Python scraping tool for trustpilot.com reviews.
- Python 3.6
- lxml 3.7.2
- requests 2.12.4
- Set up up and configure scrape.ipynb to scrape the page you want the reviews from into CSV file
- Use the clean.ipynb module to convert and clean this CSV file to a format used by most text classification algorithms
After you've run scrape and clean, you can use this example from sci-kit learn to do text classification.