{ "openapi": "3.0.1", "info": { "title": "E-commerce Product Scraper (Any Store)", "description": "E-commerce Product Scraper (Any Store) SD - E-commerce Product Scraper (Any Store) is a product data tool that extracts title, price, currency, availability, brand, SKU, GTIN, rating, reviews, images, breadcrumbs, specs and variants from any shop's product, category or search pages.", "version": "1.0", "x-build-id": "vVeaY5ADCGgQfPng9" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/neuro-scraper~e-commerce-product-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-neuro-scraper-e-commerce-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/neuro-scraper~e-commerce-product-scraper/runs": { "post": { "operationId": "runs-sync-neuro-scraper-e-commerce-product-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/neuro-scraper~e-commerce-product-scraper/run-sync": { "post": { "operationId": "run-sync-neuro-scraper-e-commerce-product-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Start URLs (product, category or search pages)", "type": "array", "description": "Pages of any online store. A product page gives one row; a category, collection, search or shop page is read page by page (the shop's own next-page link) and every product on it is scraped. The page kind is detected automatically. Example: https://books.toscrape.com/catalogue/category/books/mystery_3/index.html", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "detailsUrls": { "title": "Product detail URLs", "type": "array", "description": "Optional. URLs that are always read as single product pages (no auto-detection). Example: https://scrapeme.live/shop/Bulbasaur/", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "listingUrls": { "title": "Category listing URLs", "type": "array", "description": "Optional. URLs that are always read as product listings (category, collection, brand or search-result pages), following the shop's next-page links. Example: https://scrapeme.live/shop/", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxItems": { "title": "Max items", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum number of products to return in total. Listings are followed page after page (the shop's next-page link, or Shopify's page parameter) until this number is reached or the shop has no more pages. Example: 100", "default": 25 }, "scrapeProductDetails": { "title": "Get product details", "type": "boolean", "description": "On listing pages, open every product page for the full data (brand, SKU, GTIN, rating, description, specs, variants, breadcrumbs). Off = one row per product card of the listing (title, price, image, stock where the card shows them) - one request per listing page only, much faster.", "default": true }, "maxPagesPerListing": { "title": "Max pages per listing", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Safety limit on listing pages read per start URL (Max items is the main limit). Reaching it is logged as an error. Example: 50", "default": 100 }, "scrapeMode": { "title": "Scrape mode", "enum": [ "AUTO", "HTTP", "BROWSER" ], "type": "string", "description": "AUTO: fast HTTP requests, and a headless browser only for pages that HTTP could not read (blocked, or product data drawn by JavaScript). HTTP: never use the browser. BROWSER: load every page in the browser (slower, for shops that build pages with JavaScript). The browser only loads pages like a normal visitor - it never solves captchas.", "default": "AUTO" }, "titleSelector": { "title": "Custom title CSS selector (optional)", "type": "string", "description": "Optional CSS selector of the product title on product pages; it overrides the automatic title. Example: h1.product-title" }, "priceSelector": { "title": "Custom price CSS selector (optional)", "type": "string", "description": "Optional CSS selector of the current price on product pages; it overrides the automatic price (the number is read from the element's text or content attribute). Example: .price ins .amount" }, "includeRawMetadata": { "title": "Include raw metadata", "type": "boolean", "description": "Add a rawMetadata column with the page's schema.org product object and its OpenGraph / product meta tags, as found on the page.", "default": false }, "includeFailedUrls": { "title": "Save failed URLs as rows", "type": "boolean", "description": "Also save one row per URL that could not be read (only url, statusCode and error filled). Such rows count as results. Off = failed URLs are only named in the log and the run's status message.", "default": false }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Product pages fetched in parallel, each through its own proxy session. Keep it low for small shops. Example: 3", "default": 3 }, "requestTimeoutSecs": { "title": "Request timeout seconds", "minimum": 5, "maximum": 180, "type": "integer", "description": "Time limit for one page request. Example: 40", "default": 40 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 1, "maximum": 10, "type": "integer", "description": "A blocked or failed page (403, 429, 5xx, timeout) is retried with a new session and a new proxy IP up to this many times in total. Example: 3", "default": 3 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Residential proxy is the default (many shops block datacenter IPs). Prices, currency and stock often follow the visitor's country: pick the shop's country here to see its local prices.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }