Subscriptify is an AI-powered chatbot that determines whether a website is free, freemium, or requires a paid subscription. It uses spaCy for NLP-based keyword detection and BeautifulSoup for web scraping. The project now features a Streamlit-based GUI for easy user interaction.
โ Fetches and extracts visible text from a website. โ Uses spaCy NLP to detect subscription-related terms. โ Identifies websites as free or paid. โ Streamlit Web UI for an interactive experience. โ Error handling for better reliability.
- Python ๐
- spaCy (Natural Language Processing)
- BeautifulSoup (Web Scraping)
- Requests (HTTP requests handling)
- Streamlit (Graphical User Interface)
- Clone the repository:
git clone https://github.com/yourusername/subscriptify.git cd subscriptify
- Create a virtual environment (Optional but recommended):
python3 -m venv venv source venv/bin/activate # On Windows use: venv\Scripts\activate
- Install dependencies:
pip install -r requirements.txt
- Download spaCy's English model:
python -m spacy download en_core_web_sm
To run the GUI version:
streamlit run subscriptify_gui.py
A web interface will open where you can paste the website URL and check its subscription status.
- Improve UI design with better interactivity in Streamlit.
- Implement Selenium for dynamic page scraping.
- Create a dashboard to track website data over time.
- Integrate AI-powered text summarization to provide concise subscription details.
- Develop a browser extension for real-time subscription status checking.
- Add multi-language support to analyze international websites.
- Implement a machine learning model to improve subscription classification accuracy.
Feel free to fork the repository and submit pull requests. ๐