Jan Curn

How to scrape modern websites to feed AI agents

What if your AI could find and use new tools on its own? See how dynamic tool discovery creates powerful agents that can scrape the modern web.

How to scrape modern websites to feed AI agents
#1about 1 minute

Why web data is essential for training large language models

LLMs are trained on massive web datasets like Common Crawl, but this leads to knowledge cutoffs and hallucinations.

#2about 2 minutes

How RAG provides LLMs with up-to-date context

Retrieval-Augmented Generation (RAG), or context engineering, feeds external, live data to LLMs to produce more accurate and timely answers.

#3about 3 minutes

Navigating the complexities of modern web scraping

Modern websites use dynamic JavaScript rendering and anti-bot measures, requiring headless browsers, proxies, and CAPTCHA solvers to access data.

#4about 2 minutes

Cleaning messy HTML and scaling data extraction

To avoid the 'garbage in, garbage out' problem, you must clean HTML by removing cookie banners and ads, and manage complexities like sitemaps and robots.txt.

#5about 3 minutes

Demo of scraping a website with Apify Actors

A demonstration shows how to use the Apify Website Content Crawler to perform a deep crawl of a website and extract its content into markdown.

#6about 2 minutes

Building a RAG chatbot with scraped data and Pinecone

The scraped website data is uploaded to a Pinecone vector database, enabling a chatbot to answer questions using the site's specific content.

#7about 1 minute

Using the Model Context Protocol for AI agent integration

The Model Context Protocol (MCP) provides a fluid, dynamic interface for AI agents to communicate with and discover tools, unlike static traditional APIs.

#8about 3 minutes

Demo of dynamic tool discovery using MCP

An AI agent uses MCP to dynamically search the Apify store for a Twitter scraper, add it to its context, and then use it to fetch live data.

Related jobs
Jobs that call for the skills explored in this talk.

Matching moments

The challenge of AI agents on the human-centric web
01:35 MIN

The challenge of AI agents on the human-centric web

WebMCP - Making Agents a First-Class Citizen of the Web - Andre Cipriani Bandarra & François Beaufort

Powering real-time AI with retrieval augmented generation
02:42 MIN

Powering real-time AI with retrieval augmented generation

Scrape, Train, Predict: The Lifecycle of Data for AI Applications

The evolution of web scraping for modern applications
09:56 MIN

The evolution of web scraping for modern applications

WeAreDevelopers LIVE – Web Scraping, Agents, Actors and more

The symbiotic relationship between AI and web scraping
00:41 MIN

The symbiotic relationship between AI and web scraping

Scrape, Train, Predict: The Lifecycle of Data for AI Applications

Navigating a fragmenting web and AI content scraping
05:33 MIN

Navigating a fragmenting web and AI content scraping

Fireside Chat: Can Regulation Improve Accessibility? - Léonie Watson

Presenting live web scraping demos at a developer conference
01:57 MIN

Presenting live web scraping demos at a developer conference

Tech with Tim at WeAreDevelopers World Congress 2024

Demonstration of an AI copilot for automated scraping
02:42 MIN

Demonstration of an AI copilot for automated scraping

Scrape, Train, Predict: The Lifecycle of Data for AI Applications

Training AI models with custom scraped data
04:04 MIN

Training AI models with custom scraped data

Scrape, Train, Predict: The Lifecycle of Data for AI Applications

Featured Partners

Related Videos

See all videos
Scrape, Train, Predict: The Lifecycle of Data for AI Applications26:15

Scrape, Train, Predict: The Lifecycle of Data for AI Applications

Vidas Bacevičius

WeAreDevelopers LIVE – Web Scraping, Agents, Actors and more1:06:14

WeAreDevelopers LIVE – Web Scraping, Agents, Actors and more

Chris Heilmann, Daniel Cranney, Ondra Urban & COO & GTM at Apify

MCP Mashups: How AI Agents are Reviving the Programmable Web23:17

MCP Mashups: How AI Agents are Reviving the Programmable Web

Angie Jones

Beyond Prompting: Building Scalable AI with Multi-Agent Systems and MCP25:32

Beyond Prompting: Building Scalable AI with Multi-Agent Systems and MCP

Viktoria Semaan

Carl Lapierre - Exploring Advanced Patterns in Retrieval-Augmented Generation21:17

Carl Lapierre - Exploring Advanced Patterns in Retrieval-Augmented Generation

Carl Lapierre

Build RAG from Scratch28:04

Build RAG from Scratch

Phil Nash

From A2A to MCP: How AI’s “Brains” are Connecting to “Arms and Legs”24:12

From A2A to MCP: How AI’s “Brains” are Connecting to “Arms and Legs”

Brad Axen

Building Real-Time AI/ML Agents with Distributed Data using Apache Cassandra and Astra DB28:20

Building Real-Time AI/ML Agents with Distributed Data using Apache Cassandra and Astra DB

Dieter Flick

Related Articles

View all articles
CH
Chris Heilmann
WebMCP: Empowering Agents as First-Class Citizens of the Web
WebMCP is an exciting W3C proposal that just landed in Chrome Canary to try out . The idea is that you can use some HTML attributes on a form or register JavaScript tool methods to give agents direct access to content. This gives us as content prov...
WebMCP: Empowering Agents as First-Class Citizens of the Web

From learning to earning

Jobs that call for the skills explored in this talk.