{ "openapi": "3.0.1", "info": { "title": "E-commerce Product Scraper for AI & RAG", "description": "Scrape product catalogs into clean, chunked data for AI search, RAG, embeddings, and vector databases.", "version": "1.0", "x-build-id": "1vn4cSW8j8OTugyqw" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/coolinbex~ecommerce-product-scraper-ai-rag/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-coolinbex-ecommerce-product-scraper-ai-rag", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/coolinbex~ecommerce-product-scraper-ai-rag/runs": { "post": { "operationId": "runs-sync-coolinbex-ecommerce-product-scraper-ai-rag", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/coolinbex~ecommerce-product-scraper-ai-rag/run-sync": { "post": { "operationId": "run-sync-coolinbex-ecommerce-product-scraper-ai-rag", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "minItems": 1, "type": "array", "description": "Product pages, category pages, sitemaps, or store homepages to crawl.", "items": { "type": "object", "properties": { "url": { "title": "URL", "description": "A product, catalog, collection, sitemap, or store URL to crawl.", "type": "string" } } } }, "maxItems": { "title": "Maximum products", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum number of product records to save.", "default": 100 }, "maxPages": { "title": "Maximum pages", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Safety limit for pages fetched, including category and navigation pages.", "default": 500 }, "outputFormat": { "title": "Description format", "enum": [ "Markdown", "JSON" ], "type": "string", "description": "Format used for the canonical product text and chunks.", "default": "Markdown" }, "chunkSizeTokens": { "title": "Chunk size (tokens)", "minimum": 100, "maximum": 2000, "type": "integer", "description": "Approximate maximum tokens per retrieval chunk.", "default": 400 }, "chunkOverlapTokens": { "title": "Chunk overlap (tokens)", "minimum": 0, "maximum": 500, "type": "integer", "description": "Approximate overlap between adjacent chunks.", "default": 50 }, "renderJavaScript": { "title": "Render JavaScript", "type": "boolean", "description": "Use a real browser so React, Next.js, Shopify, and other hydrated stores are parsed.", "default": true }, "followLinks": { "title": "Follow catalog links", "type": "boolean", "description": "Follow same-domain pagination, category, and product links from the supplied URLs.", "default": true }, "includeReviews": { "title": "Include reviews", "type": "boolean", "description": "Extract visible review text and aggregate ratings when available.", "default": true }, "allowedDomains": { "title": "Allowed domains", "type": "array", "description": "Optional hostname allowlist. Empty means the hostnames in startUrls are allowed.", "items": { "type": "string" }, "default": [] }, "productUrlPatterns": { "title": "Product URL patterns", "type": "array", "description": "Optional regular expressions used to identify product pages.", "items": { "type": "string" }, "default": [] }, "maxConcurrency": { "title": "Concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Number of browser tabs used concurrently.", "default": 3 }, "maxRequestRetries": { "title": "Request retries", "minimum": 0, "maximum": 20, "type": "integer", "description": "Retries per request before it is reported as failed.", "default": 5 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy settings. A fresh session is selected after blocked responses.", "properties": { "useApifyProxy": { "title": "Use Apify Proxy", "description": "Route requests through Apify Proxy.", "type": "boolean" }, "apifyProxyGroups": { "title": "Proxy groups", "description": "Optional Apify Proxy groups, such as RESIDENTIAL.", "type": "array", "items": { "type": "string" } }, "apifyProxyCountry": { "title": "Proxy country", "description": "Optional two-letter proxy country code.", "type": "string" } }, "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }