{ "openapi": "3.0.1", "info": { "title": "U Ecommerce Scraper", "description": "An intelligent, universal e-commerce scraper for Apify that automatically detects 6+ store systems, finds product data via sitemaps or deep crawling, and normalizes it into a clean, structured format.", "version": "0.1", "x-build-id": "EbNn5XhKsoJK0Xzmc" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/kalirobot~u-ecommerce-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-kalirobot-u-ecommerce-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/kalirobot~u-ecommerce-scraper/runs": { "post": { "operationId": "runs-sync-kalirobot-u-ecommerce-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/kalirobot~u-ecommerce-scraper/run-sync": { "post": { "operationId": "run-sync-kalirobot-u-ecommerce-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "List of URLs where the crawl should start.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxCrawlDepth": { "title": "Max Crawl Depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "Maximum depth for crawling from the start URLs (0 = only start URLs, 1 = start URLs + 1 level, etc.).", "default": 3 }, "maxCrawlPages": { "title": "Max Pages to Crawl", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of pages to crawl.", "default": 100 }, "maxProducts": { "title": "Max Products to Extract", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum number of products to extract (leave empty for unlimited)." }, "detectShopPlatform": { "title": "Auto-detect Shop Platform", "type": "boolean", "description": "Automatically detect platforms like Magento, Shopify, WooCommerce, etc.", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Ethical Crawling: Obeys robots.txt disallow rules and crawl delays. Recommended for legal/ethical operation.", "default": false }, "identifyAsBot": { "title": "Identify as a Bot", "type": "boolean", "description": "Uses an identifiable User-Agent (ApifyPriceScraperBot). If false, uses a standard browser User-Agent.", "default": false }, "rotateUserAgents": { "title": "Rotate User-Agents", "type": "boolean", "description": "Uses random browser User-Agents for each request (anti-bot evasion). Overrides 'Identify as a Bot'.", "default": false }, "crawlDelay": { "title": "Crawl Delay (seconds)", "minimum": 0, "maximum": 10, "type": "number", "description": "Minimum time between requests to the same domain. 0 = no delay.", "default": 0 }, "enableDeepCrawler": { "title": "Enable Deep Crawler", "type": "boolean", "description": "⚠️ WARNING: Crawls ALL links on the site (Screaming Frog-style). Can lead to high costs! Only enable if sitemap is missing.", "default": false }, "includeUrlPatterns": { "title": "Include URL Patterns", "type": "array", "description": "Only crawl URLs that match these regex patterns (empty = all URLs).", "default": [], "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URL Patterns", "type": "array", "description": "Skip URLs that match these regex patterns.", "default": [ "\\.(pdf|jpg|jpeg|png|gif|css|js|svg|ico|woff|woff2|ttf)$" ], "items": { "type": "string" } }, "minPrice": { "title": "Minimum Price", "minimum": 0, "type": "number", "description": "Only extract products with prices above this value (optional)." }, "maxPrice": { "title": "Maximum Price", "minimum": 0, "type": "number", "description": "Only extract products with prices below this value (optional)." }, "onlyInStock": { "title": "Only In-Stock Products", "type": "boolean", "description": "Only extract products that are currently in stock.", "default": false }, "sortBy": { "title": "Sort Results By", "enum": [ "none", "name", "price_asc", "price_desc", "sku" ], "type": "string", "description": "Sort extracted products by this field.", "default": "none" }, "productType": { "title": "Product Type (WooCommerce)", "enum": [ "any", "simple", "grouped", "external", "variable" ], "type": "string", "description": "Filter by WooCommerce product type (only effective for WooCommerce stores).", "default": "any" }, "proxyConfiguration": { "title": "🌐 Proxy Configuration", "type": "object", "description": "Proxy settings for the crawler (recommended for larger stores).", "default": { "useApifyProxy": true } }, "maxConcurrency": { "title": "Max Concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Number of simultaneous HTTP requests (higher = faster, but higher risk of blocking).", "default": 1 }, "pageLoadTimeout": { "title": "Page Load Timeout", "minimum": 10, "maximum": 300, "type": "integer", "description": "Maximum time to wait for a page to load (in seconds).", "default": 60 }, "customUserAgent": { "title": "Custom User-Agent", "type": "string", "description": "Custom User-Agent string (overrides default and rotation)." }, "cookies": { "title": "🍪 HTTP Cookies", "type": "array", "description": "Custom cookies for authentication or personalization.", "default": [] }, "customHeaders": { "title": "📜 Custom HTTP Headers", "type": "object", "description": "Additional HTTP headers for all requests." }, "outputFormat": { "title": "📁 Output Format", "enum": [ "json", "csv", "xlsx" ], "type": "string", "description": "Format of the extracted data in the dataset.", "default": "json" }, "includeImages": { "title": "Include Images", "type": "boolean", "description": "Include product images in the output.", "default": true }, "includeDescription": { "title": "Include Description", "type": "boolean", "description": "Include product descriptions in the output.", "default": true }, "includeSKU": { "title": "Include SKU", "type": "boolean", "description": "Include product SKUs in the output.", "default": true }, "includeAvailability": { "title": "Include Availability", "type": "boolean", "description": "Include stock status in the output.", "default": true }, "debugMode": { "title": "🐛 Debug Mode", "type": "boolean", "description": "Enables verbose logging for debugging (shows extraction details).", "default": false }, "saveHTML": { "title": "Save HTML", "type": "boolean", "description": "Saves the HTML code of each product page in the Key-Value Store.", "default": false }, "notifyUrl": { "title": "📲 Notification URL (Ntfy/Pushover)", "type": "string", "description": "Push notification upon completion. Supports: ntfy.sh URLs or Pushover API." } } }, "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 } } } } } } } } } }