{ "openapi": "3.0.1", "info": { "title": "Shopify Product Scraper — GTIN & Collections", "description": "Scrape every product and variant from any Shopify store, with the GTIN barcodes, subscription plans and wholesale price breaks that /products.json does not contain.", "version": "1.0", "x-build-id": "7e80PXm3cYwEcKWEQ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/spool~shopify-product-feed/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-spool-shopify-product-feed", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/spool~shopify-product-feed/runs": { "post": { "operationId": "runs-sync-spool-shopify-product-feed", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/spool~shopify-product-feed/run-sync": { "post": { "operationId": "run-sync-spool-shopify-product-feed", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "storeUrls" ], "properties": { "storeUrls": { "title": "1. Shopify stores", "type": "array", "description": "Domains, full URLs or product links — mixed freely. `www.` is stripped, and `www.x.com` and `x.com` are merged so one store is never read twice.\n\nAbout five stores in six serve a public catalog. A store that does not is reported as `not_a_shopify_store` rather than silently skipped.", "items": { "type": "string" } }, "enrich": { "title": "2. Read barcodes, subscriptions and wholesale pricing", "type": "boolean", "description": "**This is the reason to use this Actor.** `/products.json`, which every other Shopify scraper reads, does not contain the GTIN/UPC barcode, subscription plans, wholesale price breaks or whether stock is even tracked.\n\nThose live on a second endpoint, one request per product. Measured across eight stores, barcodes came back on **97-100% of variants for six of them**, 81% on Rothy's and 26% on Death Wish Coffee.\n\nTurn this off for a fast, cheap catalog dump with no barcodes.", "default": true }, "rowsPer": { "title": "3. One row per…", "enum": [ "variant", "product" ], "type": "string", "description": "**Variant** gives one row per buyable SKU, each with its own barcode, price and stock. This is the shape a price monitor or a Google Merchant feed needs.\n\n**Product** gives one row per product with the variants nested, which is easier for catalog analysis.", "default": "variant" }, "maxProductsPerStore": { "title": "How many products per store", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Shopify serves 250 products per request, newest-published first.\n\nWith enrichment on, each product costs one extra request, so this is also the main lever on run time and price.", "default": 1000 }, "collectionsMode": { "title": "Collection membership", "enum": [ "key", "all", "none" ], "type": "string", "description": "Which of the merchant's own collections to map each product against. A product sitting in the store's `best-sellers` collection is a demand signal the merchant is publishing themselves.\n\n**Signal collections** reads only the ones that mean something — best sellers, sale, clearance, new arrivals, trending. Rothy's publishes 196 collections; reading all of them would cost hundreds of requests to learn mostly colour and size groupings.", "default": "key" }, "requireBarcode": { "title": "Only products with a GTIN barcode", "type": "boolean", "description": "Keep only rows carrying a barcode. Use this when you are building a Google Merchant Center feed or matching against Amazon, where a row without a GTIN is unusable.\n\nNeeds enrichment on.", "default": false }, "onlyInStock": { "title": "Only what is in stock", "type": "boolean", "description": "Keep only available variants. Note that `available` is only meaningful when the merchant tracks inventory — `inventoryTracked` in the output says whether they do.", "default": false }, "onlyOnSale": { "title": "Only discounted items", "type": "boolean", "description": "Keep only variants whose price is below their compare-at price. `discountPercent` carries the depth.", "default": false }, "requireSubscription": { "title": "Only subscription products", "type": "boolean", "description": "Keep only products offering a subscription or subscribe-and-save plan, with the real subscriber price and discount. Needs enrichment on.", "default": false }, "minPrice": { "title": "Minimum price (USD)", "type": "integer", "description": "Compared against the USD price, so it means the same thing on a GBP store as on a USD one." }, "maxPrice": { "title": "Maximum price (USD)", "type": "integer", "description": "Compared against the USD price." }, "vendors": { "title": "Only these vendors", "type": "array", "description": "Brand names as they appear in the store. Useful on multi-brand retailers — Kith stocks 138 vendors.", "items": { "type": "string" } }, "productTypes": { "title": "Only these product types", "type": "array", "description": "The store's own product types, such as `Socks` or `Men's Jackets`.", "items": { "type": "string" } }, "tags": { "title": "Only these tags", "type": "array", "description": "Keeps a product carrying any one of these tags.", "items": { "type": "string" } }, "includeDescription": { "title": "Include the product description", "type": "boolean", "description": "Adds the full description to every row. Off by default because it is large and most uses do not need it.", "default": false }, "maxConcurrency": { "title": "Parallel requests per store", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many per-product requests run at once. Shopify throttles by address rather than by rate — the built-in Apify Proxy fallback handles that — so this mostly trades speed for politeness.", "default": 5 } } }, "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 } } } } } } } } } }