AgentQL
AI-powered semantic query language for web scraping and automation
AgentQL uses natural language queries to locate web elements and extract structured data without brittle CSS selectors or XPath.
Quickstart Execution
query.ts
Get started with AgentQL in your project.
import { wrap } from 'agentql'
import { chromium } from 'playwright'
const browser = await chromium.launch()
const page = await wrap(await browser.newPage())
await page.goto('https://www.cvr.dk')
const QUERY = `{
search_input
search_button
}`
const response = await page.queryElements(QUERY)
await response.search_input.type('Novo Nordisk')
await response.search_button.click()About AgentQL
AgentQL eliminates the main failure point of web scrapers: fragile CSS and XPath selectors that break when sites change. By querying elements with semantic descriptions (e.g. `{ company_name, cvr_number, vat_status }`), AgentQL automatically resolves the correct DOM nodes even across UI redesigns.
DK
Danish Product & Data Recipes
How developers and agents use AgentQL to connect with Danish digital infrastructure.
Scrape Danish E-Commerce Prices Resilient to Redesigns
Use AgentQL semantic queries on Danish retail portals to extract price, stock, and SKU details without maintaining custom selectors.
Key Capabilities
Natural language element targeting (no CSS/XPath needed)
Self-healing against website UI and DOM updates
Drop-in Playwright extension with Python and TypeScript SDKs
AgentQL MCP server for interactive agent browser control