AI Web Scraper: extract any data from any website with Claude — $0.01 per page

Tell it what you need in plain words — "every product: name, price, rating and link" — and get clean JSON / CSV / Excel rows. No selectors, no code, no breaking when the site changes its layout.

• 🧠 Claude AI included — no API key, no extra account.
• ⚡ Works on JavaScript sites: fast download first, a real browser only when the page needs it (or when a site blocks simple bots).
• 📋 Lists or detail pages: one row per item (products, jobs, listings, reviews…) or one row per page (a product page, a profile, an article).
• 🔗 Follows pagination and detail links with simple patterns like */page/* or */product/*.
• 💸 $0.01 per page, and you only pay for pages that worked. Pages that fail or have nothing matching are free.

What can you extract?

Anything that is visible on the page:

• E-commerce: product names, prices, stock, ratings, variants, images, links.
• Leads: company name, email, phone, address, social links from contact or about pages.
• Jobs: title, company, location, salary, date, link.
• Real estate, cars, events, directories: every listing with its details.
• Articles and docs: title, author, date, summary, key facts.

How to use it

1. Paste one or more Start URLs.
2. In What to extract, describe the data in plain words. Optionally list exact Fields (one per line, price: price with currency).
3. Choose Rows: one per item for lists, one per page for detail pages.
4. Optional: Follow links matching to open pagination or detail pages, and Max pages to cap the run.
5. Run. Download the results as JSON, CSV, Excel or connect them to Google Sheets, Zapier, Make or an API.

Example input

{
  "startUrls": [{ "url": "https://books.toscrape.com/" }],
  "instruction": "Every book: title, price, star rating and whether it is in stock",
  "mode": "items",
  "followLinks": ["https://books.toscrape.com/catalogue/page-*.html"],
  "maxPages": 5
}

Example output

{
  "pageUrl": "https://books.toscrape.com/",
  "pageTitle": "All products | Books to Scrape - Sandbox",
  "title": "Sapiens: A Brief History of Humankind",
  "price": "£54.23",
  "rating": "Five",
  "stock": "In stock"
}

Pricing

$0.01 per page extracted (AI included). Failed pages and pages with nothing matching are not charged. A list page with 50 products still costs $0.01. Store discounts apply on paid Apify plans. On Apify's free plan a run reads up to 20 pages.

Tips

• Be specific: "price as a number without currency" or "date in YYYY-MM-DD" — the AI follows your format.
• For big catalogs, start from the category page with one row per item and follow the pagination pattern.
• Use Fields when you need the same columns every run (for spreadsheets and integrations).
• The AI only uses what is on the page: missing values come back as null, never invented.

FAQ

Which AI does it use? Claude (Anthropic), included in the price.

Does it work on sites that need JavaScript? Yes. In Auto mode it opens a real browser when the page needs it. You can also force it.

Can it log in or solve captchas? No. It reads public pages only. Please respect each website's terms and robots rules and the privacy laws that apply to the data you collect.

What about very long pages? They are cut to Max text per page characters (60,000 by default) and the row says so.

Related: clean and join your results with Merge & Deduplicate Datasets, or run AI on every row with Bulk ChatGPT & Claude.