{ "openapi": "3.0.1", "info": { "title": "Hybrid Ad Intelligence Scraper", "description": "Scrape competitor ads from Google Ads Transparency & Meta Ads Library, optionally enriched with Poweradspy metrics. Features LLM self-healing fallback, landing page tech detection (Shopify, WooCommerce), global deduplication, and automated inspiration reports.", "version": "1.0", "x-build-id": "qxttgQYL9wFmeP4gf" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/solutionssmart~hybrid-ad-intelligence-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-solutionssmart-hybrid-ad-intelligence-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/solutionssmart~hybrid-ad-intelligence-scraper/runs": { "post": { "operationId": "runs-sync-solutionssmart-hybrid-ad-intelligence-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/solutionssmart~hybrid-ad-intelligence-scraper/run-sync": { "post": { "operationId": "run-sync-solutionssmart-hybrid-ad-intelligence-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "mode": { "title": "Mode", "enum": [ "auto", "free", "poweradspy" ], "type": "string", "description": "Select how the Actor should behave. Auto will use Poweradspy if credentials exist, otherwise free sources.", "default": "auto" }, "freeSources": { "title": "Free Sources", "type": "array", "description": "Select public ad libraries to scrape in free/auto mode.", "items": { "type": "string", "enum": [ "google_ads_transparency", "meta_ads_library" ], "enumTitles": [ "Google Ads Transparency", "Meta Ads Library" ] }, "default": [ "google_ads_transparency" ] }, "searchKeywords": { "title": "Search Keywords (Legacy)", "type": "string", "description": "Single keyword string for backward compatibility." }, "keywords": { "title": "Keywords List", "type": "array", "description": "Multiple keywords to search across sources.", "items": { "type": "string" } }, "advertiserNames": { "title": "Advertiser Names", "type": "array", "description": "Filter by specific advertiser names (if supported by source).", "items": { "type": "string" } }, "adPlatform": { "title": "Ad Platform", "enum": [ "facebook", "instagram", "google", "youtube", "tiktok", "all" ], "type": "string", "description": "Target platform (Poweradspy / Meta options).", "default": "facebook" }, "poweradspyEmail": { "title": "Poweradspy Email", "type": "string", "description": "Your Poweradspy account email." }, "poweradspyPassword": { "title": "Poweradspy Password", "type": "string", "description": "Your Poweradspy account password." }, "enablePoweradspyEnrichment": { "title": "Enable Enrichment", "type": "boolean", "description": "Matches free results with Poweradspy for additional metrics.", "default": false }, "maxResultsPerSource": { "title": "Max Results Per Source", "type": "integer", "description": "Maximum number of ad results to collect from each source (e.g. Google, Meta, Poweradspy).", "default": 50 }, "googleAdvertisersToScan": { "title": "Google advertisers to scan", "type": "integer", "description": "Cost-control setting for Google Ads Transparency. Maximum number of advertiser suggestion pages to open per keyword.", "default": 2 }, "googleDetailPagesToVisit": { "title": "Google detail pages to visit", "type": "integer", "description": "Cost-control setting for Google Ads Transparency. Number of creative detail pages to open for richer metadata after collecting cheap preview cards.", "default": 3 }, "maxTotalResults": { "title": "Max Total Results", "type": "integer", "description": "Maximum total unique ads to keep after deduplication across all sources.", "default": 100 }, "dedupeBy": { "title": "Deduplicate By", "type": "array", "description": "Fields used to identify duplicate ads; ads matching on these keys are merged into one.", "items": { "type": "string", "enum": [ "landingPageUrl", "creativeUrl", "title" ], "enumTitles": [ "Landing Page URL", "Creative Media URL", "Ad Title/Text" ] }, "default": [ "landingPageUrl", "creativeUrl" ] }, "fallbackToMockAdsWhenEmpty": { "title": "Fallback to mock ads when empty", "type": "boolean", "description": "When free sources return 0 ads (e.g. Google DOM changed), return sample mock ads so the run has output. Set to false to get 0 items instead.", "default": true }, "extractionEngine": { "title": "Extraction Engine", "enum": [ "selectors", "stagehand_fallback" ], "type": "string", "description": "Use CSS selectors only, or allow Stagehand (LLM) fallback when selectors fail.", "default": "stagehand_fallback" }, "stagehandEnabled": { "title": "Enable Stagehand Module", "type": "boolean", "description": "When extraction fails, use Stagehand (LLM) to extract ad data from the page.", "default": true }, "stagehandModelProvider": { "title": "Stagehand Model Config (JSON)", "type": "object", "description": "E.g. {\"provider\": \"openai\"}", "default": { "provider": "openai" } }, "enableLandingPlatformDetection": { "title": "Enable Landing Platform Detection", "type": "boolean", "description": "Detect landing page platform (e.g. Shopify, WooCommerce) via HTTP requests.", "default": true }, "enrichmentMaxConcurrency": { "title": "Enrichment Concurrency", "type": "integer", "description": "Number of concurrent HTTP requests for landing platform detection.", "default": 3 }, "enrichmentMaxRequestsPerMinute": { "title": "Enrichment RPM Limit", "type": "integer", "description": "Maximum HTTP requests per minute for landing page analysis.", "default": 30 }, "enrichmentHttpTimeoutMs": { "title": "Enrichment HTTP Timeout", "type": "integer", "description": "Timeout in milliseconds for each landing page HTTP request.", "default": 15000 }, "reportFormat": { "title": "Report Format", "enum": [ "none", "html", "markdown" ], "type": "string", "description": "Format of the inspiration report saved to the Key-Value store.", "default": "html" }, "includeHtmlReport": { "title": "Legacy HTML Report (Deprecated)", "type": "boolean", "description": "Also generate an HTML report; use reportFormat for preferred output.", "default": false }, "headless": { "title": "Headless Browser", "type": "boolean", "description": "Run browser in headless mode (no visible window).", "default": true }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional Apify proxy configuration for browser requests." }, "metaAccessToken": { "title": "Meta Developer Token (Optional)", "type": "string", "description": "Meta/Facebook developer access token for Meta Ads Library API." } } }, "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 } } } } } } } } } }