This notebook will scrape the a given 4chan board and pull out all text.
The intent behind this scraping is to perform analysis on /biz/, the business board on the website. Lots of cyptocoins and tokens are discussed/promoted/shilled on the board every day, and I thought it would be interesting to analyze what trends emerge.
The image data is collected and stored in /imgs/, I'd like for the images to be the input for both a trained classification neural network and a trained generative neural network - currently being worked on.