{ "openapi": "3.0.1", "info": { "title": "E-commerce Website Scraping Tool", "description": "Scrape public e-commerce pages for product names, prices, stock status, reviews, sellers, and price changes. Use URLs or keywords, export clean data, and keep runs cheap with low-cost defaults.", "version": "0.1", "x-build-id": "DKQnfEPA422I3tTw1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/qaseemiqbal~e-commerce-website-scraping-tool/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-qaseemiqbal-e-commerce-website-scraping-tool", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/qaseemiqbal~e-commerce-website-scraping-tool/runs": { "post": { "operationId": "runs-sync-qaseemiqbal-e-commerce-website-scraping-tool", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/qaseemiqbal~e-commerce-website-scraping-tool/run-sync": { "post": { "operationId": "run-sync-qaseemiqbal-e-commerce-website-scraping-tool", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "operation" ], "properties": { "operation": { "title": "Operation", "enum": [ "PRODUCTS", "REVIEWS", "SELLERS", "DISCOVERY", "FOOD_DELIVERY", "INFLUENCER", "PRICE_MONITOR" ], "type": "string", "description": "Select which commerce records to extract.", "default": "PRODUCTS" }, "costPreset": { "title": "Cost preset", "enum": [ "LOWEST_COST", "BALANCED", "FULL_COVERAGE" ], "type": "string", "description": "Controls defaults for speed, reliability, and cost. Lowest cost avoids browser fallback and paid proxy traffic unless explicitly enabled.", "default": "LOWEST_COST" }, "scrapeMode": { "title": "Scrape mode", "enum": [ "AUTO", "HTTP", "BROWSER" ], "type": "string", "description": "HTTP is cheapest. AUTO can use browser fallback only when browser fallback is enabled. BROWSER is most expensive.", "default": "HTTP" }, "allowBrowserFallback": { "title": "Allow browser fallback", "type": "boolean", "description": "Allow AUTO mode to retry low-confidence pages with Playwright. Keep disabled for the lowest compute cost.", "default": false }, "maxBrowserFallbackPages": { "title": "Maximum browser fallback pages", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Hard cap for expensive browser fallback pages in AUTO mode.", "default": 0 }, "startUrls": { "title": "Start URLs", "type": "array", "description": "Product, listing, review, seller, food-delivery, or storefront URLs.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL", "description": "Public commerce page URL to crawl." } } }, "default": [] }, "keywords": { "title": "Keywords", "type": "array", "description": "Search terms used for discovery or keyword-based product/review/seller workflows.", "items": { "type": "string" }, "default": [] }, "searchDomains": { "title": "Search domains", "type": "array", "description": "Optional domain restrictions for keyword discovery.", "items": { "type": "string" }, "default": [] }, "countryCode": { "title": "Country code", "type": "string", "description": "ISO country code used for localization and proxy country hints.", "default": "US" }, "locale": { "title": "Locale", "type": "string", "description": "Preferred content locale, such as en-US.", "default": "en-US" }, "currency": { "title": "Preferred currency", "type": "string", "description": "Optional ISO currency code used when a page omits currency.", "default": "" }, "deliveryLocation": { "title": "Delivery location", "type": "string", "description": "Address, ZIP, city, or region for location-sensitive food-delivery scraping.", "default": "" }, "maxItems": { "title": "Maximum records", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Global hard cap for pushed dataset records.", "default": 25 }, "maxSearchResults": { "title": "Maximum search results", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum candidate product URLs to collect from each keyword or search/listing source.", "default": 10 }, "maxReviewsPerProduct": { "title": "Maximum reviews per product", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of review rows to extract for each product or review page.", "default": 50 }, "maxSellersPerProduct": { "title": "Maximum sellers per product", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum number of seller or offer rows to extract for each product page.", "default": 5 }, "maxConcurrency": { "title": "Maximum concurrency", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum number of pages processed in parallel.", "default": 3 }, "maxRequestsPerRun": { "title": "Maximum requests per run", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Hard cap for total crawled pages. Prevents runaway queue growth and unexpected compute cost.", "default": 100 }, "requestRetries": { "title": "Request retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "Retry count for failed pages. Lower values reduce compute and proxy traffic.", "default": 1 }, "requestTimeoutSecs": { "title": "Request timeout seconds", "minimum": 5, "maximum": 300, "type": "integer", "description": "Timeout for each page request. Shorter timeouts reduce long-running failed requests.", "default": 30 }, "includeVariants": { "title": "Include variants", "type": "boolean", "description": "Include visible product variant information when available.", "default": true }, "includeSellers": { "title": "Include sellers/offers", "type": "boolean", "description": "Also extract visible seller and offer information during product runs.", "default": false }, "includeReviewMedia": { "title": "Include review media", "type": "boolean", "description": "Include image or video URLs attached to reviews when available.", "default": false }, "enrichDiscoveredProducts": { "title": "Enrich discovered products", "type": "boolean", "description": "When true, DISCOVERY enqueues discovered product URLs for product extraction. Disable to avoid extra requests.", "default": false }, "previousDatasetId": { "title": "Previous dataset ID", "type": "string", "description": "Optional dataset used by PRICE_MONITOR to emit price_change records.", "default": "" }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify proxy configuration. Leave disabled for the lowest cost; enable only for sites that block direct requests.", "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 } } }, "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 } } } } } } } } } }