{ "openapi": "3.0.1", "info": { "title": "Products Shop Crawler", "description": "It discovers product pages from start URLs and/or sitemaps, follows internal links intelligently, and extracts structured data such as product name, description, price, currency, SKU, images, availability, and page metadata.", "version": "0.0", "x-build-id": "97U5Ld0bLH8fGWEgT" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/emt_getdataforu~products-shop-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-emt_getdataforu-products-shop-crawler", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/emt_getdataforu~products-shop-crawler/runs": { "post": { "operationId": "runs-sync-emt_getdataforu-products-shop-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/emt_getdataforu~products-shop-crawler/run-sync": { "post": { "operationId": "run-sync-emt_getdataforu-products-shop-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "type": "array", "description": "Homepage, category, or collection URLs to start from. Leave empty if you only use sitemap URLs below. Note: regular webpage URLs should usually go here, not in the sitemap field.\n\n**Examples by platform (replace with your own URLs):**\n- Shopify: `https://thewolf.vn/collections/giay-da-nam` (auto-reads `var meta` inline JSON for variants, prices, gallery)\n- WooCommerce: `https://teeworld.vn/shop/` (DOM + `.woocommerce-Price-amount` fallback)\n- Haravan: `https://juno.vn/collections/all` (auto-reads `window.product` / `Haravan.product`)\n- Sapo / Bizweb: `https://your-sapo-shop.com/collections/all` (auto-reads `Sapo.product`)\n- Magento: `https://your-magento-shop.com/` (microdata + `form#product_addtocart_form` fallback)\n- Custom VN (cellphones, dienmayxanh, fptshop…): often work via JSON-LD `Product`", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "productSitemapUrls": { "title": "Product sitemap URLs (recommended for Shopify / Haravan)", "minItems": 0, "type": "array", "description": "One XML sitemap URL per line. Prefer `/sitemap.xml` (index sitemap). Nested indexes and `.gz` are supported.\n\n**Examples by platform:**\n- Shopify: `https://thewolf.vn/sitemap.xml` (index → `sitemap_products_*.xml`)\n- Haravan: `https://juno.vn/sitemap.xml`\n- WooCommerce (Yoast / Rank Math): `https://teeworld.vn/product-sitemap.xml` or `https://teeworld.vn/sitemap_index.xml`\n- Sapo: `https://your-sapo-shop.com/sitemap.xml`\n- Magento: `https://your-magento-shop.com/pub/sitemap.xml`\n\nFor Shopify, use the index sitemap instead of shortened `sitemap_products_*.xml` URLs.", "items": { "type": "string" } }, "onlyFollowProductSitemapsFromIndex": { "title": "Only follow product sitemap branches from index", "type": "boolean", "description": "When enabled, index sitemap parsing follows only child sitemap URLs containing `sitemap_products`. Useful for Shopify stores to skip pages/blog/collections branches.", "default": true }, "maxRequestsPerCrawl": { "title": "Max requests per crawl", "minimum": 1, "maximum": 99999999, "type": "integer", "description": "Total page requests allowed in a run (including discovered links). Homepages often contain many navigation links; low values can hit enqueue limits before reaching enough product pages.", "default": 3000 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Number of parallel requests. Higher values are faster but increase blocking risk.", "default": 10 }, "maxProduct": { "title": "Max products to store", "minimum": 0, "maximum": 10000000, "type": "integer", "description": "Maximum product records pushed to dataset. `0` means unlimited. Once reached, the Actor stops storing new products, stops deep link expansion, and gracefully stops the crawler run.", "default": 0 }, "maxUrlsFromSitemaps": { "title": "Max URLs collected from sitemaps", "minimum": 1, "maximum": 5000000, "type": "integer", "description": "Upper bound for URLs extracted from sitemap XML to prevent excessive memory usage on very large sitemap sets.", "default": 100000 }, "followInternalLinks": { "title": "Follow internal links", "type": "boolean", "description": "If disabled, crawl only seed URLs (start URLs + sitemap URLs). If enabled, discover additional links within the same subdomain.", "default": true }, "maxDepth": { "title": "Max link depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "How many link hops from seed URLs are allowed. `0` means no expansion.", "default": 5 }, "saveNonProductPages": { "title": "Store non-product pages", "type": "boolean", "description": "When disabled (default), only product-like pages are stored. Enable for debugging or broader page analysis.", "default": false }, "excludeNavigationNoisePaths": { "title": "Exclude non-commerce navigation paths", "type": "boolean", "description": "Exclude common non-shopping paths (blog, support, account, contact, etc.) from discovered links to preserve request budget for product/category pages.", "default": true }, "smartFollowPatterns": { "title": "Use smart commerce URL patterns", "type": "boolean", "description": "Prioritize URL patterns commonly used by e-commerce platforms (e.g. `/product/`, `/products/`, `/collections/`, `/category/`) to improve product discovery.", "default": true }, "followIncludeGlobs": { "title": "Additional include URL globs", "type": "array", "description": "Advanced: add extra glob patterns for URLs that should be considered for enqueueing. Leave empty to use default smart patterns.", "items": { "type": "object", "required": [ "glob" ], "properties": { "glob": { "type": "string", "title": "Glob of a web page" } } } }, "followExcludeRegex": { "title": "Additional exclude regex for discovered links", "pattern": "^[^\\n\\r]{0,500}$", "type": "string", "description": "Advanced: URLs matching this regex are skipped during enqueue (in addition to built-in excludes)." }, "stripTrackingQueryParams": { "title": "Strip tracking query params", "type": "boolean", "description": "Remove common tracking query params (`utm_*`, `fbclid`, `gclid`, etc.) before enqueueing to reduce duplicate URLs.", "default": true }, "dropCommonFilterQueryParams": { "title": "Drop common filter/sort query params", "type": "boolean", "description": "Remove common faceted-navigation params (`filter_*`, `sort`, `orderby`, `view`, `variant`, etc.) before enqueueing to avoid URL explosion.", "default": true }, "sitemapFetchDelayMs": { "title": "Delay between sitemap requests (ms)", "minimum": 0, "maximum": 60000, "type": "integer", "description": "Delay between sitemap fetches. Useful for hosts sensitive to request bursts.", "default": 0 }, "productUrlRegex": { "title": "Product URL regex filter", "pattern": "^[^\\n\\r]{0,500}$", "type": "string", "description": "Optional regex to keep only matching page URLs from sitemap urlsets (not index files). Leave empty to disable." } } }, "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 } } } } } } } } } }