The scripts in this repository are part of a greater project for 2 real world clients. The functions shown here form the data collection portion of the project.
Online Retail Competitor Intelligence for 2 Real Clients
- Scraped (Selenium) 4000+ Lazada product pages of clients, their competitors, and similar recommended products
- Derived insight on comparative prices, discounts, & ratings across similar items. Assessed text similarity between the clients’ products and similar items using SpaCy, to find and report suspected “copy-cat” posts