Andrius Kūkšta

Can web scraping still be done without ML? Perhaps, but for large-scale operations, we need to turn to something more potent. Especially if we want data gathering to be quick and efficient. In this presentation, Andrius explores the intersections between web scraping and ML. He will provide an insightful overview of its practical uses for such things as adaptive parsing, scraper block detection, and more. He will also consider the future possibilities of ML for such areas as product matching across e-commerce platforms and website similarity detection for parsing templates.

Join his lesson to learn about:

• How do scrapers use ML to outsmart anti-bot systems and vice versa?

• What’s the role of web scraping for ML training?

• How can large language models be used in advanced parsing?