Amazon Nova Act Showcase Demos

This repository contains multiple comprehensive demos showcasing Amazon Nova Act's web automation capabilities across different popular websites and use cases.

🚀 Featured Demos

1. 🗺️ Trip Planning with Google Maps (trip_planner_demo.py)

• Search locations and get detailed directions
• Multi-destination trip planning with route optimization
• Find points of interest along routes (restaurants, gas stations, attractions)
• Local attraction discovery with ratings and reviews
• Route sharing and saving capabilities

2. 🏨 Airbnb Hostel Search (airbnb_search_demo.py)

• Advanced filtering with price ranges, amenities, and property types
• Interactive date selection and guest count configuration
• Dropdown navigation for room types and booking options
• Map-based location analysis and proximity assessment
• Multi-city comparison for budget travelers
• Booking process walkthrough (demo mode only)

3. 🛒 Amazon Product Scraping (amazon_scraper_demo.py)

• Multi-page product scraping with pagination handling
• Detailed product information extraction (prices, ratings, reviews)
• Category-based browsing and filtering
• Deal hunting and discount tracking
• Price comparison across multiple sellers
• Advanced techniques including sentiment analysis and inventory tracking

🛠️ Setup and Installation

Prerequisites

• Python 3.8+
• Virtual environment (recommended)

Quick Setup

# Clone or download the demo files
cd nova-act-showcase

# Run the setup script
python3 setup.py

# Activate virtual environment
source venv/bin/activate  # On macOS/Linux
# OR
venv\Scripts\activate.bat  # On Windows

# Verify installation
python3 -c "import nova_act; print('Nova Act ready!')"

Manual Setup

# Create virtual environment
python3 -m venv venv

# Activate virtual environment
source venv/bin/activate

# Install nova-act
pip install nova-act

🎯 Running the Demos

Run All Demos

python3 run_demos.py

Run Individual Demos

# Trip planning demo
python3 run_demos.py trip

# Airbnb search demo
python3 run_demos.py airbnb

# Amazon scraping demo
python3 run_demos.py amazon

# Advanced techniques demo
python3 run_demos.py advanced

Run Specific Demo Files

# Trip planning
python3 trip_planner_demo.py

# Airbnb search
python3 airbnb_search_demo.py

# Amazon scraping
python3 amazon_scraper_demo.py

📋 Demo Details

Trip Planning Demo Features

• Route Planning: San Francisco to Los Angeles with tourist stops
• Multi-destination: 5-city California road trip optimization
• Local Discovery: Museums in NYC, restaurants in Paris
• POI Integration: Automatic discovery of relevant stops

Airbnb Demo Features

• Smart Filtering: Budget hostels with essential amenities
• Location Analysis: Map-based proximity assessment
• Comparison Tools: Side-by-side hostel evaluation
• Booking Simulation: Complete reservation process walkthrough

Amazon Demo Features

• Product Search: "wireless headphones" across multiple pages
• Category Mining: Electronics section deep-dive
• Deal Detection: Lightning deals and time-sensitive offers
• Price Tracking: Cross-seller comparison and best value analysis

🔧 Customization

Modify Search Parameters

Edit the demo files to customize:

• Locations: Change cities, countries, or addresses
• Date Ranges: Adjust travel dates and booking windows
• Products: Search for different items or categories
• Filters: Modify price ranges, amenities, or preferences

Example Customizations

# Trip planning - change destinations
demo.multi_destination_trip([
    "Seattle, WA",
    "Portland, OR",
    "San Francisco, CA"
])

# Airbnb - modify search criteria
demo.search_hostels_workflow(
    location="Tokyo, Japan",
    checkin_date="2024-06-01",
    checkout_date="2024-06-07",
    guests=2
)

# Amazon - search different products
scraper.search_and_scrape_products(
    search_term="mechanical keyboards",
    max_pages=3
)

🎨 Nova Act Usage Patterns

Basic Pattern

from nova_act import NovaAct

with NovaAct(starting_page="https://example.com") as nova:
    result = nova.act("Describe the action to perform")

Complex Multi-Step Actions

with NovaAct(starting_page="https://maps.google.com") as nova:
    result = nova.act(f"""
        1. Search for '{origin}' in the search box
        2. Click the 'Directions' button
        3. Enter '{destination}' as the destination
        4. Analyze route options and select the best one
        5. Return route details including time and distance
    """)

Data Extraction

with NovaAct(starting_page="https://www.airbnb.com") as nova:
    result = nova.act("""
        For each hostel result, extract:
        - Name and rating
        - Price per night
        - Available amenities
        - Distance from city center
        Return structured data for the top 5 results
    """)

📊 Expected Results

Trip Planning Output

• Route details with time and distance estimates
• Optimized multi-destination itineraries
• Points of interest with ratings and descriptions
• Shareable route links

Airbnb Search Output

• Filtered hostel listings with key details
• Price comparisons across properties
• Location analysis and proximity data
• Booking process insights

Amazon Scraping Output

• Product listings with prices, ratings, and features
• Deal information with discount percentages
• Cross-seller price comparisons
• Category trends and bestseller data

🚨 Important Notes

Rate Limiting

• Built-in delays prevent overwhelming target websites
• Respect robots.txt and terms of service
• Monitor for rate limiting responses

Demo Mode

• Airbnb booking demo stops before actual payment
• No real reservations or purchases are made
• All scraping is for demonstration purposes only

Legal Compliance

• Use demos responsibly and ethically
• Respect website terms of service
• Consider contacting websites for permission for large-scale scraping

🤝 Contributing

Feel free to:

• Add new demo scenarios
• Improve existing automation flows
• Optimize scraping techniques
• Add error handling and robustness

📄 License

This project is for educational and demonstration purposes. Please respect the terms of service of all websites used in the demos.