An automated agent that helps manage and analyze IMDb watchlists using AI-powered title matching and browser automation.
- Automated title matching using Google's Gemini AI
- Browser automation for IMDb interactions using Selenium
- CSV report generation
- Environment-based configuration
- Command-line interface for easy interaction
- Python 3.8 or higher
- Google Cloud Project with Gemini API enabled
- Chrome or Chromium browser installed
- IMDb account (for watchlist management)
- Clone the repository
- Install dependencies:
pip install -r requirements.txt
- Create a
.envfile in the project root with your Gemini API key:GEMINI_API_KEY=your_api_key_here
- Prepare your list of titles in a
titles.csvfile (one title per line) - Run the main script:
python watch.py
- Follow the on-screen instructions to log in to your IMDb account when prompted
The script will:
- Process titles from
titles.csv - Use Gemini AI to find the best matching IMDb titles
- Generate a report in
report.csvwith the results - (Future) Store any screenshots or images in the
imagesdirectory
watch.py- Main entry point and orchestrationgemini_api.py- Integration with Google's Gemini AI for title matchingbrowser_controller.py- Selenium-based browser automationtitle_matcher.py- Title matching utilitiesreport_generator.py- CSV report generationtitles.csv- Input file containing titles to processreport.csv- Output file with processing resultsimages/- Directory for storing screenshots (future use)
You can customize the following environment variables in your .env file:
GEMINI_API_KEY: Your Google Gemini API key (required)ANONYMIZED_TELEMETRY: Set to "false" to disable telemetry (default: false)
- Fork the repository
- Create a feature branch
- Commit your changes
- Push to the branch
- Create a Pull Request
[Specify your license here]
- Google Gemini API
- IMDb
- Selenium WebDriver