HNHacker News
TopNewBestAskShowJobs

nghota

3 karma · joined March 12, 2023

submissionscomments
nghota··on Trafilatura: Python tool to gather text on the Web
check out nghota.com api. It is able to pull out the main text from most non-ecommerce web pages and return that to you in json.
nghota··on Experimental library for scraping websites using OpenAI's GPT API
Only articles are supported atm. I am working on algorithms for other page types.