# Google AI Overview Scraper (`devcake/google-ai-overview-scraper`) Actor
Fetch Google's AI Overview block (body, cited sources, images, structured text blocks) plus the standard organic SERP for one or more search queries. Uses the Apify GOOGLE\_SERP proxy and a Chrome-147 TLS fingerprint. Optional SerpApi BYOK fallback resolves queries that Google chooses to defer.
- **URL**: https://apify.com/devcake/google-ai-overview-scraper.md
- **Developed by:** [devcake](https://apify.com/devcake) (community)
- **Categories:** AI, SEO tools, Automation
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet
## Pricing
from $10.00 / 1,000 results
This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage.
Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have.
Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event
## What's an Apify Actor?
Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".
## How to integrate an Actor?
If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.
In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md):
```bash
npm install apify-client
```
In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md):
```bash
pip install apify-client
```
In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md):
````bash
# MacOS / Linux
curl -fsSL https://apify.com/install-cli.sh | bash
# Windows
irm https://apify.com/install-cli.ps1 | iex
```bash
In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md).
If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md).
For usage examples, see the [API](#api) section below.
For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).
# README
## Google AI Overview Scraper — AEO/GEO Citation Tracker & Brand Visibility Monitor
**Extract Google's AI Overview (AIO) block, every cited source with citation position, structured answer content, and inline images — purpose-built for AEO tracking, GEO analytics, brand citation monitoring, and share-of-voice analysis across 53 countries and 26 languages.**
The AI-generated answer box that Google surfaces above the regular search results is the new front page of the internet. If your brand is not cited in it, you lose the click — even if you rank #1 in the organic results. This tool gives marketers, SEO teams, and brand-protection analysts the data they need to **track AI citations, measure brand visibility in AI answers, and benchmark share of voice across Google AI Overview, locales, and competitors.**
---
### 📊 What It Does
This scraper fetches Google's AI-generated answer block for any search query and returns the full structured payload: the AI-generated body text, every cited source (title, URL, domain, citation position, snippet), structured answer blocks (paragraph / heading / list / table / citation card), inline images, the standard organic results, and — when you provide your brand domain — a brand-match report with citation rank and total mentions. Every query becomes one result record ready for AEO/GEO dashboards, marketing analytics, or competitor intelligence pipelines.
---
### 👥 Who It's For
- **Marketing teams and SEO agencies** — measure how your brand appears inside Google's AI-generated answers, not just in traditional search rankings.
- **Brand managers and PR teams** — monitor brand visibility and citation share across markets, languages, and competitor sets.
- **Content strategists** — find the queries where your content is cited by Google AI, where competitors win the citation, and where the citation gap is widest.
- **Competitor intelligence analysts** — track competitor AI citations across locales, build share-of-voice heatmaps, and surface citation-gap opportunities.
- **Marketing analytics and BI teams** — pipe AI citation data into dashboards (Looker, Tableau, Metabase) for board-level reporting on AI search visibility.
- **Brand-protection and reputation teams** — detect when your brand appears in AI answers for sensitive, regulatory, or crisis-related queries.
---
### 📊 Data You Get
Every query produces one result record with the following.
| Field | What it is |
|---|---|
| **Query, country, language** | The original search, plus the market and language used. |
| **AI Overview present** | Whether Google returned an AI Overview block. |
| **AI Overview text** | Plain-text version of the AI-generated answer. |
| **AI Overview HTML** | Raw HTML of the AIO block for full structural fidelity. |
| **Cited sources** | Every source Google cites — title, decoded URL, domain, snippet, and **1-based citation position**. |
| **Structured answer blocks** | The AIO content classified as paragraph / heading / list / table / citation card. |
| **Inline images** | Every image inside the AIO block with source URL and alt text. |
| **Source count and unique domains** | Total cited sources and distinct domains after collapsing `www.` prefixes. |
| **Brand match** | AEO/GEO brand-visibility report — was your brand cited, at what position, on which URL, and how many times. |
| **Organic results** | Standard search results outside the AIO block (when enabled). |
| **Device, status, timestamp, search URL** | Run metadata for reproducibility and error tracking. |
A run-level summary is also produced with aggregate counts (total queries, AIO hits, total sources extracted, errors, finished-at timestamp).
---
### 💡 Use Cases
#### 🔍 AEO / GEO brand tracking
Provide your brand domain and every result record tells you whether your brand was cited in the AI answer, at what position, on which URL, and how many times. Aggregate across hundreds of queries to compute citation share, average citation rank, top-cited URL, and total mentions — the standard AEO/GEO KPIs that replace traditional rank tracking for the AI era.
