AI Web Scraper - Extract Any Website to JSON in Plain English

AI Web Scraper: Extract Any Website to JSON in Plain English

Describe the data you want in plain English and get clean, structured JSON from any web page. No CSS selectors, no code, and nothing to fix when a site changes its layout. Paste URLs, write something like "product name, price, stock status and SKU", and the AI page extractor returns one tidy record per page, or one record per item on listing pages.

What can this AI web scraper do?

• Extract any fields you describe: prices, product details, contact details, event dates, job listings, specifications, facts from articles.
• Handle listing pages: turn on Page lists many items to get one row per product, result, event or directory entry.
• Keep columns consistent: name the exact Output fields you want (with hints like price: number only) for spreadsheet-ready data.
• Handle JavaScript sites: pages are downloaded directly first; if a page comes back nearly empty, it is opened in a real browser automatically (Render JavaScript: Auto).
• Never invent data: values not on the page come back as null.
• Choose cost vs. precision: Standard mode for most pages, Accurate mode for messy or complex pages, or bring your own Anthropic API key for the lowest price.

What do you get?

Who uses it?

• E-commerce teams: product names, prices, variants, ratings and availability from store pages.
• Lead generation: company names, addresses, phone numbers and websites from business directories.
• Events and listings: dates, venues, prices and links from calendars and listing pages.
• Research: facts, tables and key figures from articles, reports and Wikipedia.
• AI agents and automations: a reliable "read this page and give me these fields" step.

How to use it

1. Click Try for free (or Start).
2. Paste one or more Page URLs.
3. In What to extract, describe the fields in plain English. Be specific: "price as a number without the currency symbol".
4. Optionally list Output fields and turn on Page lists many items for catalogs and search results.
5. Run it and export the results to Excel, CSV, JSON or Google Sheets.

Input example

{
  "startUrls": [
    {
      "url": "https://books.toscrape.com/catalogue/a-light-in-the-attic_1000/index.html"
    }
  ],
  "instructions": "Book title, price, availability, star rating and UPC",
  "mode": "standard"
}

Output example

{
  "url": "https://books.toscrape.com/catalogue/a-light-in-the-attic_1000/index.html",
  "status": "ok",
  "pageTitle": "A Light in the Attic | Books to Scrape - Sandbox",
  "truncated": false,
  "renderedWithBrowser": false,
  "data": {
    "title": "A Light in the Attic",
    "price": "£51.77",
    "availability": "In stock (22 available)",
    "star_rating": "Three",
    "upc": "a897fe39b1053632"
  }
}

How much does it cost?

You pay per page extracted, with no separate compute charge (only a $0.00005 start fee per run):

Examples: 200 product pages in Standard mode cost $1.00; 50 tricky pages in Accurate mode cost $1.50. Pages that fail to load or are empty are not charged for AI extraction. Apify's free plan includes monthly credits, so you can try it at no cost.

Use it via API, Make, Zapier, n8n or an AI agent

Apify API. Start a run and get the results back in one HTTP request (replace YOUR_API_TOKEN with the token from Apify Console > Settings > Integrations):

curl -X POST "https://api.apify.com/v2/acts/plotpointtech~ai-page-extractor/run-sync-get-dataset-items?token=YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"startUrls": [{"url": "https://books.toscrape.com/catalogue/a-light-in-the-attic_1000/index.html"}], "instructions": "Book title, price, availability, star rating and UPC", "mode": "standard"}'

For longer jobs, start the run asynchronously and read the dataset when it finishes. Official apify-client libraries exist for Python and JavaScript; the API tab on this page has ready-made code.

No-code automation. Connect the tool to Make, Zapier, n8n, Google Sheets, Slack, Airtable or any webhook with Apify integrations, and use Schedules in Apify Console to run it hourly, daily or weekly.

AI agents (MCP). Give Claude, ChatGPT, Cursor, VS Code or any MCP-compatible agent direct access to this tool through the hosted Apify MCP server. Add this server URL to your client:

https://mcp.apify.com?tools=plotpointtech/ai-page-extractor

The agent can then call the tool with the same input fields shown above and read the results.

FAQ

Is it legal to scrape websites with AI? Extracting publicly available information is generally lawful, but you are responsible for respecting each website's terms of use, copyright and privacy laws such as GDPR when pages contain personal data. This tool does not log in, solve CAPTCHAs or get around blocking.

Which websites does it work on? Most public pages: online stores, directories, news and blogs, documentation, event calendars. Sites that block automated visitors, or content behind a login, are not supported.

How accurate is it? Very good on well-structured pages in Standard mode. For dense tables, unusual layouts or pages where precision matters, use Accurate mode. Naming your fields with short hints gives the most consistent output.

Can it follow links or crawl a whole site? It processes the URLs you give it. To collect a list of pages first, export them from the site's sitemap (our SEO Audit Crawler has a cheap "Sitemap URLs only" mode), then pass the URLs here.

Is my API key safe? Your own Anthropic key is stored as an encrypted secret input and is never logged.

Related tools from Plot Point Technologies

• Website to Markdown Crawler for AI, LLM & RAG - $1/1K: any website as clean Markdown for LLMs and RAG.
• Email & Contact Scraper - Website Emails, Phones & Socials: emails, phones and social links from any list of company websites.
• Website Tech Stack Detector - CMS, Analytics & 290+ Techs: CMS, ecommerce, analytics, pixels and hosting of any website.
• SEO Audit Crawler - Titles, Meta, H1, Broken Pages & Links: on-page SEO check of every page in a website's sitemap.

Plot Point Technologies is not affiliated with Anthropic or any website you process.

If this tool saved you time, we would be grateful for a short review on this page; it helps other people find it. If something did not work as expected, please open an issue on the Issues tab and we will look into it quickly.