{ "openapi": "3.0.1", "info": { "title": "Website Menu Enrichment Scraper", "description": "Restaurant Website Menu Scraper & Enrichment extracts structured menu data, menu sections, and prices from restaurant websites. It is designed for Apify workflows that start with Google Maps or local business discovery and then enrich each restaurant record with website-only menu coverage", "version": "0.0", "x-build-id": "eqYPoPnvU8endC07l" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gtgyani206~website-menu-enrichment-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gtgyani206-website-menu-enrichment-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/gtgyani206~website-menu-enrichment-scraper/runs": { "post": { "operationId": "runs-sync-gtgyani206-website-menu-enrichment-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/gtgyani206~website-menu-enrichment-scraper/run-sync": { "post": { "operationId": "run-sync-gtgyani206-website-menu-enrichment-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "restaurants": { "title": "Discovery Records", "type": "array", "description": "Array of records from the discovery actor. Each record should include restaurantId, name, website, and websiteTargets when available.", "default": [] }, "startUrls": { "title": "Fallback Website URLs", "type": "array", "description": "Optional raw website URLs for direct runs when discovery records are not available.", "default": [], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Optional proxy settings for websites that block or throttle repeated requests.", "default": { "useApifyProxy": false } }, "sourceDiscoveryRunId": { "title": "Discovery Run ID", "type": "string", "description": "Optional discovery run identifier to stamp onto each enrichment result.", "default": "" }, "maxPagesPerSite": { "title": "Max Pages Per Site", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum number of same-domain pages to scan for each restaurant website.", "default": 5 }, "maxConcurrency": { "title": "Parallel Sites", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many restaurant websites to enrich in parallel.", "default": 5 }, "maxDiscoveredLinksPerPage": { "title": "Max Discovered Links Per Page", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum number of additional menu-like links to enqueue from one scanned page.", "default": 8 }, "successItemThreshold": { "title": "Success Item Threshold", "minimum": 1, "maximum": 50, "type": "integer", "description": "Once this many menu items are captured for a site, the crawler stops discovering additional pages aggressively.", "default": 8 }, "freshnessWindowDays": { "title": "Freshness Window (Days)", "minimum": 0, "maximum": 90, "type": "integer", "description": "Skip and reuse cached enrichment results when the same restaurant website was processed within this many days.", "default": 7 }, "respectNeedsWebsiteEnrichment": { "title": "Respect Discovery Flag", "type": "boolean", "description": "Skip records where needsWebsiteEnrichment is explicitly false.", "default": true }, "forceRefresh": { "title": "Force Refresh", "type": "boolean", "description": "Ignore freshness cache and scrape websites again immediately.", "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 } } }, "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 } } } } } } } } } }