{ "openapi": "3.0.1", "info": { "title": "Grocery Product Scraper for Instacart", "description": "Scrapes product details, retailer storefronts and cross-retailer search results from instacart.com. Independent tool, not affiliated with or endorsed by Instacart.", "version": "0.0", "x-build-id": "Q35vXX0yZUbKeqrCV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/piotrv1001~instacart-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-piotrv1001-instacart-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/piotrv1001~instacart-scraper/runs": { "post": { "operationId": "runs-sync-piotrv1001-instacart-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/piotrv1001~instacart-scraper/run-sync": { "post": { "operationId": "run-sync-piotrv1001-instacart-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Any mix of Instacart URLs: PDPs (/products/...), retailer storefronts (/store/{retailer}), or cross-retailer search (/store/s?k=...). Other Instacart URL families will be skipped.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "retailerSlugs": { "title": "Retailer slugs", "uniqueItems": true, "type": "array", "description": "List of retailer slugs (e.g. costco, safeway, target). For each one the actor scrapes the storefront and enqueues featured products as PDPs. In grid mode (Postal codes set) these are the retailers priced in each ZIP instead.", "default": [], "items": { "type": "string" } }, "searchQueries": { "title": "Search queries", "uniqueItems": true, "type": "array", "description": "List of free-text queries to run against the cross-retailer search (/store/s?k=...). Only the first SSR page is captured.", "default": [], "items": { "type": "string" } }, "productIds": { "title": "Product IDs", "uniqueItems": true, "type": "array", "description": "List of Instacart product IDs to fetch directly. The slug part of the PDP URL is decorative and is omitted. In grid mode (Postal codes set) these are the products priced in each ZIP.", "default": [], "items": { "type": "string" } }, "defaultRetailerSlug": { "title": "Default retailer slug for product IDs", "type": "string", "description": "Retailer slug to attach as ?retailerSlug= when fetching PDPs from productIds. If empty, Instacart returns its default (SF) market.", "default": "" }, "seedFromHome": { "title": "Seed retailers from Instacart home", "type": "boolean", "description": "If true, fetch https://www.instacart.com/ and enqueue all retailer storefronts found on it. Useful when you want a broad sweep.", "default": false }, "postalCode": { "title": "Postal code (ZIP)", "type": "string", "description": "US ZIP code recorded on PDP / storefront / search rows. Those pages are always priced for Instacart's default location (94105, San Francisco). For real per-ZIP prices use Postal codes (grid mode) below.", "default": "94105" }, "postalCodes": { "title": "Postal codes (price grid by ZIP)", "uniqueItems": true, "type": "array", "description": "List of US ZIP codes. When set, the actor runs grid mode: every Product ID × ZIP × retailer (Retailer slugs, or the default retailer slug) is priced at the store that actually serves that ZIP. One row per priced cell with shopId, retailerLocationId, place and zoneId. Cells that cannot be priced (retailer does not serve the ZIP, ZIP outside Instacart, product not carried there) are not charged and are listed in the GRID_COVERAGE key-value record. In grid mode Retailer slugs and Product IDs are used for the grid, not for storefront / PDP scraping.", "default": [], "items": { "type": "string" } }, "maxItems": { "title": "Max items", "minimum": 0, "type": "integer", "description": "Stop pushing to the dataset after this many products. 0 = unlimited.", "default": 50 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings. PDP, storefront and cross-retailer search work from any IP, but a US IP yields more accurate location defaults.", "default": { "useApifyProxy": false } } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }