Pricing

Pay per usage

Structured Web Scraper

Extract articles, products, headings, images and links from any website in clean structured JSON format. Supports multiple URLs per run.

Pricing

Pay per usage

Rating

0.0

(0)

Developer

Huy Tran

Actor stats

Bookmarked

Total users

Monthly active users

16 hours ago

Last modified

What it extracts

Field	Description
`title`	Page title
`description`	Meta description (up to 300 chars)
`articles`	Article/post titles, links, scores
`products`	Product names, prices, links
`headings`	All H1–H6 headings
`images`	Image URLs with alt text
`links`	All outbound links
`text`	Clean body text (up to 3000 chars)

Input

{
  "urls": ["https://news.ycombinator.com/"],
  "contentType": "all",
  "extractImages": true,
  "extractLinks": false,
  "maxItems": 30
}

Field	Options	Default
`urls`	Array of URLs	—
`contentType`	`all`, `article`, `product`	`all`
`extractImages`	`true`, `false`	`true`
`extractLinks`	`true`, `false`	`false`
`maxItems`	Integer	`30`

Supported sites

Hacker News — extracts story titles, links, and vote scores
Generic sites — auto-detects articles/products by HTML structure
Fallback — parses numbered lists from raw text when HTML structure isn't detected

Output

Results are saved to Apify Dataset as structured JSON. Each page produces one record.

Use cases

Build datasets for LLM training
Monitor news, job boards, product listings
Aggregate content from multiple sources
Power AI agents with fresh web data

universal-structured-web-extractor-base

pierremrd29/universal-structured-web-extractor-base

Autonomous web change detection Actor for AI agents. Monitors URLs, detects meaningful content changes, computes diffs, and outputs structured signals for automation, alerts, and decision-making workflows.

Pierre Morandeau

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

LLM Token Counter & Cost Estimator (Claude/GPT/Gemini/Llama)

gochujang/llm-token-counter

Count tokens for any text across 16+ models (Claude Opus/Sonnet/Haiku, GPT-4o, o3, Gemini 1.5, Llama, Mistral) and estimate per-million-token cost. Claude via Anthropic API (BYO key), GPT via tiktoken, others via heuristic. $0.001 per text counted.

Hojun Lee

MCP Config Generator (Apify Actor → Claude / Cursor)

gochujang/mcp-config-generator

Given any Apify actor ID, generates ready-to-paste Model Context Protocol (MCP) server configs for Claude Desktop, Claude Code, and Cursor. Wraps the actor as a tool Claude can call directly. $0.005 per config.

Hojun Lee

Tweet / X Thread → Article (Claude, Markdown)

gochujang/tweet-thread-to-article

Convert a Twitter / X thread (URL or pasted text) into a clean Markdown article. Removes '1/N' noise, smooths transitions, adds optional H2 headings, preserves facts and quotes. BYO Anthropic API key. $0.01 per thread.

Hojun Lee

Article Summarizer (Claude — TL;DR + Bullets + Topics)

gochujang/article-summarizer

Pass any URL or text — get back a tight summary in your chosen style (TL;DR / bullets / executive / tweet) plus topic tags + sentiment. Article body auto-extracted via trafilatura. BYO Anthropic API key. $0.005 per summary, Claude tokens billed by Anthropic.

Hojun Lee

AI Web Scraper — Structured Data Extraction from Any Website

oneary/ai-powered-data-extractor

Extract structured data from any webpage using AI. Define your schema and the AI identifies relevant content — no selectors or coding needed. Handles products, reviews, contacts, and custom fields.

Luan M.

AI-Ready Content Extractor — Structured Web Data for LLM & MCP

yuchiaoniu/ai-content-extractor

Extract structured JSON from any URL for LLM, RAG, and MCP integration. Outputs title, sections, contact info, links, structured data, and clean plain text.

Niu Yuchiao

AI Web Scraper — Structured Data From Any URL

muhammadafzal/ai-web-extractor

Extract structured data from any website using an LLM and your own field schema — no CSS selectors. Give it URLs and the fields you want; get clean JSON rows back. Works on blogs, job boards, product pages, listings, and more.

Muhammad Afzal

Faire Wholesale Product Scraper

parseforge/faire-scraper

Browse Faire by keyword and pull every matching wholesale product with its name, brand, retail price, minimum order quantity, and brand rating. Each item includes the image, review count, and origin country. Handy for retail sourcing, assortment research, and price benchmarking.