This is a python-based webscraper to collect data on used cars from kijiji, a marketplace very popular in Quebec. I'd regularly visit the front page, collect all the recently posted ads and extract metrics from them such as the brand of the car, the mileage and how old it was.
The idea then was to use this data to try to fit a model to predict the price of a car based on it's stats!
I eventually scraped (lol) this project because I had a lot of issues ensuring the data was of high quality. The database is still available in the repo and contains ~30k entries of cars in the Montreal area collected during summer 2023.