{ "openapi": "3.0.1", "info": { "title": "Google AI Overviews Scraper", "description": "Scrape Google AI Overview (AIO) for any query — get the AI-generated answer text, cited source domains/URLs/titles, citation positions, and optional brand-match detection. Multi-country, desktop/mobile, MCP-ready for AI agents. Hybrid Camoufox scrape + optional SerpApi BYOK fallback.", "version": "0.1", "x-build-id": "5s5mv4F7Yo4nqui0j" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/khadinakbar~google-ai-overviews-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-khadinakbar-google-ai-overviews-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/khadinakbar~google-ai-overviews-scraper/runs": { "post": { "operationId": "runs-sync-khadinakbar-google-ai-overviews-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/khadinakbar~google-ai-overviews-scraper/run-sync": { "post": { "operationId": "run-sync-khadinakbar-google-ai-overviews-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": 50, "type": "array", "description": "List of Google search queries to check for AI Overviews (e.g., ['best CRM software 2026', 'how to scrape Google AI Overviews']). One record per query is returned. Max 50 queries per run. NOT a list of full Google URLs — pass plain text queries; the actor builds the SERP URL with countryCode/languageCode.", "items": { "type": "string" } }, "targetDomain": { "title": "Brand domain to detect (optional)", "type": "string", "description": "Your brand domain to match against AIO source citations (e.g., 'apify.com', or comma-separated 'apify.com,docs.apify.com'). When set, output includes brandMatch.matched, position, citedUrl, matchCount. Leave empty to skip brand matching. NOT a full URL — pass bare domains only." }, "countryCode": { "title": "Country code", "enum": [ "us", "gb", "de", "fr", "es", "it", "nl", "br", "in", "au", "ca", "jp", "kr", "mx", "ar", "co", "pl", "ru", "tr", "ae", "sa", "za", "se", "no", "fi", "dk", "ch", "at", "be", "ie", "nz", "sg", "hk", "tw", "th", "id", "vn", "ph", "my", "il" ], "type": "string", "description": "Two-letter ISO 3166-1 alpha-2 country code for geo-targeting Google SERP (e.g., 'us', 'gb', 'de'). Affects which results and which AIO variant Google returns. Defaults to 'us'. NOT a country name — use ISO codes only.", "default": "us" }, "languageCode": { "title": "Language code", "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": "Two-letter ISO 639-1 language code for Google interface language (e.g., 'en', 'de', 'es'). Sets the hl= URL param. Defaults to 'en'. NOT a locale string like 'en-US' — use the bare language code.", "default": "en" }, "device": { "title": "Device emulation", "enum": [ "desktop", "mobile" ], "type": "string", "description": "Browser viewport to emulate when fetching the SERP. Google sometimes shows different AIO content for mobile vs desktop. Defaults to 'desktop'. NOT a specific phone model — only 'desktop' or 'mobile' accepted.", "default": "desktop" }, "serpApiKey": { "title": "SerpApi key (BYOK fallback, optional)", "type": "string", "description": "Optional SerpApi.com key for hybrid fallback when the Camoufox scrape is blocked. Get one free at serpapi.com (100/mo free). When provided, failed queries are retried via SerpApi automatically. Leave empty to use Camoufox-only — most queries succeed. NOT a Google API key — must be a SerpApi.com key." }, "maxRetries": { "title": "Max retries per query", "minimum": 0, "maximum": 5, "type": "integer", "description": "How many times to retry a query that fails to load AIO or returns no answer container. Helps with intermittent rendering. Defaults to 2 (3 attempts total). NOT a global cap — applies per query.", "default": 2 }, "forceSerpapi": { "title": "Skip Camoufox, use SerpApi directly", "type": "boolean", "description": "Skip the Camoufox scrape attempt entirely and go straight to SerpApi (managed if you don't bring a key, BYOK otherwise). Saves ~7 seconds per query when you already know Google residential blocks. Defaults to false. NOT recommended for normal use — automatic circuit breaker handles persistent blocking.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy setup. Defaults to Apify residential (mandatory for Google scraping). Override only if you know what you're doing — datacenter proxies get blocked instantly by Google. NOT optional in practice.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }