AI Data Extractor: web page or PDF to JSON by your schema
Pricing
from $20.00 / 1,000 extracted pages
Give a URL and the fields you want, get structured JSON from any web page or PDF with AI. A field the page does not state comes back null, never invented. Up to 20 fields: text, number, true/false, date or list.
Links to the web pages or PDFs to read, one per line (up to 50). Each must be a public http or https URL (ports 80 and 443) that serves a web page or a PDF of at most 10 MB, on a site whose robots.txt allows automated fetching. Every page that yields at least one of your fields is one result. A link that cannot be fetched, or a page that states none of your fields, returns nothing and is not charged.
[ "https://en.wikipedia.org/wiki/Solana_(blockchain_platform)"]A JSON object that names each field you want and its type: string, number, boolean, date or string[] (a list of text). 1 to 20 fields, the same for every URL. A value the page does not state comes back as null, never as a guess.
{ "name": "string", "original_author": "string", "initial_release_year": "number", "consensus_mechanism": "string", "native_token": "string"}