MirrorMetrics is an AI-powered analytics platform for TikTok content analysis. It combines TikTok data scraping with advanced AI analysis using Google's Gemini to provide comprehensive insights and recommendations.
- 📊 Data Scraping: Fetch TikTok video data and metadata
- 🤖 AI Analysis: Leverage Google Gemini for intelligent content analysis
- 📈 Analytics Dashboard: Interactive Streamlit-based UI
- 📋 Report Generation: Export analysis in multiple formats (HTML, Markdown)
mirrormetrics/
├── app.py # Streamlit UI
├── scraper.py # TikTok scraper
├── agent.py # Gemini analysis agent
├── report.py # Report formatter
├── requirements.txt # Python dependencies
└── README.md # This file
- Clone the repository:
git clone <repository-url>
cd mirrormetrics- Install dependencies:
pip install -r requirements.txt- Set up environment variables:
# Create .env file
echo GEMINI_API_KEY=your_api_key_here > .envRun the Streamlit application:
streamlit run app.pyThe application will open in your default browser at http://localhost:8501
GEMINI_API_KEY: Your Google Gemini API key (required)
- TikTok API: Optional. If not provided, the scraper will use alternative data sources
- Google Gemini API: Required for AI analysis features
Main Streamlit application interface. Provides a user-friendly dashboard for:
- Configuring analysis parameters
- Viewing collected data
- Running AI analysis
- Generating and downloading reports
Handles all TikTok data collection:
- Fetch individual video data
- Get trending videos
- Extract metadata and statistics
AI-powered analysis engine using Google Gemini:
- Analyze content sentiment and topics
- Predict engagement metrics
- Generate actionable recommendations
- Create comprehensive insights from multiple videos
Report generation and formatting:
- Generate HTML reports
- Generate Markdown reports
- Export analysis results
- Customize report formatting
- Python 3.8+
- Streamlit
- Google Generative AI
- Requests
- Pandas
- Plotly
See requirements.txt for specific versions.
Contributions are welcome! Please feel free to submit pull requests or open issues for bugs and feature requests.
This project is licensed under the MIT License - see the LICENSE file for details.
For issues, questions, or suggestions, please open an issue on the repository.
Made with ❤️ for content creators and analysts