{ "openapi": "3.0.1", "info": { "title": "OpenRice Restaurant Scraper (Hong Kong)", "description": "Scrape Hong Kong restaurant detail, reviews, and menu photos from OpenRice into a structured dataset. Scheduled batch data feed — polite, reliable crawling over residential proxy.", "version": "0.0", "x-build-id": "cyJwDg225gvNZJf3D" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/precious_nucleus~openrice-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-precious_nucleus-openrice-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/precious_nucleus~openrice-scraper/runs": { "post": { "operationId": "runs-sync-precious_nucleus-openrice-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/precious_nucleus~openrice-scraper/run-sync": { "post": { "operationId": "run-sync-precious_nucleus-openrice-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "district": { "title": "District", "enum": [ "", "2008", "1019", "2010", "1022", "2026", "1003", "3018", "2001", "2029", "2028", "3003", "3007", "1001", "3020", "1004", "2013", "2019", "2016", "3012", "2004", "2005", "2011", "2015", "2022", "3005", "1008", "1026", "2003", "3002", "3015", "1014", "1017", "1018", "1009", "2027", "3006", "3014", "4009", "1011", "1020", "1023", "1025", "2002", "2006", "2020", "2030", "3004", "3017", "3019" ], "type": "string", "description": "Crawl restaurants in a specific Hong Kong district. Covers the main dining areas; for an area not listed, use Keyword or Restaurant IDs.", "default": "" }, "keyword": { "title": "Keyword", "type": "string", "description": "Free-text search (restaurant name, cuisine, dish, area). Combine with District to narrow further. Leave empty to skip." }, "cuisineId": { "title": "Cuisine ID (advanced)", "type": "integer", "description": "Filter by OpenRice cuisine/category id (e.g. 2004). Advanced: there is no public name list, so this takes a raw numeric id. Leave empty to skip." }, "newlyOpenedOnly": { "title": "Newly opened only", "type": "boolean", "description": "Restrict to newly-opened restaurants (~900). Combines with District/Keyword/Cuisine.", "default": false }, "crawlAll": { "title": "Crawl all of Hong Kong", "type": "boolean", "description": "Crawl across all of HK (~33,000) when no District/Keyword/Cuisine filter is set, bounded by Max restaurants. Takes many hours — keep the cap modest and run on a schedule.", "default": false }, "restaurantIds": { "title": "Restaurant IDs", "type": "array", "description": "Specific OpenRice POI ids — the number after -r in a restaurant URL (e.g. 600214). Takes priority over the filters above.", "items": { "type": "string" } }, "startUrls": { "title": "Start URLs", "type": "array", "description": "Specific OpenRice restaurant detail page URLs. Takes priority over the filters above.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxRestaurants": { "title": "Max restaurants", "minimum": 1, "type": "integer", "description": "Hard cap on how many restaurants to crawl this run (applies to every mode).", "default": 500 }, "reviewsPerRestaurant": { "title": "Reviews per restaurant", "minimum": 0, "type": "integer", "description": "How many of the most relevant + recent reviews to collect per restaurant. 0 skips reviews.", "default": 50 }, "includeMenuPhotos": { "title": "Include menu photos", "type": "boolean", "description": "Also collect user-uploaded menu / price-list photos. Turn off to reduce runtime and proxy usage.", "default": true }, "language": { "title": "Language", "enum": [ "zh", "en" ], "type": "string", "description": "Content language for OpenRice.", "default": "zh" } } }, "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 } } } } } } } } } }