Brave AI Mode Scraper

Scrapes Brave Search's AI Mode / Summarizer answers. Extracts the full canonical ai-summary schema: synthesized summary (text + HTML + length + tokens), model/provider, sources, citations, inline references, related & follow-up questions, accompanying organic results, and confidence metadata.

What this Actor collects

Each dataset item represents one Brave AI answer attempt, with the generated summary, cited sources, inline references, related questions, organic results, and extraction metadata that Brave exposes.

• Uses the input limits and filters below to control the crawl.
• Stores source-backed fields defined by the 37-field dataset schema.
• Omits optional fields when the source does not expose a value instead of writing nulls or fabricated placeholders.

Use cases

• Answer-engine monitoring
• Citation and source research
• Generative-search analysis

Input

Provide input in JSON. Fields marked required must be supplied; source-specific alternatives and constraints are described in the field text.

Field	Type	Required	Default	Description
query	string	No	—	A single search query to get the Brave AI Summarizer response for.
queries	array	No	—	Optional list of queries to process in batch (overrides 'query' if provided).
maxItems	integer	No	10	Maximum number of queries to process (when using the 'queries' list).
country	string	No	"us"	Brave country code for localized results (e.g. 'us', 'gb', 'in').
language	string	No	"en"	Brave language code (e.g. 'en', 'de', 'fr').
waitForSummary	boolean	No	true	Whether to wait extra time for the AI summary to load dynamically.
summaryTimeoutMs	integer	No	30000	Maximum milliseconds to wait for the AI summary block to appear.
navigationTimeoutSecs	integer	No	60	Maximum seconds for Brave page navigation.
headless	boolean	No	true	Run Firefox without a visible window.
proxyConfiguration	object	No	—	Use Apify Proxy or authorized custom proxy URLs when required.
debug	boolean	No	false	Enable verbose diagnostics without logging query contents or sensitive values.

Example input

{
  "query": "What is artificial intelligence",
  "maxItems": 10,
  "country": "us",
  "language": "en",
  "proxyConfiguration": {
    "useApifyProxy": false
  },
  "waitForSummary": true,
  "summaryTimeoutMs": 30000,
  "navigationTimeoutSecs": 60,
  "headless": true
}

Output

The default dataset contains one item per processed query. The following are the most useful fields; hasSummary and the count fields distinguish a returned answer from a source-backed no-summary result.

Field	Type	Description
searchQuery	string	Search Query
hasSummary	boolean	Has Summary
aiSummaryLength	integer	Ai Summary Length
model	string	Model
modelProvider	string	Model Provider
sourcesCount	integer	Sources Count
citationsCount	integer	Citations Count
relatedQuestionsCount	integer	Related Questions Count
organicResultsCount	integer	Organic Results Count
matchedSelector	string	Matched Selector
extractionConfidence	number	Extraction Confidence
country	string	Country
language	string	Language
scrapedAt	string	Scraped At
position	integer	Position
type	string	Record Type

Example dataset item

This compact example is taken from local Actor storage. Long text and nested collections are shortened for documentation only.

{
  "searchQuery": "What is artificial intelligence",
  "hasSummary": true,
  "aiSummaryLength": 1026,
  "sourcesCount": 20,
  "citationsCount": 42,
  "relatedQuestionsCount": 8,
  "organicResultsCount": 10,
  "matchedSelector": "#chatllm-main-answer-content",
  "extractionConfidence": 0.9,
  "country": "us",
  "language": "en",
  "scrapedAt": "2026-07-23T15:18:10.460Z"
}

Related Actors

• Brave Autocomplete Scraper
• Brave Discussions Scraper
• Brave Goggles Scraper