Re:Ask HN: What's your quarantine side project?
by geckoquaint on Thursday May 14, 2020 @06:56AM
(#23177974)
I started learning some machine learning and nlp.
Built a Product AutoExtract API, to extract clean product data from any e-commerce product page automatically, without any selectors or rules.
Most of the project uses off the shelf open source software: chrome headless and puppeteer for rendering, some computer vision algorithms tech and Cloud Run to slash costs for hosting.
Still training the algos, but you can try it our for a spin here: https://crawlify.io.
Built a Product AutoExtract API, to extract clean product data from any e-commerce product page automatically, without any selectors or rules.
Most of the project uses off the shelf open source software: chrome headless and puppeteer for rendering, some computer vision algorithms tech and Cloud Run to slash costs for hosting.
Still training the algos, but you can try it our for a spin here: https://crawlify.io.