{ "openapi": "3.0.1", "info": { "title": "Tabelog Restaurant Scraper (Japan)", "description": "Scrapes restaurants from Tabelog — Japan's #1 restaurant review site. Search any Japanese area by prefecture, district or neighbourhood with 35 cuisine genres; returns name, rating, review count, nearest station, budget, feature tags, address, GPS coordinates and phone number.", "version": "0.1", "x-build-id": "4fbzBlH9D4RKXCpZg" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapyx~tabelog-restaurants-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapyx-tabelog-restaurants-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapyx~tabelog-restaurants-scraper/runs": { "post": { "operationId": "runs-sync-scrapyx-tabelog-restaurants-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapyx~tabelog-restaurants-scraper/run-sync": { "post": { "operationId": "run-sync-scrapyx-tabelog-restaurants-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "areas": { "title": "Areas", "type": "array", "description": "Tabelog area paths — one search per entry, each with its own SEARCH_SUMMARY row. Areas are hierarchical and every depth works:\n\n• `tokyo` — the whole prefecture (139,211 restaurants)\n• `tokyo/A1301` — Ginza & Shimbashi & Yurakucho (6,260)\n• `tokyo/A1301/A130101` — Ginza (2,669)\n\nA full list URL works too (https://tabelog.com/en/tokyo/A1301/A130101/rstLst/) — the easiest way to get one is to browse to the area on tabelog.com and copy the address.\n\nIf an area CODE is wrong, Tabelog does NOT error: it silently searches the parent area instead. The actor detects that via Tabelog's own breadcrumb, refuses to page it, and reports areaApplied: false. (A wrong prefecture returns a clean 404.)\n\nBecause each query caps at 1,200 rows, several narrow areas return far more data than one broad one.", "default": [], "items": { "type": "string" } }, "genre": { "title": "Genre", "enum": [ "", "bar", "bistro", "cafe", "cake", "chinese", "curry", "gyouza", "hamburger", "hamburgersteak", "izakaya", "japanese", "kushiage", "monjya", "motsu", "nabe", "okonomiyaki", "pan", "pasta", "ramen", "ryokan", "seafood", "soba", "steak", "sushi", "sweets", "syabusyabu", "teishoku", "tempura", "tonkatsu", "udon", "unagi", "viking", "washoku", "yakiniku", "yakitori" ], "type": "string", "description": "Restrict to one cuisine/genre. An unrecognised slug returns a clean HTTP 404 (no silent-widen risk here), and every value below was verified to genuinely narrow the results.", "default": "" }, "sortByRating": { "title": "Sort by rating", "type": "boolean", "description": "Return the highest-rated restaurants first instead of Tabelog's default order. This is the only sort Tabelog actually honours — review-count and budget sorts were tested and are silently ignored, so they are not offered.", "default": false }, "restaurantUrls": { "title": "Restaurant URLs (direct mode)", "type": "array", "description": "Scrape specific restaurants directly, skipping the area search. Accepts full Tabelog restaurant URLs (https://tabelog.com/en/tokyo/A1301/A130101/13277198/). Can be combined with an area search in the same run.", "default": [], "items": { "type": "string" } }, "maxItems": { "title": "Max restaurants per area", "minimum": 0, "type": "integer", "description": "Stop paginating an area after this many restaurants. Set to 0 for unlimited — note Tabelog itself stops at 1,200 rows per query (60 pages × 20) however many results it reports. Use a deeper area code or a genre to reach the rest.", "default": 100 }, "includeRestaurantDetails": { "title": "Fetch full restaurant details", "type": "boolean", "description": "Fetch each restaurant's Schema.org record via one extra request: exact street address, postal code, GPS coordinates, phone number, price range and cuisine. Turn this off for a fast list-only crawl — list rows already carry name, rating, review count, nearest station, genre, dinner/lunch budget and feature tags.", "default": true }, "maxConcurrency": { "title": "Max concurrent requests", "minimum": 1, "maximum": 16, "type": "integer", "description": "How many requests may be in flight at once. This absorbs latency variance; it is NOT the throttle — the crawl rate is set by 'Minimum interval between requests' below. Raising this past ~5 will not speed up a run on its own.", "default": 5 }, "minRequestInterval": { "title": "Minimum interval between requests (seconds)", "minimum": 0.05, "maximum": 10, "type": "number", "description": "The actual speed control: the shortest gap between two requests to Tabelog, across all workers. 0.4s (default) ≈ 2.5 requests/second. Lower it to finish faster, raise it to be gentler.\n\nTabelog serves no bot challenge at all, which is worth preserving — an unthrottled crawl is how a WAF-free site stops being WAF-free. Values below 0.05s are clamped.", "default": 0.4 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Tabelog runs no bot challenge at all (8/8 TLS profiles clean), but Residential pinned to Japan is the cloud default — container egress is a different posture than a home connection, and a JP exit gets the same regional content a real visitor sees.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ], "apifyProxyCountry": "JP" } } } }, "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 } } } } } } } } } }