WEB DATA EXTRACT SUMMIT 2025 Austin Texas

Learn how agent-style tools, such as Copilot, Cursor, Codex, and LLM prompt tactics can super-charge and sometimes break your scraping workflow. We’ll demo patterns, anti-patterns, security gotchas, and quick fixes for reliable selector generation and code execution.

Create a scalable and robust web scraping system with Scrapy and Zyte API. We'll create and manage a queue for URL input and data output, plus handle our spiders logs, all ready to scrape data quickly and efficiently.

In this workshop, we'll go through the code of a complete Scrapy spider that's using everything that Zyte API and Scrapy offer to crawl a complex website, and show off a few features you wouldn't usually see live! We'll also discuss codebase design strategies and structures, and showcase our most recent updates to Scrapy

Discover the latest Scrapy features, including split/reusable crawling and parameter validation. Learn hands-on techniques using modern tooling like scrapy-poet and scrapy-spider-metadata to write cleaner, more maintainable web scraping code for your growing projects

Join our no-slide, open-mic roundtable where scraper pros turned ML and AI builders share how LLMs are reshaping workflows—auto-coding ETL, generating selectors, and powering RAG chatbots. Get real talk on the skills you need next (dbt, Airflow, vector DBs, LangChain) and what actually drives career pivots, salary jumps, and meaningful learning.