New in Zyte: Web Scraping Copilot, LLM-friendly text, MCP scraping

In this packed edition of Zyte’s Product Update, we want to share:

1. Three big new products and features:

   A Web Scraping CoPilot for your code editor.

   Get clean text content from any web page.

   Command center for enterprise customers.

2. Scrape web data through MCP.

3. Watch Extract Summit Austin recordings.

Want to accelerate your scraping with AI, while still keeping control of your environment?

Launched at Extract Summit by Zyte, Web Scraping Copilot is a free Visual Studio Code extension that helps you generate web scraping code with GitHub Copilot.

It streamlines working with Scrapy projects and includes optional integration with Scrapy Cloud and Zyte API, making it easier to deploy and monitor your web scraping jobs.

Read our announcement, download now and watch the video to see the extension in action:

Zyte API’s new pageContent automatic extraction data type lets you extract any page’s main content in a clean, structured, LLM-friendly format, completely free from HTML, ads, or clutter.

Get only the meaningful text to feed your AI, cutting down token costs and processing time by up to 99% compared to using raw HTML. 

Read the announcement, see the docs here or try it in Playground.

Misconfigured spiders can hurt success rates - but can be hard to spot at scale.

That’s why we added a new command center for monitoring and improving crawl success for enterprise customers with large numbers of domains. The hub detects possible problems and makes helpful suggestions.

The hub is currently available to enterprise users. To learn more about how we can help, just contact sales or support.

Now you can scrape data using natural language input, without restrictions.

Join our very own John Rooney as he shows how to build an MCP server that enables compatible LLMs to read web pages using Zyte API and FastMCP.

[Watch on YouTube - with GitHub repo]

Extract Summit Austin in September was a blast. Watch deep-dives from the summit into Zyte’s latest features, practical demos, and industry insights from data leaders shaping the future of web data. Catch up anytime and see what’s next for the ecosystem.

Watch the Talks from both events
Extract Summit Austin
Extract Summit Dublin

Agentic web scraping: Hype, reality and what happens next

From broken parsers to context limits, today’s AI agents have real challenges, but with the right tools and orchestration, they could reshape how we extract web data.

The new economics of web data: Smaller scraping just got cheaper

Smarter tools and AI-driven automation are rewriting the rules of web scraping. As costs fall and setup barriers vanish, smaller teams can now compete at scale, reshaping how the web’s data economy works.

Memo to CTOs: Don’t build the product 

Zyte’s CTO says great tech leaders don’t work on software; they work on systems that make software.

Plan your web scraping project like a product manager

Most web scraping projects that collapse don't fail because of technical incompetence. They fail because teams treat data extraction like a coding sprint rather than a product launch.