{ "openapi": "3.0.1", "info": { "title": "Ecommerce Product Data Extraction API - Price, Stock, GTIN", "description": "Extract ecommerce product data from any product, category or search page URL: name, price, regular price, currency, availability, SKU, MPN, GTIN, brand, rating, images and breadcrumbs, plus every product on a listing page and category navigation links. Uses your own Zyte API key.", "version": "0.1", "x-build-id": "joKz2ySyF2TLC0E7C" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/nabeelbaghoor~ecommerce-product-extraction-api/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-nabeelbaghoor-ecommerce-product-extraction-api", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/nabeelbaghoor~ecommerce-product-extraction-api/runs": { "post": { "operationId": "runs-sync-nabeelbaghoor-ecommerce-product-extraction-api", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/nabeelbaghoor~ecommerce-product-extraction-api/run-sync": { "post": { "operationId": "run-sync-nabeelbaghoor-ecommerce-product-extraction-api", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "extractionType": { "title": "What to extract", "enum": [ "product", "productList", "productNavigation" ], "type": "string", "description": "One extraction type per run. Product details reads one product from each product page URL. Product list reads every product shown on a category or search results page, with its price and image. Product navigation reads the product links, subcategory links and next page link of a category page, for building a crawl.", "default": "product" }, "urls": { "title": "Page URLs", "type": "array", "description": "One page URL per line, absolute and starting with https://. The host must be a domain name, not an IP address. Use product page URLs for product details, and category or search result page URLs for product list and product navigation.", "items": { "type": "string" } }, "extractFrom": { "title": "Extraction source", "enum": [ "auto", "httpResponseBody", "browserHtml" ], "type": "string", "description": "Where Zyte API reads the page from. Automatic lets the provider choose, which is currently a rendered browser page for this kind of extraction. Raw HTTP response is usually faster and cheaper at the provider. Rendered browser page usually gives better results on JavaScript-heavy stores.", "default": "auto" }, "geolocation": { "title": "Country to fetch from", "type": "string", "description": "Optional two-letter ISO 3166-1 country code, such as US, GB or DE, for the country the page should be requested from. Stores often show a different price, currency or stock level by country. Leave blank to let the provider choose." }, "ipType": { "title": "IP type", "enum": [ "auto", "datacenter", "residential" ], "type": "string", "description": "Whether the provider fetches from a datacenter or a residential IP address. Leave on automatic unless you have a reason: the provider picks the type that avoids bans on each website.", "default": "auto" }, "productModel": { "title": "Product model version", "enum": [ "auto", "2024-09-16", "2024-02-01" ], "type": "string", "description": "Pin the provider's product extraction model to a dated version, so results stay comparable while a newer model rolls out. Product details only; ignored for the other types.", "default": "auto" }, "minProbability": { "title": "Minimum product probability", "minimum": 0, "maximum": 1, "type": "number", "description": "Product details only. The provider scores how likely each page is to be a single product page, from 0 to 1, and recommends 0.5 as the threshold. Pages scored below this become an uncharged row saying so instead of a product.", "default": 0.5 }, "maxPagesPerUrl": { "title": "Pages to follow per URL", "minimum": 1, "maximum": 100, "type": "integer", "description": "Product navigation only. Follow the next page link the provider finds, up to this many pages per starting URL. 1 reads only the page you gave.", "default": 1 }, "maxResults": { "title": "Maximum results", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Stop after this many rows. A single listing or category page can return dozens of rows, so this is what bounds a run over many URLs.", "default": 100 }, "requestsPerMinute": { "title": "Requests per minute", "minimum": 1, "maximum": 600, "type": "integer", "description": "Pacing ceiling for calls to Zyte API. Standard plans allow far more, but websites also have their own limits at the provider, and rate limited calls are retried with a pause rather than dropped.", "default": 60 }, "apiKey": { "title": "Zyte API key", "type": "string", "description": "Your own Zyte API key, from the API access page of your Zyte account. This actor is bring-your-own-key and never ships a key of its own. Leave blank to use the DATA_API_KEY environment secret instead." }, "baseUrl": { "title": "API base URL", "type": "string", "description": "Override the host the actor calls. Only useful for testing against a different environment." } } }, "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 } } } } } } } } } }