{ "openapi": "3.0.1", "info": { "title": "Product Page Extractor: Price, Stock, GTIN & Variants from Any ", "description": "Extract product data from any online store: price, currency, sale/list price, stock status, brand, SKU, GTIN/EAN/UPC, MPN, images, rating, reviews and every variant. Paste product URLs or discover a store's catalog from its sitemap. Built-in price monitor flags price drops. $3 per 1,000 products.", "version": "0.1", "x-build-id": "oZxUBwEyMXveA5mGC" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/larkmoor~product-page-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-larkmoor-product-page-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/larkmoor~product-page-extractor/runs": { "post": { "operationId": "runs-sync-larkmoor-product-page-extractor", "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/larkmoor~product-page-extractor/run-sync": { "post": { "operationId": "run-sync-larkmoor-product-page-extractor", "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": { "productUrls": { "title": "Product URLs", "type": "array", "description": "Product pages to extract, one per line. Each page with a product gives one row (variants are listed inside it).", "items": { "type": "string" } }, "discoverFrom": { "title": "Discover products from", "type": "array", "description": "Store homepages (the store's sitemap is read), product sitemaps (sitemap_products_1.xml, product-sitemap.xml, .xml.gz) or category/collection pages. The actor finds the product links there and extracts them.", "items": { "type": "string" } }, "maxProductsPerSite": { "title": "Max products per site", "minimum": 1, "maximum": 10000, "type": "integer", "description": "How many products to take from each discovery source / store.", "default": 100 }, "maxProducts": { "title": "Max products in total", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Hard cap on products extracted (and charged) in this run.", "default": 1000 }, "monitorName": { "title": "Price monitor name (optional)", "type": "string", "description": "Give a name (e.g. 'competitor-shoes') to remember each product's price and stock in a named key-value store on your account. Every later run with the same name adds previousPrice, change (new / price_down / price_up / availability / none), priceChange and priceChangePercent. Schedule the run daily for a price tracker." }, "onlyChanges": { "title": "Output only changed products", "type": "boolean", "description": "With a price monitor name: leave unchanged products out of the dataset (and out of the bill). The first run outputs everything as 'new'.", "default": false }, "includeVariants": { "title": "Include variants", "type": "boolean", "description": "List every variant (size, color...) with its own SKU, GTIN, price and stock status inside the product row.", "default": true }, "descriptionMaxChars": { "title": "Description length", "minimum": 0, "maximum": 20000, "type": "integer", "description": "Characters of product description to keep (0 = leave the description out).", "default": 500 }, "maxImages": { "title": "Images per product", "minimum": 0, "maximum": 100, "type": "integer", "description": "How many image URLs to keep in 'images' (0 = only the main image).", "default": 10 }, "includeRawSchema": { "title": "Include raw schema.org data", "type": "boolean", "description": "Add the page's full schema.org Product object as 'rawSchema' (for fields not mapped to columns).", "default": false }, "skipFailed": { "title": "Skip pages without a product", "type": "boolean", "description": "Leave pages without product data out of the dataset (they are never charged either way).", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages the site's robots.txt disallows (recommended).", "default": true }, "concurrency": { "title": "Parallel pages", "minimum": 1, "maximum": 10, "type": "integer", "description": "Pages fetched at the same time (1-10). Keep it low for small stores.", "default": 5 }, "useResidentialProxy": { "title": "Residential proxy for blocked stores", "type": "boolean", "description": "Some large stores block datacenter IPs (HTTP 403/429). Turn this on to retry those pages through Apify residential proxy (billed by Apify per GB of proxy traffic on your account; most stores do not need it).", "default": 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 }, "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 } } } } } } } } } }