Pricing

from $7.00 / 1,000 page extracteds

Try for free

Go to Apify Store

AI Web Scraper – JSON Schema Data Extractor

Try for free

AI web scraper: give URLs and your own JSON Schema or a ready-made preset (product, job, event, article); get one schema-valid JSON object per page. Claude reads page text and JSON-LD, every answer is validated and retried with the errors, and invalid output is free. Uses your own Anthropic API key.

Pricing

from $7.00 / 1,000 page extracteds

Rating

0.0

(0)

Developer

Brisa Works

Actor stats

Bookmarked

Total users

Monthly active users

3 days ago

Last modified

Categories

Developer tools

Start URLs

startUrls

Required

Pages to extract from. Each page is fetched once (no crawling). The example is a page of Books to Scrape, a demo shop built for scraping practice.

Type:array

Preset schema

preset

Optional

A ready-made schema for a common page type, used when the JSON Schema field below is empty. Product: name, brand, SKU, price, currency, stock, rating, reviews. Job: title, company, location, remote, salary range, date posted, skills. Event: name, dates, venue, city, country, online, price. Article: headline, authors, dates, publisher, summary, key points. Your own JSON Schema always wins over a preset.

Type:string

Options:

productjobeventarticle

JSON Schema

jsonSchema

Optional

Your own JSON Schema (draft 2020-12 / draft-07) for the record you want per page. Leave empty to use the preset above; when both are set, this schema wins. Every result is validated against it; add a "description" to each field to guide the model.

Type:object

Anthropic API key

anthropicApiKey

Optional

Your Anthropic API key (console.anthropic.com). Claude usage is billed to your Anthropic account. Without a key the run returns free page previews only.

Type:string

Claude model

model

Optional

Model ID. claude-haiku-5-5 is fast and cheap; use claude-sonnet-5-5 for hard pages.

Type:string

Default:claude-haiku-5-5

Extra instructions

instructions

Optional

Optional guidance, e.g. "prices in EUR as numbers" or "only the main product, not related items".

Type:string

Max page characters sent

maxPageChars

Optional

Longer pages are cut to this many characters of text (the output's truncated flag tells you).

Type:integer

Minimum:1000

Maximum:400000

Default:60000

Retries when output fails validation

maxRetriesOnInvalid

Optional

How many times the model is shown the validation errors and asked to fix its JSON.

Type:integer

Minimum:0

Maximum:3

Default:1

Respect robots.txt

respectRobotsTxt

Optional

Skip pages the site's robots.txt disallows.

Type:boolean

Default:true

Include page text

includePageText

Optional

Also return the page text that was sent to the model.

Type:boolean

Default:false

OpenAI Web Scraper

dtrungtin/openai-web-scraper

Crawl web pages and extract structured information using OpenAI

Tin

Universal Web Scraper & Data Extractor

motivational_nickel/universal-scraper

Fast AI-ready webpage extraction with structured JSON output for automation workflows, AI agents, RAG pipelines, SEO analysis, and website intelligence.

Leoncio Coronado Jr

JSON Schema Auto-Generator (Infer from Samples)

gochujang/json-schema-generator

Provide one or more JSON samples (inline or from URLs) and get an inferred JSON Schema (Draft 7 / 2020-12) describing their shape. Bootstrap API validators, Apify input schemas, BigQuery / DuckDB schemas. Powered by genson. $0.01 per inference.

Hojun Lee

Schema Markup Extractor - JSON-LD SEO Data

benthepythondev/schema-markup-extractor

Extract Schema.org JSON-LD structured data from web pages, including schema types, nodes, block counts and parse errors.

Ben

Schema.Org Json Ld Extractor

sync-network/schema-org-json-ld-extractor

Extract Schema.org JSON-LD structured data from any website. Fast, lightweight HTTP-based scraper that pulls all JSON-LD scripts - perfect for SEO analysis, product data extraction, and AI/RAG pipelines. No browser overhead.

Alam

LD+JSON Schema scraper

pocesar/json-ld-schema

Extract all LD+JSON tags from the given URLs.

Paulo Cesar

460

5.0

(1)

China Public Web Intelligence Extractor

huakelilinjie/china-public-web-intelligence-extractor

Extract structured JSON from public Chinese web pages and text-based PDFs. Capture clean text, titles, dates, issuers, metadata, and source URLs for research, monitoring, and AI workflows.

林杰李

JSON Schema Validator — Bulk

hipersoft/json-schema-validator

Validate JSON documents or every row of a dataset against a JSON Schema and get every failing path with a clear message. Enforce data contracts and QA scraped data.

hiper soft

AI Web Scraper: JSON Schema Extractor

tiger19935/schema-ai-extractor

AI web scraper with strict JSON Schema extraction: give URLs and a schema, get validated JSON per page. HTTP-first, so far cheaper than browser scrapers. Bring your own LLM key at $0.003 per page, failed pages are never charged.

Andrew Boiko

eBay Market Analyser: Prices, Competition & Profit

best_actors/ebay-market-analyser

Keywords in, the live eBay market out: price range with postage, seller concentration, China competition, optional real sold data and your profit per sale. 8 eBay sites. Pay only for keywords with real data.