{ "openapi": "3.0.1", "info": { "title": "Structured Data Extractor: JSON-LD, Schema.org, Open Graph", "description": "Pull the schema.org JSON-LD, Microdata, RDFa and Open Graph of any page list into flat rows: types, product price, availability, ratings, organization, breadcrumbs, with validation issues. robots.txt obeyed, no personal data, pay per page.", "version": "1.0", "x-build-id": "CFkuwh4iwDhPlttbv" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/rowcraft~structured-data-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-rowcraft-structured-data-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/rowcraft~structured-data-extractor/runs": { "post": { "operationId": "runs-sync-rowcraft-structured-data-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/rowcraft~structured-data-extractor/run-sync": { "post": { "operationId": "run-sync-rowcraft-structured-data-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Pages or websites", "type": "array", "description": "Page addresses (https://example.com/product/blue-shoe) or domains (example.com), one per line. Each one is read as the page it points to; a domain means its home page. Duplicates and invalid entries are skipped and never charged.", "items": { "type": "string" } }, "crawlSameSite": { "title": "Add more pages of the same site", "type": "boolean", "description": "Off (default): only the pages you list are read. On: the sitemap listed in robots.txt and the internal links of each page are used to find more pages of the same site (robots.txt obeyed), up to the page limit below.", "default": false }, "maxPagesPerSite": { "title": "Maximum pages per site", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Only used when Add more pages of the same site is on: the most pages read per site, counting the pages you listed. Links with a query string (?...) and files such as PDFs and images are not followed.", "default": 20 }, "onlyPagesWithData": { "title": "Deliver only pages that have structured data", "type": "boolean", "description": "Off (default): every page that was read is delivered, with validation issues such as no_structured_data. On: pages without any JSON-LD, Microdata or RDFa are left out and not charged. Useful together with the site option above.", "default": false }, "includeRawJsonLd": { "title": "Include the raw JSON-LD", "type": "boolean", "description": "Off (default): rows hold the flat fields only. On: each row also holds the cleaned JSON-LD of the page in rawJsonLd (people reduced to their type, no telephone or e-mail), up to 200,000 characters per page.", "default": false }, "maxItems": { "title": "Maximum pages delivered", "minimum": 0, "type": "integer", "description": "Stop after this many pages are delivered. 0 = no limit (the list and the page limit decide).", "default": 0 }, "onlyNew": { "title": "Only new rows since the last run", "type": "boolean", "description": "Remember the rows already delivered to you (in a key-value store in your Apify account) and deliver only rows that appeared since the last run with the same state key. The first run delivers everything that matches; later runs cost only the new rows. Ideal for schedules.", "default": false }, "stateName": { "title": "State name", "type": "string", "description": "Name of the memory used by \"Only new rows\". Use a different name for each schedule or search (for example `stockholm-python`) so they do not share one memory.", "default": "default" }, "notifyUrl": { "title": "Notify this URL when the run ends", "type": "string", "description": "A webhook address that receives one JSON POST with the number of new rows and links to the dataset: a Slack or Discord incoming webhook, a Make, n8n or Zapier catch hook, or your own endpoint. The message is also in the `text` (Slack) and `content` (Discord) fields." }, "notifyWhenEmpty": { "title": "Notify also when there are no new rows", "type": "boolean", "description": "By default the notification is sent only when at least one row was delivered.", "default": false }, "requestIntervalMs": { "title": "Delay between requests (ms)", "minimum": 250, "maximum": 10000, "type": "integer", "description": "Default 1000 ms (one request per second). Each page takes two requests: robots.txt (once per site) and the page, plus redirects and sitemap files. A Crawl-delay in a site's robots.txt is obeyed when it is longer. Minimum 250.", "default": 1000 } } }, "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 } } } } } } } } } }