Skip to content
looot docs
Esc
↑↓navigate↵open⌘Jpreview
On this page

ScrapeGraphAI / Search and extract

ScrapeGraphAI tool scrapegraphai-search-extract on looot: input fields, $0.01 per result, output shape, and code to run it with curl, JavaScript or Python.

Searches the web, reads each result page and returns JSON extracted for your prompt (optionally shaped by a JSON schema), plus the results[]. numResults 1-20, default 3.

  • Tool id: scrapegraphai-search-extract
  • Provider: ScrapeGraphAI
  • Job: Answer web search (web.search.answer)
  • Price: $0.01 per result. A call that fails at the provider costs $0.

Inputs

Name Type Required Description
allowedTypes array yes MIME types to accept; PDFs are excluded because they bill per page. Use [“text/html”].
fetchConfig object no Fetch options (stealth is not offered: it adds 5 credits)
locationGeoCode string no
numResults integer no
prompt string yes
query string yes
schema object no
timeRange string no

Output

The run’s result holds the provider’s answer. Signed in, looot inspect scrapegraphai-search-extract prints its fields.

Run it

Every call needs your API token in LOOOT_TOKEN; Sign in shows how to get one. Each run also needs a new idempotency key, so a retry never pays twice. With wait: 30 the answer comes back inline when the run ends within 30 seconds. Otherwise you get the running run back: poll GET /v1/runs/<runId>.

Example input with placeholder values:

curl -X POST "https://api.looot.ai/v1/runs" \
  -H "Authorization: Bearer $LOOOT_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"endpointId":"scrapegraphai-search-extract","input":{"query":"<query>","prompt":"<prompt>","allowedTypes":[]},"wait":30}'
const response = await fetch("https://api.looot.ai/v1/runs", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.LOOOT_TOKEN}`,
    "Content-Type": "application/json",
    "Idempotency-Key": crypto.randomUUID(),
  },
  body: JSON.stringify({
    endpointId: "scrapegraphai-search-extract",
    input: {
      query: "<query>",
      prompt: "<prompt>",
      allowedTypes: [],
    },
    wait: 30,
  }),
});
const run = await response.json();
console.log(run.status, run.result);
import os
import uuid

import requests

response = requests.post(
    "https://api.looot.ai/v1/runs",
    headers={
        "Authorization": f"Bearer {os.environ['LOOOT_TOKEN']}",
        "Idempotency-Key": str(uuid.uuid4()),
    },
    json={
        "endpointId": "scrapegraphai-search-extract",
        "input": {
            "query": "<query>",
            "prompt": "<prompt>",
            "allowedTypes": [],
        },
        "wait": 30,
    },
    timeout=90,
)
run = response.json()
print(run["status"], run.get("result"))

To let looot pick among every provider of this job instead, send job:web.search.answer as endpointId; see the job page.

Was this page helpful?