Google AI Overview Scraper

Scrapes Google AI Overviews (SGE) for any query. Extracts the overview text and HTML, model/provider, sources, inline references, follow-up/related questions, organic results, extraction confidence, and more.

Pricing

from $1.99 / 1,000 google ai overview scraper results

Rating

0.0

(0)

Developer

Search API

Actor stats

Bookmarked

105

Total users

Monthly active users

2 days ago

Last modified

What this Actor collects

The Actor stores one clean JSON record per Google AI Overview, including overview text and HTML, provider, citations and inline references, follow-up questions, related organic results, confidence signals, locale, and retrieval provenance when available.

Uses the input limits and filters below to control the crawl.
Stores source-backed fields defined by the 44-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. The Default / example column shows a schema default when one exists; otherwise it shows a documented prefill or fixture value.

Field	Type	Required	Default / example	Description
`queries`	array	Yes	`["What is quantum computing"]`	List of search queries to scrape AI Overviews for.
`maxItems`	integer	No	`10`	Maximum number of results to return.
`gl`	string	No	`"us"`	Google country parameter (e.g. 'us', 'uk', 'in').
`hl`	string	No	`"en"`	Google language parameter (e.g. 'en', 'es', 'fr').
`proxyConfiguration`	object	No	`{"useApifyProxy":true,"apifyProxyGroups":["GOOGLE_SERP"]}`	Select proxies to use for the scraper.

Example input

{
  "queries": [
    "what is machine learning"
  ],
  "maxItems": 20,
  "proxyConfiguration": {
    "useApifyProxy": true,
    "apifyProxyGroups": [
      "GOOGLE_SERP"
    ]
  },
  "gl": "us",
  "hl": "en"
}

Output

The default dataset contains one item per query that yields an AI Overview. The following are the most useful fields; citations, follow-ups, organic results, and model details appear only when Google exposes them.

Field	Type	Description
`position`	integer	Query Position
`searchQuery`	string	Search Query
`summaryTitle`	string	Summary Title
`aiSummary`	string	AI Summary
`sourcesCount`	integer	Sources Count
`relatedQuestionsCount`	integer	Related Questions Count
`organicResultsCount`	integer	Organic Results Count
`extractionConfidence`	string	Extraction Confidence
`scrapedAt`	string	Scraped At
`type`	string	Record Type
`query`	string	Query
`resultType`	string	Result Type
`page`	integer	Page
`queryLength`	integer	Query Length
`queryWordCount`	integer	Query Word Count
`aiSummaryHtml`	string	Clean Summary HTML

Example dataset item

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

{
  "position": 1,
  "searchQuery": "what is machine learning",
  "summaryTitle": "Machine learning is a subset of artificial intelligence where algorithms analyze vast amounts of data to detect patterns and make predictions without needing explicit, hard-coded …",
  "aiSummary": "Machine learning is a subset of artificial intelligence where algorithms analyze vast amounts of data to detect patterns and make predictions without needing explicit, hard-coded …",
  "sourcesCount": 2,
  "relatedQuestionsCount": 4,
  "organicResultsCount": 8,
  "extractionConfidence": "high",
  "scrapedAt": "2026-07-23T19:20:34.552Z",
  "type": "ai_overview",
  "query": "what is machine learning",
  "resultType": "google_ai_overview"
}

Google AI Overview Scraper

codingfrontend/google-ai-overview-scraper

A robust, high-performance utility designed for developer automation, data integration, and AI training. Features built-in captcha bypass, headful/headless browser execution, and proxy support to scrape Google data seamlessly, reliably, and at scale.