Context API / Scrape Styleguide

Context.dev tool context-dev-web-styleguide on looot: input fields, $0.025 per call, output shape, and code to run it with curl, JavaScript or Python.

Extract a comprehensive design system from a website including colors, typography, spacing, shadows, and UI components. Send one of: domain, directUrl.

Tool id: context-dev-web-styleguide
Provider: Context.dev
Job: Styleguide web (web.styleguide)
Price: $0.025 per call. A call that fails at the provider costs $0.

Inputs

Name	Type	Required	Description
`colorScheme`	string	no	Optional browser color scheme to emulate for websites that respond to prefers-color-scheme. This value is part of the styleguide cache key.
`directUrl`	string	no	A specific URL to fetch the styleguide from directly, bypassing domain resolution (e.g., ‘https://example.com/design-system’). When provided, the styleguide is extracted from this exact URL. You must provide either ‘domain’ or ‘directUrl’, but not both.
`domain`	string	no	Domain name to extract styleguide from (e.g., ‘example.com’, ‘google.com’). The domain will be automatically normalized and validated. You must provide either ‘domain’ or ‘directUrl’, but not both. Example: “stripe.com”
`maxAgeMs`	string	no	Maximum age in milliseconds for cached brand data before the API performs a hard refresh. Defaults to 3 months (7776000000 ms). Values below 1 day (86400000 ms) are clamped to 1 day; values above 1 year (31536000000 ms) are clamped to 1 year.
`tags`	array	no	Optional tags for tracking usage. Up to 20 tags, each 1 to 50 characters.
`timeoutMS`	integer	no	Optional timeout in milliseconds for the request. If the request takes longer than this value, it will be aborted with a 408 status code. Maximum allowed value is 300000ms (5 minutes).

Output

Shape of the run’s result, checked against 1 real answer:

{ code, domain, status, request_id, styleguide: { mode, colors: { text, accent, background }, shadows: { lg, md, sm, xl, inner }, fontLinks: { sohne-var: { ... } }, components: { card: { ... }, button: { ... } }, typography: { p: { ... }, headings: { ... } }, elementSpacing: { lg, md, sm, xl, xs } }, key_metadata: { credits_consumed, credits_remaining }, finalDOMState, cache_metadata: { age_ms, status } }

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":"context-dev-web-styleguide","input":{"tags":["production","team-alpha"],"domain":"stripe.com"},"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: "context-dev-web-styleguide",
    input: {
      tags: ["production", "team-alpha"],
      domain: "stripe.com",
    },
    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": "context-dev-web-styleguide",
        "input": {
            "tags": ["production", "team-alpha"],
            "domain": "stripe.com",
        },
        "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.styleguide as endpointId; see the job page.

Context API / Scrape Styleguide

Inputs

Output

Run it