{ "openapi": "3.0.1", "info": { "title": "Recipe Scraper (Universal / schema.org)", "description": "Scrape any schema.org-compliant recipe site like Epicurious, BBC Good Food, Tasty, NYT Cooking, Serious Eats, Food Network, plus thousands of food blogs. Extracts ingredients, instructions, nutrition, ratings, prep/cook time, yield, author, and images via JSON-LD parsing.", "version": "1.0", "x-build-id": "aUhyUDKrg3vhfM12x" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/crawlerbros~recipe-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-crawlerbros-recipe-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/crawlerbros~recipe-scraper/runs": { "post": { "operationId": "runs-sync-crawlerbros-recipe-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/crawlerbros~recipe-scraper/run-sync": { "post": { "operationId": "run-sync-crawlerbros-recipe-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "mode" ], "properties": { "mode": { "title": "Mode", "enum": [ "byUrls", "byTag", "bySitemap" ], "type": "string", "description": "How to source recipe URLs.", "default": "byUrls" }, "recipeUrls": { "title": "Recipe URLs (mode=byUrls)", "type": "array", "description": "Recipe URLs from any schema.org-compliant site (Epicurious, BBC Good Food, Tasty, NYT Cooking, Bon Appétit, Serious Eats, Food Network, King Arthur Baking, food blogs, etc.). AllRecipes URLs are rejected as unsupported.", "default": [ "https://www.epicurious.com/recipes/food/views/banana-bread" ], "items": { "type": "string" } }, "tagUrls": { "title": "Tag URLs (mode=byTag)", "type": "array", "description": "Epicurious tag/category URLs OR bare slugs. Examples: `https://www.epicurious.com/recipes/category/main-course`, `/ingredient/banana`, `dessert`. The actor scrapes the tag page → finds recipe URLs → fetches each.", "default": [], "items": { "type": "string" } }, "sitemapUrls": { "title": "Sitemap URLs (mode=bySitemap)", "type": "array", "description": "Sitemap.xml URLs from any recipe site (e.g. `https://www.bbcgoodfood.com/sitemap.xml`, `https://www.epicurious.com/sitemap.xml`, or a deeper recipe-only sitemap). The actor walks the sitemap (one level deep into sitemap indexes), filters recipe-looking URLs, and runs them through the JSON-LD pipeline.", "default": [], "items": { "type": "string" } }, "minRating": { "title": "Min rating (optional)", "minimum": 0, "maximum": 500, "type": "integer", "description": "Drop recipes with `ratingValue` below this. Scale 0-500 (e.g. 400 = 4.0/5)." }, "minRatingCount": { "title": "Min rating count (optional)", "minimum": 0, "maximum": 10000000, "type": "integer", "description": "Drop recipes with fewer than this many ratings." }, "maxTotalTimeMinutes": { "title": "Max total time (minutes)", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Drop recipes whose `prep + cook` time exceeds this many minutes." }, "keywordIncludes": { "title": "Must contain keyword (optional)", "type": "string", "description": "Drop recipes whose name + description don't contain this keyword." }, "proxy": { "title": "Apify Proxy (optional)", "type": "object", "description": "Apify Proxy is optional. For Epicurious / Tasty / BBC Good Food / NYT Cooking / most food blogs, no proxy is needed; datacenter or residential both work. Provided here for sites that occasionally rate-limit.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }, "maxItems": { "title": "Max items", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Hard cap on emitted records.", "default": 50 } } }, "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 } } } } } } } } } }