In this hands-on workshop hosted by Iván Sánchez, you'll learn how to harness the incredible power of Large Language Models (LLMs) to tackle your toughest scraping challenges. Whether you're using open-source or commercial LLMs, we'll show you practical techniques that actually work.

In this workshop, you will learn about:

• Applying LLMs on every page: Unlock the power of LLMs to analyze web pages individually, achieving high accuracy while managing costs. Learn how this approach can be optimized for scalable, precise data extraction, and see where it fits best within your scraping strategy.

• Code and selector generation: See how LLMs can automatically generate code and selectors for complex websites. Master the art of scaling these techniques for real-world scenarios where page structures are dynamic and varied.

• Choosing the right LLM for the job: Gain insights into selecting between open-source and commercial LLMs for your projects. This workshop will guide you on when to leverage each model’s strengths, highlighting how these approaches can outperform traditional scraping methods in speed and accuracy.

Whether you’re a beginner in LLM-based scraping or looking to refine your advanced techniques, this workshop will equip you with the tools and knowledge to elevate your web scraping capabilities.

For any follow-up questions after watching the session, join our Discord community and engage directly with the team. We are a thriving community of 10,000+web scraping enthusiasts, committed to sharing insights, learning and exploring new technologies, and advancing in web scraping.