OxyCast: Podcast on Everything Web Scraping Related

  • Tune in to the hottest topics on public data gathering

  • Hear our personal experiences on web scraping

  • Learn about the best web scraping practices

Our mentions

OxyCast is mentioned in several media channels

About OxyCast

One of Oxylabs’ core beliefs is knowledge sharing. Listen to our podcast and learn more about all things web scraping. Find out why web scraping exists, discover solutions to daily challenges, and uncover what’s new in the web scraping community.

Episode 6

Machine Learning: The Driving Force of Web Scraping

In the 6th episode of our podcast, OxyCast host Augustinas Kalvis (Software Engineer) talks to Jurijus Gorskovas (Machine Learning Engineer) about how web scraping is being revolutionized through the use of Machine Learning (ML). Jurijus shares his expertise by touching upon a multitude of ML topics, from getting a career in an ML-focused field to what features Machine Learning provides and which difficulties it solves.

In this episode, we cover the following:

  • Challenges of finding a job in the machine learning field 

  • Why is machine learning an exciting field to work in?

  • What is a Universal E-Commerce Parser, and how does it work?

  • Explanation of the "feature" in machine learning

  • Basics of a machine learning model

  • Delving deeper to understand "features" even more

  • What problems can be solved with machine learning?

An introduction to the web scraping world

  • The purpose of web scraping

  • The process & challenges of public data gathering

  • Buying vs. building a web scraper

The most common challenges of web scraping

  • Ensuring reliability & scalability

  • Handling bot detection

  • Tips and tricks on avoiding blocks

The main principles of data parsing

  • Exploring the process step-by-step

  • Writing a good selector

  • Making the parser scalable

The intricacies of scaling

  • Boosting the number of requests

  • Solutions to bottlenecks

  • Tips on system design

The usage of proxies in web scraping

  • The essentials of proxies in web scraping

  • Considerations for proxy acquisition

  • The differences of proxy types

Machine Learning in web scraping

  • Complexities of ML in web scraping

  • "Features" of ML

  • Problem solving capabilities of ML

Share your input

We are always looking for new thematic angles and people to share them with you. Do you have anything particular in mind? Then go ahead and suggest a topic or refer a guest. Let us know to make it a reality by sending an email!

Contact us: events@oxylabs.io