POST/api/extract

Extract Structured JSON

LLM-driven extraction from a URL, HTML, or markdown input with a prompt and optional JSON schema.

ScrapeGraphAI·Dynamic pricing

Dynamic pricing

0.025 + (get(body, 'fetchConfig.stealth', 0) ? 0.025 : 0)

Example code

// Using @orth/sdk - The simplest way to call APIs
// Install: npm install @orth/sdk
import Orthogonal from "@orth/sdk";

const orthogonal = new Orthogonal({
  apiKey: process.env.ORTHOGONAL_API_KEY,
});

const output = await orthogonal.run({
  api: "scrapegraphai",
  path: "/api/extract",
  body: {
    "prompt": "example"
  }
});

console.log(output);

Body parameters

promptrequired

string

Extraction prompt (1-10000 chars)

url

string

URL to extract from

html

string

Raw HTML to extract from

markdown

string

Markdown to extract from

schema

object

JSON schema for structured output

mode

string

Content mode: normal, reader, or prune

contentType

string

Force content type

fetchConfig

object

Fetch options: mode, stealth, timeout, wait, headers, cookies, country, scrolls

Response

string

raw

null

json.job_title

null

json.company_name

string

json.job_location

string

json.company_domain

string

usage.promptTokens

number

usage.completionTokens

number

metadata.chunker.chunks.0.size

number