{ "openapi": "3.0.1", "info": { "title": "Recipe Extractor: Ingredients, Steps & Nutrition from Any URL", "description": "Extract structured recipes from any food blog or recipe site: name, ingredients, step-by-step instructions, prep/cook/total time, servings, nutrition, rating, cuisine, image and video. Paste recipe URLs or discover recipes from a sitemap, feed or category page. $2 per 1,000 recipes.", "version": "0.1", "x-build-id": "VoL6jUU5OxUBQtmRu" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/larkmoor~recipe-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-larkmoor-recipe-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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~recipe-extractor/runs": { "post": { "operationId": "runs-sync-larkmoor-recipe-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~recipe-extractor/run-sync": { "post": { "operationId": "run-sync-larkmoor-recipe-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": { "recipeUrls": { "title": "Recipe URLs", "type": "array", "description": "Recipe pages to extract, one per line. Each page with a recipe gives one row.", "items": { "type": "string" } }, "discoverFrom": { "title": "Discover recipes from", "type": "array", "description": "Sitemaps (sitemap.xml, post-sitemap.xml), RSS feeds or category pages of recipe sites. The actor finds recipe links there and extracts them.", "items": { "type": "string" } }, "maxRecipesPerSite": { "title": "Max recipes per site", "minimum": 1, "maximum": 5000, "type": "integer", "description": "How many recipes to take from each discovery source / website.", "default": 50 }, "maxRecipes": { "title": "Max recipes in total", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Hard cap on recipes extracted (and charged) in this run.", "default": 1000 }, "keepSections": { "title": "Keep instruction sections", "type": "boolean", "description": "Return instructions as objects with their section name (e.g. 'For the sauce') instead of a plain list of step texts.", "default": false }, "includeRawSchema": { "title": "Include raw schema.org data", "type": "boolean", "description": "Add the page's full schema.org Recipe object as 'rawSchema' (for fields not mapped to columns).", "default": false }, "skipFailed": { "title": "Skip pages without a recipe", "type": "boolean", "description": "Leave pages without recipe markup 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).", "default": 5 }, "useResidentialProxy": { "title": "Residential proxy for blocked sites", "type": "boolean", "description": "Some large recipe publishers block datacenter IPs (HTTP 403). Turn this on to retry those pages through Apify residential proxy (billed by Apify per GB of proxy traffic on your account; most food blogs 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 } } } } } } } } } }