{ "openapi": "3.0.1", "info": { "title": "Booking.com Review Scraper", "description": "Which room type gets the complaints? What do guests really say about your breakfast? Scrape Booking.com reviews at room level — score, liked/disliked texts, stay details, traveler type, management replies — with score-band filters and topic search. Deduplicated, LLM-ready.", "version": "0.0", "x-build-id": "m1sQzb9LfGdA2X2lS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/noraview~booking-com-review-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-noraview-booking-com-review-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/noraview~booking-com-review-scraper/runs": { "post": { "operationId": "runs-sync-noraview-booking-com-review-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/noraview~booking-com-review-scraper/run-sync": { "post": { "operationId": "run-sync-noraview-booking-com-review-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "hotelUrls" ], "properties": { "hotelUrls": { "title": "🏨 Hotel URLs", "type": "array", "description": "Booking.com hotel URLs to scrape reviews for.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxReviewsPerHotel": { "title": "📊 Max Reviews per Hotel", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Newest reviews to collect per hotel (sorted newest first). ~200 = 8 pages.", "default": 200 }, "cutoffMonths": { "title": "📅 Cutoff (months)", "minimum": 1, "maximum": 120, "type": "integer", "description": "Stop paginating once reviews are older than this many months — beyond that a review no longer describes the hotel as it is today.", "default": 24 }, "sort": { "title": "Sort Order", "enum": [ "f_recent_desc", "f_recent_asc", "f_score_desc", "f_score_asc", "f_relevance" ], "type": "string", "description": "Booking.com review sort order.", "default": "f_recent_desc" }, "reviewScoreFilter": { "title": "Review scores filter", "type": "array", "description": "Filter reviews by score band (server-side, same as Booking's own filter — no wasted pages). 'All' = no filter. Multiple bands = one pass per band, merged and deduplicated.", "items": { "type": "string", "enum": [ "all", "superb", "good", "passable", "poor", "very_poor" ], "enumTitles": [ "All", "Superb: 9+", "Good: 7-9", "Passable: 5-7", "Poor: 3-5", "Very poor: 1-3" ] }, "default": [ "all" ] }, "searchText": { "title": "🔍 Search in reviews (optional)", "type": "string", "description": "Same as Booking's 'Search guest reviews by topic' bar — server-side semantic search (e.g. 'breakfast', 'pool', 'noise', 'wifi'). Leave empty for no search. Combines with the score filter.", "default": "" }, "useApifyProxy": { "title": "Force Apify residential proxy", "type": "boolean", "description": "OFF by default — the scraper first tries cheap datacenter IPs. Turn ON only to force the residential proxy from the start (more expensive, rarely needed while auto fallback below is enabled).", "default": false }, "autoProxyFallback": { "title": "🛡️ Auto fallback to residential proxy", "type": "boolean", "description": "Tries datacenter IPs first; if Booking blocks us (WAF / CAPTCHA / HTTP 403-429), the same hotel is automatically retried through Apify's residential proxy. Best cost/reliability balance.", "default": true }, "proxyCountries": { "title": "Proxy Countries", "type": "array", "description": "Source markets to route the proxy through. Reviews are geo-independent — this is only for proxy-pool diversity, not per-country cohorts. One country is normal.", "default": [ "FR" ], "items": { "type": "string" } }, "proxyUrl": { "title": "External Proxy URL (optional)", "type": "string", "description": "Used only if 'Use Apify Proxy' is off. Format: http://user:pass@host:port", "default": "" }, "delayBetweenRequests": { "title": "Delay Between Page Requests (seconds)", "minimum": 1, "maximum": 10, "type": "integer", "description": "Wait time between each review page fetch.", "default": 2 } } }, "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 } } } } } } } } } }