", "Thiseio", "Koukaki", "Pangrati", "Glyfada", "Vouliagmeni", "Kifisia", "Marousi", "Piraeus", "Nea Smyrni", "Palaio Faliro", "Chalandri", "Agia Paraskevi", "Holargos", "Amarousi", "Vrilissia" ] self.greek_dishes = [ {"name": "Moussaka", "price": 12.50, "category": "Main Course"}, {"name": "Souvlaki", "price": 8.00, "category": "Grills"}, {"name": "Greek Salad", "price": 7.50, "category": "Salads"}, {"name": "Tzatziki", "price": 4.50, "category": "Appetizers"}, {"name": "Dolmades", "price": 6.00, "category": "Appetizers"}, {"name": "Spanakopita", "price": 5.50, "category": "Appetizers"}, {"name": "Pastitsio", "price": 11.00, "category": "Main Course"}, {"name": "Grilled Octopus", "price": 15.00, "category": "Seafood"}, {"name": "Lamb Kleftiko", "price": 18.00, "category": "Main Course"}, {"name": "Fried Calamari", "price": 12.00, "category": "Seafood"}, {"name": "Feta Saganaki", "price": 6.50, "category": "Appetizers"}, {"name": "Avgolemono Soup", "price": 5.00, "category": "Soups"}, {"name": "Grilled Sea Bass", "price": 22.00, "category": "Seafood"}, {"name": "Gemista", "price": 9.50, "category": "Main Course"}, {"name": "Keftedes", "price": 7.00, "category": "Appetizers"}, {"name": "Baklava", "price": 4.00, "category": "Desserts"}, {"name": "Galaktoboureko", "price": 4.50, "category": "Desserts"}, {"name": "Greek Coffee", "price": 2.50, "category": "Beverages"}, {"name": "Ouzo", "price": 3.50, "category": "Beverages"}, {"name": "Retsina Wine", "price": 4.00, "category": "Beverages"}, {"name": "Grilled Lamb Chops", "price": 20.00, "category": "Main Course"}, {"name": "Fassolada", "price": 6.50, "category": "Soups"}, {"name": "Horiatiki Salad", "price": 8.00, "category": "Salads"}, {"name": "Grilled Sardines", "price": 10.00, "category": "Seafood"}, {"name": "Yemista Peppers", "price": 8.50, "category": "Main Course"} ] self.descriptions = [ "Traditional Greek taverna serving authentic dishes in a cozy atmosphere", "Modern Greek cuisine with a contemporary twist on classic recipes", "Family-owned restaurant offering the best of Mediterranean flavors", "Elegant dining experience with panoramic views of the Acropolis", "Casual dining spot popular with locals for fresh seafood", "Historic taverna in the heart of Plaka serving traditional Greek food", "Upscale restaurant featuring innovative Greek cuisine", "Waterfront dining with spectacular sunset views", "Authentic Greek mezze and grilled specialties", "Fine dining establishment with award-winning cuisine", "Rustic taverna with live Greek music and dancing", "Modern bistro combining Greek and international flavors", "Rooftop restaurant with stunning city views", "Traditional psistaria specializing in grilled meats", "Cozy neighborhood restaurant with homestyle cooking" ] def generate_restaurant_data(self, count: int = 500) -> List[Dict]: """Generate realistic restaurant data""" restaurants = [] used_names = set() for i in range(count): # Generate unique name base_name = random.choice(self.restaurant_names) if base_name in used_names: name = f"{base_name} {random.choice(self.neighborhoods)}" else: name = base_name used_names.add(name) # Generate restaurant details cuisine = random.choice(self.cuisine_types) neighborhood = random.choice(self.neighborhoods) # Some restaurants close at midnight if random.random() < 0.1: # 10% chance closing_hour = 0 # Midnight else: closing_hour = random.randint(22, 23) restaurant = { 'name': name, 'description': random.choice(self.descriptions), 'cuisine_type': cuisine, 'address': f"{random.randint(1, 200)} {random.choice(['Adrianou', 'Ermou', 'Mitropoleos', 'Pandrossou', 'Kidathineon'])} St, {neighborhood}, Athens, Greece", 'phone': f"+30 21 {random.randint(1000, 9999)} {random.randint(1000, 9999)}", 'rating': round(random.uniform(3.5, 4.8), 1), 'review_count': random.randint(50, 1500), 'opening_time': dt_time(random.randint(11, 13), random.choice([0, 30])), 'closing_time': dt_time(closing_hour, random.choice([0, 30])), 'price_range': random.choice(['€', '€€', '€€€']), 'photos': self.generate_photo_urls(name, random.randint(3, 8)), 'menu_items': self.generate_menu_items(cuisine, random.randint(8, 25)) } restaurants.append(restaurant) if (i + 1) % 50 == 0: print(f"📊 Generated {i + 1}/{count} restaurants") return restaurants def generate_photo_urls(self, restaurant_name: str, count: int) -> List[str]: """Generate placeholder photo URLs""" photos = [] base_urls = [ "https://picsum.photos/800/600", "https://source.unsplash.com/800x600/?restaurant,food,greek", "https://source.unsplash.com/800x600/?athens,taverna", "https://source.unsplash.com/800x600/?mediterranean,cuisine" ] for i in range(count): photos.append(f"{random.choice(base_urls)}&sig={random.randint(1, 1000)}") return photos def generate_menu_items(self, cuisine_type: str, count: int) -> List[Dict]: """Generate menu items based on cuisine type""" menu_items = [] available_dishes = self.greek_dishes.copy() # Add some cuisine-specific variations if 'seafood' in cuisine_type.lower(): seafood_multiplier = 2 available_dishes = [dish for dish in available_dishes if 'seafood' in dish['category'].lower()] * seafood_multiplier + available_dishes selected_dishes = random.sample(available_dishes, min(count, len(available_dishes))) for dish in selected_dishes: # Add some price variation base_price = dish['price'] price_variation = random.uniform(0.8, 1.3) final_price = round(base_price * price_variation, 2) menu_items.append({ 'name': dish['name'], 'price': final_price, 'category': dish['category'], 'description': f"Traditional {dish['name'].lower()} prepared with fresh ingredients" }) return menu_items def download_sample_photos(self, restaurants: List[Dict]): """Download sample photos for restaurants""" print("📷 Downloading sample photos...") for i, restaurant in enumerate(restaurants[:20]): # Download for first 20 restaurants try: safe_name = restaurant['name'].replace(' ', '_').replace('/', '_')[:30] for j, photo_url in enumerate(restaurant['photos'][:3]): # Max 3 photos per restaurant try: filename = f"{safe_name}_{j+1}.jpg" filepath = os.path.join(self.photo_dir, filename) if not os.path.exists(filepath): # Use a simple food photo URL sample_url = f"https://picsum.photos/800/600?random={random.randint(1, 1000)}" urllib.request.urlretrieve(sample_url, filepath) print(f" Downloaded: {filename}") except Exception as e: print(f" ⚠️ Photo download failed: {e}") except Exception as e: print(f" ❌ Error with restaurant {restaurant['name']}: {e}") time.sleep(0.5) # Be polite to image services def save_to_database(self, restaurants: List[Dict]): """Save restaurants to database""" print("💾 Saving restaurants to database...") with self.engine.connect() as db: # Get company and currency info company_id = "c35388d2-0028-4002-bcc4-db4d7ed2042e" # Try to get Athens beach place beach_result = db.execute(text("SELECT beach_place_id FROM beach_places WHERE city ILIKE '%athens%' LIMIT 1")).fetchone() beach_place_id = beach_result[0] if beach_result else None currency_id = 1 # EUR successful_saves = 0 for restaurant in restaurants: try: # Check if already exists existing = db.execute(text("SELECT 1 FROM restaurants WHERE restaurant_name = :name"), {'name': restaurant['name']}).fetchone() if existing: print(f"⏭️ Skipped (exists): {restaurant['name']}") continue restaurant_id = str(uuid.uuid4()) # Insert restaurant db.execute(text(""" INSERT INTO restaurants ( restaurant_id, restaurant_name, company_id, beach_place_id, description, cuisine_type, opening_time, closing_time, is_active, created_at ) VALUES ( :restaurant_id, :restaurant_name, :company_id, :beach_place_id, :description, :cuisine_type, :opening_time, :closing_time, :is_active, NOW() ) """), { 'restaurant_id': restaurant_id, 'restaurant_name': restaurant['name'], 'company_id': company_id, 'beach_place_id': beach_place_id, 'description': restaurant['description'], 'cuisine_type': restaurant['cuisine_type'], 'opening_time': restaurant['opening_time'], 'closing_time': restaurant['closing_time'], 'is_active': True }) # Create category category_id = int(time.time() * 1000000) % 2000000000 # Unique ID try: db.execute(text(""" INSERT INTO restaurant_categories ( category_id, restaurant_id, category_name, description ) VALUES ( :category_id, :restaurant_id, :category_name, :description ) """), { 'category_id': category_id, 'restaurant_id': restaurant_id, 'category_name': restaurant['cuisine_type'], 'description': f"{restaurant['cuisine_type']} cuisine and specialties" }) except: category_id = 1 # Fallback # Insert menu items for item in restaurant['menu_items']: try: item_id = str(uuid.uuid4()) db.execute(text(""" INSERT INTO restaurant_items ( item_id, restaurant_id, category_id, item_name, description, price, currency_id, is_available, created_at ) VALUES ( :item_id, :restaurant_id, :category_id, :item_name, :description, :price, :currency_id, :is_available, NOW() ) """), { 'item_id': item_id, 'restaurant_id': restaurant_id, 'category_id': category_id, 'item_name': item['name'], 'description': item.get('description', ''), 'price': item['price'], 'currency_id': currency_id, 'is_available': True }) except Exception as e: print(f" ⚠️ Menu item save failed: {e}") db.commit() successful_saves += 1 if successful_saves % 25 == 0: print(f" ✅ Saved {successful_saves} restaurants...") except Exception as e: db.rollback() print(f"❌ Failed to save {restaurant['name']}: {e}") print(f"✅ Successfully saved {successful_saves}/{len(restaurants)} restaurants") def generate_athens_restaurants(self, count: int = 500): """Main generation method""" print(f"🚀 Generating {count} Athens restaurants...") # Generate data restaurants = self.generate_restaurant_data(count) # Download sample photos self.download_sample_photos(restaurants) # Save to database self.save_to_database(restaurants) # Save to JSON for backup with open('athens_restaurants.json', 'w', encoding='utf-8') as f: # Convert time objects to strings for JSON serialization json_restaurants = [] for r in restaurants: json_r = r.copy() if 'opening_time' in json_r and json_r['opening_time']: json_r['opening_time'] = json_r['opening_time'].strftime('%H:%M:%S') if 'closing_time' in json_r and json_r['closing_time']: json_r['closing_time'] = json_r['closing_time'].strftime('%H:%M:%S') json_restaurants.append(json_r) json.dump(json_restaurants, f, indent=2, ensure_ascii=False) print(f"🎉 Generated {len(restaurants)} Athens restaurants!") print(f"📁 Photos saved to: {self.photo_dir}") print(f"📄 Data backup: athens_restaurants.json") return restaurants def main(): """Main function""" generator = AthensRestaurantGenerator() try: restaurants = generator.generate_athens_restaurants(count=500) print(f"\n✅ GENERATION COMPLETE!") print(f" 🏪 Total restaurants: {len(restaurants)}") print(f" 📷 Sample photos downloaded") print(f" 💾 Data saved to database") print(f" 📄 Backup saved to JSON") # Show some statistics cuisines = {} total_items = 0 for r in restaurants: cuisine = r['cuisine_type'] cuisines[cuisine] = cuisines.get(cuisine, 0) + 1 total_items += len(r['menu_items']) print(f"\n📊 STATISTICS:") print(f" 🍽️ Total menu items: {total_items}") print(f" 🏷️ Cuisine types: {len(cuisines)}") for cuisine, count in sorted(cuisines.items(), key=lambda x: x[1], reverse=True)[:5]: print(f" {cuisine}: {count} restaurants") except Exception as e: print(f"❌ Error: {e}") import traceback traceback.print_exc() if __name__ == "__main__": main()