Brave AI Mode Scraper

Extracts completed answers from Brave Search's public AI Summarizer for one query or a bounded batch. The Actor opens the website, requests AI mode, waits for a recognized completed answer container, and stores one validated record per answer.

Modes

• Single query with query
• Multiple queries with query plus queries
• Bounded parallel query pages with maxConcurrency
• Country and language localization
• Configurable summary and navigation timeouts
• Direct, authorized Apify Residential, or custom proxy routing

Input

Field	Type	Default	Description
query	string	—	Main search query.
queries	array of strings	—	Additional queries to process with query.
maxItems	integer	10	Maximum query count when using queries.
country	string	us	Brave country code.
language	string	en	Brave language code.
waitForSummary	boolean	true	Wait extra time for the AI summary to load.
summaryTimeoutMs	integer	30000	Maximum wait for the summary block in milliseconds.
navigationTimeoutSecs	integer	60	Maximum page-navigation time.
maxConcurrency	integer	2	Maximum query pages processed concurrently in one browser session.
maxRequestRetries	integer	1	Retries temporary failures; explicit access blocks are not retried.
headless	boolean	true	Run Chrome/Chromium without a visible window.
proxyConfiguration	object	—	Apify Proxy or authorized custom proxy URLs.

The complete input contract is in .actor/input_schema.json.

Output

Each successful record includes a stable query/locale ID, query/global positions, plain summary text, sanitized structural HTML, character/word/estimated-token counts, related and follow-up questions, source/citation arrays when Brave displays them, model information when displayed, accompanying organic results when present, exact search context, provenance, and scrape timestamp.

All dataset fields, types, and requiredness are defined in .actor/dataset_schema.json.

Optional attributes are omitted when Brave does not display them. Legitimate zero counts remain numeric zero. Ordinary organic-result text or full-page body text is never accepted as an AI answer, and failed batches store no partial dataset.

Example

{
  "query": "What is machine learning?",
  "queries": ["What is quantum computing?"],
  "maxItems": 2,
  "country": "us",
  "language": "en",
  "waitForSummary": true,
  "summaryTimeoutMs": 45000,
  "navigationTimeoutSecs": 60,
  "maxConcurrency": 2,
  "maxRequestRetries": 1,
  "proxyConfiguration": { "useApifyProxy": false }
}

Reliability and limitations

The Actor uses one internally consistent Chrome/Chromium profile and stable proxy session per run, validates HTTP status and content type, detects explicit block pages, closes every page/context/browser, and retries only bounded temporary failures. CAPTCHA and access-control pages are never solved or repeatedly retried.

Brave controls whether AI mode is available for a query and which optional sources, citations, model names, or organic results appear. A confirmed empty search completes with an empty dataset. A non-empty search page that never produces a genuine AI answer fails clearly instead of storing a placeholder.

How to use

Enter a query or batch in the Apify Input tab, choose the market and language, and start the Actor. Review completed summaries in the Output dataset. The sample record is a truthful Chrome observation of the configured query; Brave may return a CAPTCHA or HTTP 429 to a fresh automated session even while the interactive page renders the answer.