HushSearchDocs

Agent Scrape

Give a URL and a goal; a browser agent navigates until it finds what you asked for.

BrowsersLong-running: consider /v1/jobs

POST/v1/agent-scrape/5 credits

Request
curl -X POST https://api.hushsearch.io/v1/agent-scrape/ \
  -H "X-API-Key: hs_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "url": "https://books.toscrape.com/",
  "goal": "Find the price of the first travel book",
  "max_steps": 4
}'

A browser agent starts at url and takes up to max_steps actions (clicking, scrolling, following links) to satisfy the goal, then returns what it found.

Parameters

FieldTypeDefaultNotes
urlstring—Required. Starting page.
goalstring—Required. 1–500 characters, e.g. "find the pricing for the team plan".
max_stepsinteger41–20 browser actions.

Costs 5 credits per call. If the agent fails, the charge is refunded.

On this page