{ "openapi": "3.0.1", "info": { "title": "Shopify Product & Price Scraper", "description": "Scrape full product catalogues from any Shopify store: variant-level prices, compare-at discounts, SKUs and live stock status. Bulk multi-store, one row per product or per SKU, with a per-store pricing summary. Built for daily price monitoring. From $0.40 / 1,000 products.", "version": "0.0", "x-build-id": "Otcq0cAsC1SHbpDqJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/eiv~shopify-product-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-eiv-shopify-product-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/eiv~shopify-product-scraper/runs": { "post": { "operationId": "runs-sync-eiv-shopify-product-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/eiv~shopify-product-scraper/run-sync": { "post": { "operationId": "run-sync-eiv-shopify-product-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": { "stores": { "title": "Shopify stores", "type": "array", "description": "Store domains or URLs, one per line — 'allbirds.com', 'https://www.grind.co.uk'. Any Shopify storefront works; the Actor reads the store's own public catalogue endpoint.", "items": { "type": "string" } }, "startUrls": { "title": "Start URLs (for chaining)", "type": "array", "description": "Alternative to Stores, for feeding output from another Actor straight into this one.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "sourceDatasetId": { "title": "Source dataset ID", "type": "string", "description": "Read store domains from an existing dataset. Pairs with a tech-stack Actor: detect which of your prospects run Shopify, then scrape their catalogues." }, "sourceDatasetField": { "title": "Source dataset field", "type": "string", "description": "Which field on the source dataset holds the store domain.", "default": "domain" }, "granularity": { "title": "Row granularity", "enum": [ "product", "variant" ], "type": "string", "description": "'product' gives one row per product with its variants nested. 'variant' gives one row per purchasable SKU, which is what price and stock monitoring needs — a sold-out size or a discounted colour is invisible in a product row that only carries a min and max. Billing counts products either way.", "default": "product" }, "maxProductsPerStore": { "title": "Max products per store", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Hard cap per store. Large catalogues run to many thousands of products, so this protects you from an unexpected bill. Records flag truncated:true when a catalogue exceeded the cap.", "default": 1000 }, "includeDescriptions": { "title": "Include full HTML descriptions", "type": "boolean", "description": "Store each product's full description body. Off by default because descriptions dominate dataset size; a 300-character plain-text snippet is always included. Note this does not reduce bandwidth — Shopify returns descriptions in the catalogue payload either way.", "default": false }, "includeCollections": { "title": "Include store collections", "type": "boolean", "description": "Also fetch the store's public collection list and attach the names to the store summary. One extra request per store.", "default": false }, "includeStoreSummary": { "title": "Include per-store summary", "type": "boolean", "description": "Add one rollup record per store (recordType: store-summary) with price range, average price, discount rate, out-of-stock count, top vendors and product types. Not billed as a product.", "default": true }, "onSaleOnly": { "title": "Discounted products only", "type": "boolean", "description": "Keep only products where at least one variant is priced below its compare-at price.", "default": false }, "inStockOnly": { "title": "In-stock products only", "type": "boolean", "description": "Keep only products with at least one purchasable variant.", "default": false }, "excludeHidden": { "title": "Exclude storefront-hidden products", "type": "boolean", "description": "Drop products the store tags 'hidden' or 'hidden_product' to keep them off its storefront — influencer exclusives, deal-site bundles, spare parts. They sit in the catalogue feed but no shopper can browse to them, and they can be a third of what a store returns. Every record carries isHidden either way.", "default": false }, "minPrice": { "title": "Minimum price", "minimum": 0, "type": "integer", "description": "Keep products whose highest variant price is at least this. In the store's own currency. 0 disables.", "default": 0 }, "maxPrice": { "title": "Maximum price", "minimum": 0, "type": "integer", "description": "Keep products whose lowest variant price is at most this. In the store's own currency. 0 disables.", "default": 0 }, "titleKeywords": { "title": "Title keywords", "type": "array", "description": "Keep only products whose title contains any of these (case-insensitive).", "items": { "type": "string" } }, "vendors": { "title": "Vendors", "type": "array", "description": "Keep only products from these vendors (exact, case-insensitive).", "items": { "type": "string" } }, "productTypes": { "title": "Product types", "type": "array", "description": "Keep only these Shopify product types (exact, case-insensitive).", "items": { "type": "string" } }, "addedWithinDays": { "title": "Added within (days)", "minimum": 0, "maximum": 3650, "type": "integer", "description": "Keep only products created in the last N days — the new-arrivals feed. Uses created_at rather than published_at, because stores that republish their catalogue would otherwise report every product as new. 0 keeps everything.", "default": 0 }, "maxConcurrency": { "title": "Concurrency", "minimum": 1, "maximum": 100, "type": "integer", "description": "Stores processed in parallel. Catalogue pages can be several megabytes, so raise memory alongside this.", "default": 10 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 3, "maximum": 180, "type": "integer", "description": "Per-request timeout. Large catalogue pages are slow to serialise, so this is generous by default.", "default": 60 }, "maxRetries": { "title": "Retries per request", "minimum": 0, "maximum": 5, "type": "integer", "description": "Retries for connection resets and 5xx responses. A 403 is not retried, because a store that blocks its catalogue endpoint keeps blocking it.", "default": 1 }, "flattenOutput": { "title": "Flatten output for CSV", "type": "boolean", "description": "Emit flat dot-notation columns with arrays joined by ' | '. Use for spreadsheets; leave off for warehouses. At variant granularity the flat shape is already close to a price table.", "default": false }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Usually unnecessary — the catalogue endpoint is public and unauthenticated. Worth enabling only if you are scraping many stores behind the same CDN and start seeing 403s.", "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 } } }, "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 } } } } } } } } } }