{ "openapi": "3.0.1", "info": { "title": "Shopify Store Products & Prices Scraper", "description": "Extract the public product catalogue of any Shopify store: every product and variant with price, compare-at price, SKU, availability, vendor, type, tags, images and dates. Monitor many stores and emit only price changes. One row per variant, $0.30 per 1,000.", "version": "0.1", "x-build-id": "HIKd6PmggyCu2O04j" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/hridayrungta~shopify-products-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-hridayrungta-shopify-products-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/hridayrungta~shopify-products-scraper/runs": { "post": { "operationId": "runs-sync-hridayrungta-shopify-products-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/hridayrungta~shopify-products-scraper/run-sync": { "post": { "operationId": "run-sync-hridayrungta-shopify-products-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": [ "storeUrls" ], "properties": { "storeUrls": { "title": "Store URLs", "type": "array", "description": "Shopify storefronts to scrape, one per line: a domain (`example-store.com`), a homepage URL or a `*.myshopify.com` address. Any path or query string is ignored. Non-Shopify sites are detected and skipped.", "items": { "type": "string" } }, "collectionHandles": { "title": "Collection handles (optional)", "type": "array", "description": "Only scrape these collections, e.g. `sale`, `new-arrivals` or a full `/collections/mens` URL. Applies to every store. Leave empty to scrape the whole catalogue via `/products.json`.", "items": { "type": "string" } }, "outputMode": { "title": "Output mode", "enum": [ "all", "newOnly", "priceChangesOnly" ], "type": "string", "description": "`all`: every variant every run. `newOnly`: only variants not seen in an earlier run. `priceChangesOnly`: new variants plus variants whose price or compare-at price changed since the last run (rows carry `priceChange {old,new}`). Change modes keep one snapshot per store in the key-value store named below; the first run saves a baseline and emits nothing unless **Emit everything on first run** is on.", "default": "all" }, "maxProductsPerStore": { "title": "Max products per store", "minimum": 1, "maximum": 25000, "type": "integer", "description": "Stop paging a store after this many products (each product can have many variants). Shopify's public feed itself stops at page 100 = 25,000 products.", "default": 5000 }, "maxItems": { "title": "Max rows (all stores)", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Hard cap on saved rows across all stores. This is also your cost cap: you are billed once per saved row.", "default": 10000 }, "includeVariants": { "title": "One row per variant", "type": "boolean", "description": "On (default): one row per variant with `variantId`, `variantTitle`, `sku`, `price`. Off: one row per product using its cheapest variant's price, plus `variantCount`.", "default": true }, "includeImages": { "title": "Include all image URLs", "type": "boolean", "description": "Add `images[]` with every product image URL. `imageUrl` (the variant's or product's main image) is always included.", "default": false }, "includeBodyHtml": { "title": "Include description", "type": "boolean", "description": "Add `bodyHtml` (raw HTML) and `description` (plain text). Off by default to keep rows small.", "default": false }, "emitAllOnFirstRun": { "title": "Emit everything on first run", "type": "boolean", "description": "In `newOnly` / `priceChangesOnly` mode, also output the full catalogue when a store has no snapshot yet (every row gets `changeType: \"new\"`). Off: the first run only saves the baseline.", "default": false }, "snapshotStoreName": { "title": "Snapshot key-value store", "type": "string", "description": "Name of the named key-value store that holds the last-seen prices per store domain (created if missing). Use different names to keep independent watch-lists.", "default": "shopify-products-snapshots" }, "requestsPerSecond": { "title": "Requests per second (per store)", "minimum": 1, "maximum": 5, "type": "integer", "description": "Throttle per storefront (1-5). Shopify answers 429/430 to aggressive clients; 2 is safe for virtually every store.", "default": 2 }, "storeConcurrency": { "title": "Stores in parallel", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many stores to scrape at the same time (each with its own throttle).", "default": 3 }, "maxRetries": { "title": "Max retries per request", "minimum": 0, "maximum": 10, "type": "integer", "description": "Retries with exponential backoff (honouring Retry-After) for network errors, 5xx, 403, 429 and 430 responses.", "default": 4 }, "allowHtmlFallback": { "title": "Allow HTML fallback", "type": "boolean", "description": "When a store has disabled `/products.json`, read product handles from its sitemap and, failing that, from `/collections/all` pages, then fetch each product's `.js` feed. Costs one request per product.", "default": true }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. The product feed is public and works without a proxy for most stores; enable Apify Proxy if a store answers 429/430 or 403.", "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 } } } } } } } } } }