{ "openapi": "3.0.1", "info": { "title": "Universal Store Catalog Scraper (Shopify/Woo/Generic)", "description": "Extract clean, normalized product-catalog data from any Shopify, WooCommerce, or generic e-commerce storefront. AI-agent / MCP ready: every store comes back in one identical schema.", "version": "1.0", "x-build-id": "K6ozLI00m6uoLCy6R" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/maninder~store-catalog-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-maninder-store-catalog-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/maninder~store-catalog-scraper/runs": { "post": { "operationId": "runs-sync-maninder-store-catalog-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/maninder~store-catalog-scraper/run-sync": { "post": { "operationId": "run-sync-maninder-store-catalog-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "storeUrls": { "title": "Store URLs", "type": "array", "description": "Mode 1 (default, safest). Store homepages, collection URLs, or product URLs. Each entry is treated as its own storefront.", "default": [], "items": { "type": "string" } }, "discovery": { "title": "Discovery (opt-in, capped)", "type": "object", "description": "Mode 2. Best-effort discovery of stores from keywords. Disabled by default. You are responsible for what you crawl.", "default": { "enabled": false, "keywords": [], "platformHint": "any", "maxStores": 10 } }, "maxProductsPerStore": { "title": "Max products per store", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Hard cost ceiling per store. Pagination stops here even if more products exist.", "default": 200 }, "includeVariants": { "title": "Include variants", "type": "boolean", "description": "Emit the per-variant array (price, sku, options, availability).", "default": true }, "includeImages": { "title": "Include images", "type": "boolean", "description": "Emit the images array (primary image first).", "default": true }, "includeDescriptionHtml": { "title": "Include raw HTML descriptions", "type": "boolean", "description": "Raw HTML descriptions are bulky. Off by default — clean text is always provided in descriptionText.", "default": false }, "forcePlatform": { "title": "Force platform", "enum": [ "auto", "shopify", "woocommerce", "generic" ], "type": "string", "description": "Override auto-detection.", "default": "auto" }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Honor each store's robots.txt before requesting a URL. Strongly recommended.", "default": true }, "maxConcurrency": { "title": "Max concurrent stores", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many stores to process in parallel. Kept low to stay polite per merchant.", "default": 5 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy used for all requests. Apify auto proxy by default.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }