{ "openapi": "3.0.1", "info": { "title": "The Warehouse NZ Scraper | Search, URLs, Details, Reviews", "description": "Scrape The Warehouse New Zealand search results, category pages, and direct product URLs. Extract prices, availability, brand, images, breadcrumbs, attributes, product details, and optional customer reviews. Supports search mode, URL mode, sorting, pagination, and MCP connector export.", "version": "0.1", "x-build-id": "oJ5peMYpneMPq24Dr" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/abotapi~thewarehouse-co-nz-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-abotapi-thewarehouse-co-nz-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/abotapi~thewarehouse-co-nz-scraper/runs": { "post": { "operationId": "runs-sync-abotapi-thewarehouse-co-nz-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/abotapi~thewarehouse-co-nz-scraper/run-sync": { "post": { "operationId": "run-sync-abotapi-thewarehouse-co-nz-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "mode" ], "properties": { "mode": { "title": "Mode", "enum": [ "search", "url" ], "type": "string", "description": "Use search mode for keyword search. Use URL mode when you already have The Warehouse search, category, or product URLs.", "default": "search" }, "queries": { "title": "Search keywords", "type": "array", "description": "One or more keywords to search. Each query is searched separately.", "items": { "type": "string" } }, "sortBy": { "title": "Sort by", "enum": [ "relevance", "price_asc", "price_desc", "top_rated", "newest", "best_sellers", "name_asc", "name_desc" ], "type": "string", "description": "Maps directly to the storefront search sort rules. URL mode preserves whatever sort is already encoded in the pasted URL.", "default": "relevance" }, "urls": { "title": "The Warehouse URLs", "type": "array", "description": "Search, category, or product URLs. Pagination starts from the page encoded in the URL when present and walks forward.", "items": { "type": "string" } }, "fetchDetails": { "title": "Fetch product details", "type": "boolean", "description": "Open each product page for description, brand, structured attributes, breadcrumbs, image gallery and availability.", "default": true }, "fetchReviews": { "title": "Fetch customer reviews", "type": "boolean", "description": "Also collect product reviews when the page exposes a review API or inline review markup.", "default": false }, "maxReviewsPerProduct": { "title": "Max reviews per product", "minimum": 0, "type": "integer", "description": "Cap on reviews collected per product when Fetch customer reviews is on. Set 0 for all available reviews returned by the detected endpoint.", "default": 10 }, "includeUnavailable": { "title": "Include unavailable products", "type": "boolean", "description": "Keep products marked unavailable or out of stock. Turn off to return only likely in-stock products when the page exposes availability.", "default": true }, "maxItems": { "title": "Max products", "minimum": 0, "type": "integer", "description": "Maximum matching products to save. Leave empty or set 0 for unlimited. This is the run's only default cap.", "default": 20 }, "maxPages": { "title": "Max pages per query / URL", "minimum": 0, "maximum": 200, "type": "integer", "description": "Leave empty or set 0 for unlimited; the run stops at Max products. Use this only when you want an explicit page cap.", "default": 0 }, "mcpConnectors": { "title": "Pipe results into your apps (optional)", "type": "array", "description": "Optionally send the scraped results into the apps you already use, via Model Context Protocol (MCP) connectors. Authorize a connector once under Apify → Settings → Integrations, then select it here. Notion gets a page per item; other connectors receive a best-effort write or digest. Leave empty to skip — this never changes the dataset output. Supported: Notion (https://mcp.notion.com/mcp), Linear (https://mcp.linear.app/sse), Airtable (https://mcp.airtable.com/mcp), Apify (https://mcp.apify.com)." }, "notionParentPageUrl": { "title": "Notion parent page (Notion connector only)", "type": "string", "description": "URL (or id) of the Notion page under which item pages are created. Required to enable the Notion export; ignored by other connectors." }, "maxNotifyListings": { "title": "Max items to export per connector", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Cap on items written to each connector per run. Does not affect the dataset.", "default": 50 }, "proxy": { "title": "Proxy configuration", "type": "object", "description": "Use a proxy configuration that matches your account and traffic needs. The default prefill is suitable for most production runs.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ], "apifyProxyCountry": "NZ" } } } }, "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 } } } } } } } } } }