#### 🌐 Multilingual brand monitoring
Google's AI Overview is not locale-agnostic — the answer, the sources, and the citation domains all change by country and language. Run the same query list in different market/language combinations and compare the cited sources and brand-match blocks to see where your brand is strong, weak, and invisible in AI-generated answers.
#### 📈 Share-of-voice analysis
Run your brand and a competitor brand (two passes) and compare citation counts per query. Build a share-of-voice heatmap by query × market × language to spot where competitors are cited and you are not — the new "keyword gap" for AI search.
#### 🛡️ Brand protection
Track brand citations for sensitive queries (regulatory topics, crisis moments, YMYL categories). Set your brand domain and a curated query list — every record tells you whether your official source is in the citation set, or whether an aggregator, critic, or competitor has taken the citation slot.
#### 🔬 SEO research
Run a query set without a brand filter to harvest the raw cited sources. Domain-frequency analysis on the output reveals which sources Google AI Overview consistently trusts for which topics — actionable input for content strategy, link building, and digital PR.
#### 📰 AI answer dataset and RAG pipeline
Stream the AI Overview text plus cited sources into downstream pipelines for question-answering dataset construction, RAG knowledge bases, or LLM evaluation corpora.
---
### 🚀 Quick Start
1. **Open the tool** on the Apify platform and click *Try for free*, or add it to your AI assistant's MCP server.
2. **Configure your inputs** — paste your query list (1–500 queries), optionally provide your brand domain for AEO/GEO tracking, choose the country and language, and toggle the organic-results option if you want the standard search results too.
3. **Run and download** — the tool pushes one result record per query. Open the **Cited Sources** view for citation analysis, the **Overview** view for fast triage, or the **Organic Results** view for standard search rows.
---
### ⚙️ Input Parameters
| Parameter | Required | Description |
|---|---|---|
| **Queries** | yes | One or more search queries (1–500). Each produces one result record. |
| **Country** | no | The market to query (53 countries — US, UK, Germany, France, Japan, Brazil, Australia, India, etc.). Default: United States. |
| **Language** | no | The language to query (26 languages — English, German, Spanish, French, Japanese, etc.). Default: English. |
| **Brand domain** | no | Your brand domain for AEO/GEO brand tracking. Triggers the brand-match report on every record. Example: `apify.com`. |
| **Device** | no | Desktop or mobile Chrome emulation. Default: desktop. |
| **Include organic results** | no | Also extract the standard search results outside the AIO block. Off by default. |
| **Max organic results per query** | no | Cap for organic results when the option above is enabled (1–100, default 10). |
**Defaults:** United States, English, desktop. Run with these defaults for the most reliable AIO results — Google's AI Overview is English-dominant in most regions.
---
### 📝 Example
#### Input — AEO brand tracking for Nike in the US market
````
Queries: best running shoes 2026, how to choose trail running shoes, marathon training plan for beginners
Country: United States
Language: English
Brand domain: nike.com
````
#### Output — one record per query
For `best running shoes 2026`:
- **AI Overview present:** yes
- **AI Overview text:** "The best running shoes of 2026 combine responsive foam, lightweight mesh uppers, and reliable outsole grip. Top picks include shoes engineered for daily training, tempo runs, and long-distance racing..."
- **Cited sources:** 6, across 6 unique domains (runnersworld.com, nike.com, ...)
- **Brand match (nike.com):** ✓ cited at position 2 — `https://www.nike.com/a/what-is-pe`
- **Structured blocks:** paragraph + 6 citation cards
- **Device:** desktop
- **Search URL:** `http://www.google.com/search?q=best+running+shoes+2026&hl=en&gl=us`
- **Fetched at:** 2026-06-24 17:05 UTC
Aggregate the brand-match block across all queries to compute Nike's **citation share**, **average citation rank**, **top-cited URL**, and **citation gap** versus competitors.
# Actor input Schema
## `queries` (type: `array`):
Enter one or more Google search queries. Each query runs independently and produces one record.
Tip: AI Overview fires most reliably on how/why/compare questions, e.g. "what causes inflation". Bare brand searches like "amazon" usually return no AIO.
## `gl` (type: `string`):
ISO 3166-1 alpha-2 country code (e.g. us, gb, de). Drives which Google domain and locale-specific results you see.
## `hl` (type: `string`):
ISO 639-1 language code (e.g. en, de, es).
Note: AI Overview is English-dominant in most regions; non-en values frequently yield no AIO.
## `targetDomain` (type: `string`):
Optional. When set, each record includes a brandMatch block with matched, position, citedUrl, and matchCount.
Format: enter the bare domain — apify.com, not https://apify.com/. The www. prefix is stripped automatically.
## `includeOrganic` (type: `boolean`):
Extract standard organic results (position, title, url, snippet) outside the AIO container. Turn on if you need the full SERP, not just the AI block.
## `organicLimit` (type: `integer`):
Only used when Include organic SERP is on. Google emits ~10 organic results per page, so 10 is usually enough.
## Actor input object example
```json
{
"queries": [
"what causes inflation"
],
"gl": "us",
"hl": "en",
"includeOrganic": false,
"organicLimit": 10
}
````
# Actor output Schema
## `dataset` (type: `string`):
One record per query with the AIO body, cited sources, organic SERP, and run metadata.
## `summary` (type: `string`):
Aggregate counts for the run: total queries, AIO hits, total sources extracted, finished-at timestamp.
# API
You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.
## JavaScript example
```javascript
import { ApifyClient } from 'apify-client';
// Initialize the ApifyClient with your Apify API token
// Replace the '' with your token
const client = new ApifyClient({
token: '',
});
// Prepare Actor input
const input = {
"queries": [
"what causes inflation"
]
};
// Run the Actor and wait for it to finish
const run = await client.actor("devcake/google-ai-overview-scraper").call(input);
// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
console.dir(item);
});
// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs
```
## Python example
```python
from apify_client import ApifyClient
# Initialize the ApifyClient with your Apify API token
# Replace '' with your token.
client = ApifyClient("")
# Prepare the Actor input
run_input = { "queries": ["what causes inflation"] }
# Run the Actor and wait for it to finish
run = client.actor("devcake/google-ai-overview-scraper").call(run_input=run_input)
# Fetch and print Actor results from the run's dataset (if there are any)
print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"])
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
print(item)
# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start
```
## CLI example
```bash
echo '{
"queries": [
"what causes inflation"
]
}' |
apify call devcake/google-ai-overview-scraper --silent --output-dataset
```
## MCP server setup
```json
{
"mcpServers": {
"apify": {
"command": "npx",
"args": [
"mcp-remote",
"https://mcp.apify.com/?tools=devcake/google-ai-overview-scraper",
"--header",
"Authorization: Bearer "
]
}
}
}
```
## OpenAPI specification
```json
{
"openapi": "3.0.1",
"info": {
"title": "Google AI Overview Scraper",
"description": "Fetch Google's AI Overview block (body, cited sources, images, structured text blocks) plus the standard organic SERP for one or more search queries. Uses the Apify GOOGLE_SERP proxy and a Chrome-147 TLS fingerprint. Optional SerpApi BYOK fallback resolves queries that Google chooses to defer.",
"version": "0.3",
"x-build-id": "EAqiPOxOhKcZGfhtn"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/devcake~google-ai-overview-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-devcake-google-ai-overview-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/devcake~google-ai-overview-scraper/runs": {
"post": {
"operationId": "runs-sync-devcake-google-ai-overview-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/devcake~google-ai-overview-scraper/run-sync": {
"post": {
"operationId": "run-sync-devcake-google-ai-overview-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
}
},
"components": {
"schemas": {
"inputSchema": {
"type": "object",
"required": [
"queries"
],
"properties": {
"queries": {
"title": "Search queries",
"minItems": 1,
"maxItems": 500,
"type": "array",
"description": "Enter one or more Google search queries. Each query runs independently and produces one record.
Tip: AI Overview fires most reliably on how/why/compare questions, e.g. \"what causes inflation\". Bare brand searches like \"amazon\" usually return no AIO.",
"items": {
"type": "string"
}
},
"gl": {
"title": "Country (gl=)",
"enum": [
"us",
"gb",
"de",
"fr",
"ca",
"au",
"es",
"it",
"br",
"nl",
"ar",
"at",
"be",
"bg",
"ch",
"cl",
"co",
"cz",
"dk",
"eg",
"fi",
"gr",
"hk",
"hr",
"hu",
"id",
"ie",
"il",
"in",
"jp",
"kr",
"mx",
"my",
"ng",
"no",
"nz",
"pe",
"ph",
"pk",
"pl",
"pt",
"ro",
"ru",
"sa",
"se",
"sg",
"sk",
"th",
"tr",
"tw",
"ua",
"ae",
"vn",
"za"
],
"type": "string",
"description": "ISO 3166-1 alpha-2 country code (e.g. us, gb, de). Drives which Google domain and locale-specific results you see.",
"default": "us"
},
"hl": {
"title": "Language (hl=)",
"enum": [
"en",
"de",
"es",
"fr",
"it",
"nl",
"pt",
"ru",
"ja",
"ko",
"zh",
"ar",
"hi",
"tr",
"pl",
"sv",
"no",
"fi",
"da",
"el",
"he",
"th",
"vi",
"id",
"ms",
"cs"
],
"type": "string",
"description": "ISO 639-1 language code (e.g. en, de, es).
Note: AI Overview is English-dominant in most regions; non-en values frequently yield no AIO.",
"default": "en"
},
"targetDomain": {
"title": "Brand domain",
"type": "string",
"description": "Optional. When set, each record includes a brandMatch block with matched, position, citedUrl, and matchCount.
Format: enter the bare domain — apify.com, not https://apify.com/. The www. prefix is stripped automatically."
},
"includeOrganic": {
"title": "Include organic SERP",
"type": "boolean",
"description": "Extract standard organic results (position, title, url, snippet) outside the AIO container. Turn on if you need the full SERP, not just the AI block.",
"default": false
},
"organicLimit": {
"title": "Max organic results per query",
"minimum": 1,
"maximum": 100,
"type": "integer",
"description": "Only used when Include organic SERP is on. Google emits ~10 organic results per page, so 10 is usually enough.",
"default": 10
}
}
},
"runsResponseSchema": {
"type": "object",
"properties": {
"data": {
"type": "object",
"properties": {
"id": {
"type": "string"
},
"actId": {
"type": "string"
},
"userId": {
"type": "string"
},
"startedAt": {
"type": "string",
"format": "date-time",
"example": "2025-01-08T00:00:00.000Z"
},
"finishedAt": {
"type": "string",
"format": "date-time",
"example": "2025-01-08T00:00:00.000Z"
},
"status": {
"type": "string",
"example": "READY"
},
"meta": {
"type": "object",
"properties": {
"origin": {
"type": "string",
"example": "API"
},
"userAgent": {
"type": "string"
}
}
},
"stats": {
"type": "object",
"properties": {
"inputBodyLen": {
"type": "integer",
"example": 2000
},
"rebootCount": {
"type": "integer",
"example": 0
},
"restartCount": {
"type": "integer",
"example": 0
},
"resurrectCount": {
"type": "integer",
"example": 0
},
"computeUnits": {
"type": "integer",
"example": 0
}
}
},
"options": {
"type": "object",
"properties": {
"build": {
"type": "string",
"example": "latest"
},
"timeoutSecs": {
"type": "integer",
"example": 300
},
"memoryMbytes": {
"type": "integer",
"example": 1024
},
"diskMbytes": {
"type": "integer",
"example": 2048
}
}
},
"buildId": {
"type": "string"
},
"defaultKeyValueStoreId": {
"type": "string"
},
"defaultDatasetId": {
"type": "string"
},
"defaultRequestQueueId": {
"type": "string"
},
"buildNumber": {
"type": "string",
"example": "1.0.0"
},
"containerUrl": {
"type": "string"
},
"usage": {
"type": "object",
"properties": {
"ACTOR_COMPUTE_UNITS": {
"type": "integer",
"example": 0
},
"DATASET_READS": {
"type": "integer",
"example": 0
},
"DATASET_WRITES": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_READS": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_WRITES": {
"type": "integer",
"example": 1
},
"KEY_VALUE_STORE_LISTS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_READS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_WRITES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_INTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_EXTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_SERPS": {
"type": "integer",
"example": 0
}
}
},
"usageTotalUsd": {
"type": "number",
"example": 0.00005
},
"usageUsd": {
"type": "object",
"properties": {
"ACTOR_COMPUTE_UNITS": {
"type": "integer",
"example": 0
},
"DATASET_READS": {
"type": "integer",
"example": 0
},
"DATASET_WRITES": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_READS": {
"type": "integer",
"example": 0
},
"KEY_VALUE_STORE_WRITES": {
"type": "number",
"example": 0.00005
},
"KEY_VALUE_STORE_LISTS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_READS": {
"type": "integer",
"example": 0
},
"REQUEST_QUEUE_WRITES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_INTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"DATA_TRANSFER_EXTERNAL_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
"type": "integer",
"example": 0
},
"PROXY_SERPS": {
"type": "integer",
"example": 0
}
}
}
}
}
}
}
}
}
}
```