{ "openapi": "3.0.1", "info": { "title": "Product Page Scraper – Price, Stock & GTIN from Any Store", "description": "Extract price, currency, stock, SKU, GTIN, brand, rating, images and variants from any online store's product URLs (Shopify, WooCommerce, Magento, BigCommerce, custom). Monitor mode reports price and stock changes. HTTP only, robots.txt respected, $0.001 per product.", "version": "0.1", "x-build-id": "pGBl4uKfj8hifTp0m" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gazidev~product-page-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gazidev-product-page-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/gazidev~product-page-extractor/runs": { "post": { "operationId": "runs-sync-gazidev-product-page-extractor", "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/gazidev~product-page-extractor/run-sync": { "post": { "operationId": "run-sync-gazidev-product-page-extractor", "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": { "productUrls": { "title": "Product page URLs", "type": "array", "description": "Product pages from any online store (Shopify, WooCommerce, Magento, BigCommerce, PrestaShop, Shopware, Wix, Squarespace, custom). One URL per line. Big marketplaces whose terms forbid scraping (Amazon, Walmart, eBay, Etsy, Target, AliExpress, Temu, Shein...) are refused for free.", "items": { "type": "string" } }, "sitemapUrls": { "title": "Or: product sitemaps", "type": "array", "description": "Optional sitemap URLs (e.g. `https://store.com/sitemap_products_1.xml` or `https://store.com/sitemap.xml`). Product-like URLs (matching the pattern below) are taken from them, up to Max products.", "items": { "type": "string" } }, "urlPattern": { "title": "Product URL pattern (for sitemaps)", "type": "string", "description": "Regular expression that selects product URLs from the sitemaps. Default: `/products?/`, `/p/`, `/item/`, `/shop//`." }, "datasetId": { "title": "Or: dataset ID with URLs", "type": "string", "description": "Read product URLs from an Apify dataset (e.g. the output of another scraper)." }, "datasetUrlField": { "title": "Dataset URL field", "type": "string", "description": "Field of the dataset items that holds the product URL.", "default": "url" }, "includeVariants": { "title": "Include variants", "type": "boolean", "description": "List variants (size, colour...) with SKU, GTIN, price and availability. On Shopify and WooCommerce this uses the store's public product JSON (one extra request per product, no extra charge).", "default": true }, "includeDescription": { "title": "Include description", "type": "boolean", "description": "Add the product description text (up to 5,000 characters).", "default": true }, "monitor": { "title": "Monitor mode (price & stock changes)", "type": "boolean", "description": "Keep a snapshot between runs and add previousPrice, priceChange, priceChangePercent and availabilityChanged. Schedule the Actor (e.g. daily) with the same Monitor key.", "default": false }, "onlyChanges": { "title": "Monitor: output only changed products", "type": "boolean", "description": "In monitor mode, write only new and changed products to the dataset (every checked product is still charged as a product).", "default": true }, "monitorKey": { "title": "Monitor key", "type": "string", "description": "Name of the snapshot. Use different keys for different product lists.", "default": "default" }, "maxItems": { "title": "Max products", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum number of product URLs to process in this run.", "default": 100 }, "maxConcurrency": { "title": "Stores in parallel", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many different stores are fetched at the same time. Each store always gets one request at a time.", "default": 10 }, "minDelayMillis": { "title": "Delay between requests to the same store (ms)", "minimum": 250, "maximum": 30000, "type": "integer", "description": "Politeness delay per store. A larger robots.txt Crawl-delay is always respected.", "default": 1000 }, "requestTimeoutSecs": { "title": "Request timeout (s)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeout of one HTTP request.", "default": 30 }, "maxRetries": { "title": "Retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Retries for network errors, HTTP 429 and 5xx.", "default": 2 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. Not needed for most stores. Stores that block automated requests are reported with status `blocked` and not charged.", "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 } } } } } } } } } }