Ultimate Web ScraperAI-Started Extractions
Ask Claude or any MCP agent to extract product data, emails, social links, phone numbers, or Google Maps places — with credit estimates before anything runs.
With a full-access connection, you can ask your AI assistant to start a new extraction for you. These are zero-configuration extractions — no element picking, no selectors — the same technology behind the extension's automatic extraction modes, running in cloud browsers.
What agents can extract
| Type | What you get |
|---|---|
| Product pages | Structured product data (name, price, availability, brand, ratings, images…) from any site that publishes structured data — the catalogue use case |
| Emails | Email addresses found across the given pages |
| Social links | Social media profile links (7 platforms) |
| Phone numbers | Phone numbers found on the given pages |
| Google Maps | Place name, rating, address, phone, website, hours from Maps listings |
Where the URLs come from
- Straight from the chat — paste up to 500 URLs into the conversation.
- From an existing table — point the agent at a link column of a table you've already scraped. This is the path for big jobs: thousands of URLs, no pasting. It's also how chaining works: scrape a list once, then have the agent visit every link in it.
Credit safety: estimate first, run on confirmation
An agent-started extraction never begins silently. The first request returns a credit estimate — "1,240 URLs ≈ 1,240 credits, you have 8,400" — so the agent can check with you before committing. Extractions cost about 1 credit per page, the same as any cloud run, and runs are refused when your balance is empty. Credits can never go negative.
Scheduling
Agent-created extractions can carry a recurring schedule, like any other cloud task — so "check these 200 product pages every morning" is a single instruction.
Guardrails
The same rules as the rest of the product apply: LinkedIn is refused, and page extractions stay on a single domain. Runs are asynchronous — the agent gets a run ID immediately and checks progress rather than blocking your conversation.
Example conversation
You: Take the "Company URL" column from my YC directory table and find contact emails for each company.
Agent: That's 486 URLs — an email extraction will use about 486 credits (you have 9,200). Run it?
You: Yes.
Agent: Started. I'll check progress… Done — 1,832 emails across 431 companies, saved as a new table. Want it in Google Sheets?