Skip to main content
POST https://v2-api.scrapegraphai.com/api/extract
Replaces the v1 smartscraper endpoint. Provide a prompt (and optionally a JSON schema) and get typed JSON back — no selectors or post-processing needed.

​
Request body

Exactly one of url, html, or markdown must be supplied as the source.
​
url
string
URL of the page to extract from.
​
html
string
Raw HTML content to extract from (max 2 MB).
​
markdown
string
Markdown content to extract from (max 2 MB).
​
prompt
string
required
Natural-language description of what to extract.
​
schema
object
JSON schema describing the desired output shape. When provided, the LLM is constrained to match it.
​
mode
string
HTML pre-processing mode: "normal", "reader", or "prune".
​
fetchConfig
object
Fetch-time options. See the Scrape endpoint for the full field list (mode, stealth, headers, cookies, scrolls, wait, timeout, country). Ignored when html or markdown is supplied.

​
Example request

curl -X POST https://v2-api.scrapegraphai.com/api/extract \
  -H "SGAI-APIKEY: $SGAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://example.com",
    "prompt": "What is the title of this page?"
  }'

​
Example response

{
  "id": "8c34fc03-17be-4fcc-a7ce-6ebcab23ad43",
  "raw": null,
  "json": {
    "title": "Example Domain"
  },
  "usage": {
    "promptTokens": 361,
    "completionTokens": 92
  },
  "metadata": {
    "chunker": { "chunks": [{ "size": 33 }] },
    "fetch": {}
  }
}
FieldDescription
idUUID for this extract call.
jsonStructured output matching the schema (or free-form JSON when no schema is supplied).
rawRaw model output before JSON parsing, when available.
usage.promptTokens / usage.completionTokensLLM token accounting.
metadata.chunkerHow the source content was split before extraction.
metadata.fetchFetch diagnostics (populated when the page was fetched by the API).

​
With a schema

curl -X POST https://v2-api.scrapegraphai.com/api/extract \
  -H "SGAI-APIKEY: $SGAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://example.com",
    "prompt": "Extract the page title and description",
    "schema": {
      "type": "object",
      "properties": {
        "title":       { "type": "string" },
        "description": { "type": "string" }
      },
      "required": ["title"]
    }
  }'

​
Extract from HTML or markdown

curl -X POST https://v2-api.scrapegraphai.com/api/extract \
  -H "SGAI-APIKEY: $SGAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "html": "<html><body><h1>Widget</h1><p>$9.99</p></body></html>",
    "prompt": "Extract product name and price"
  }'