Pricing

from $1.00 / 1,000 results

Try for free

Go to Apify Store

LLM Scraping Agent - Describe Any Page, Get Structured JSON

Try for free

LLM web scraper that turns any URL into clean, structured JSON. List the fields you want or describe them in plain English, bring your own OpenAI (GPT) or Anthropic (Claude) key, and the model reads the page like a human - no CSS selectors, no per-site code. JSON, CSV or Excel.

Pricing

from $1.00 / 1,000 results

Rating

5.0

(1)

Developer

Flash Scrape

Actor stats

Bookmarked

Total users

Monthly active users

2 hours ago

Last modified

Configure MCP server with LLM Web Scraper - Any Site to JSON with GPT or Claude

The configuration above connects to the hosted Apify MCP server with the LLM Web Scraper - Any Site to JSON with GPT or Claude Actor already loaded. It uses OAuth, so your client opens a browser window to sign you in to Apify on first use. No API token is needed. Clients without OAuth support can authenticate with an Authorization: Bearer header carrying an API token from API & Integrations in Apify Console.

Get a ready-to-use configuration for your MCP client with the LLM Web Scraper - Any Site to JSON with GPT or Claude Actor preconfigured at https://mcp.apify.com/?tools=fetch-actor-details,flash_scraper/ai-universal-scraper.

You can connect to the Apify MCP Server using clients like Tester MCP Client, or any other MCP client of your choice.

If you want to learn more about our Apify MCP implementation, check out our MCP documentation. To learn more about the Model Context Protocol in general, refer to the official MCP documentation or read our blog post.

AI Web Data Extractor — URL + Prompt → JSON

hichemdev/ai-web-extractor

Extract structured data from any web page with a plain-English prompt, using your own OpenAI or Anthropic API key. Turn messy pages into clean JSON.

Hichem Ben Moussa

Claude AI Web Automation

dtrungtin/claude-ai-web-automation

A real browser with Anthropic's Claude models to navigate any website and extract structured data — no CSS selectors or page-specific scraping code required.

Tin

AI Web Scraper: Extract Structured Data With Plain English

lanky_quantifier/ai-web-scraper

Extract structured data from any website using plain English. Describe what you need, AI scraper does the rest. No CSS selectors needed. Export JSON/CSV. Bundle: 30 scrapers at vhubster3.gumroad.com/l/fjmtqn

Vhub Systems

LLM Web Scraper

incredible_moment/llm-scraper

Turn any website into structured JSON using AI. Supports OpenAI GPT-4 and Anthropic Claude. Built in Rust to minimize compute costs while waiting for LLM responses. Extract data without selectors.

Daniel Rosen

Best AI Web Scraper

hgservices/Best-AI-Web-Scraper

Extract any data from any website by simply describing what you want in plain English. AI-powered web scraping with no code, no selectors, and no per-site setup.

Harish Garg

OpenAI Web Automation

dtrungtin/openai-web-automation

Controls a real browser with an OpenAI model to interact with web pages and extract structured data — no CSS selectors or page-specific scraping code required.

Tin

No-Code Web Scraper: Extract Any Website by Example

flash_scraper/smart-scraper-by-example

A no-code web scraper that extracts any website by example - no CSS selectors, no API key. Paste a URL plus values you can see on the page; it learns the HTML pattern and pulls every matching item into structured rows with a confidence score. Follows pagination. CSV, JSON, Excel.

Flash Scrape

AI Web Scraper

crawlworks/ai-web-scraper

Scrape any webpage with a URL and a plain-English prompt. Get structured JSON output powered by AI — no coding, no selectors, no configuration.

Crawlworks

Web Structured Data Extractor (Claude, JSON Schema)

gochujang/web-structured-extractor

Pass a URL + JSON schema (or natural-language goal). Claude reads the page and returns a strict JSON object matching your schema. Product / news / hotel / real-estate / job-board extraction. BYO Anthropic API key. $0.01 per page.

Hojun Lee

Page to API / Sitemap to JSON for RAG & LLM Ingestion

timely_quarterstaff/page-to-api-extractor

Turn any page URL or sitemap into embedding-ready JSON for RAG and LLM pipelines - drop-in for LlamaIndex & LangChain. Clean main_text per page, no HTML noise. Also a plain page to api / sitemap to json extractor. Deterministic code, no AI required.