{ "openapi": "3.0.1", "info": { "title": "Airbnb Scraper", "description": "Scrape rich public Airbnb listing search and detail data with explicit access-boundary diagnostics when the site is unavailable or challenged.", "version": "1.1", "x-build-id": "FgXIqhuyj24jCAn6V" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/w3crawler~airbnb-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-w3crawler-airbnb-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/w3crawler~airbnb-scraper/runs": { "post": { "operationId": "runs-sync-w3crawler-airbnb-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/w3crawler~airbnb-scraper/run-sync": { "post": { "operationId": "run-sync-w3crawler-airbnb-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "Run mode", "enum": [ "search", "productUrl" ], "type": "string", "description": "Search one or more result pages, or scrape specific public listing URLs.", "default": "search" }, "location": { "title": "Location", "maxLength": 160, "type": "string", "description": "City, region, or neighbourhood used to create the public Airbnb search URL.", "default": "Paris" }, "searchUrl": { "title": "Search URL", "type": "string", "description": "Optional HTTPS Airbnb /s/... URL. Its public filters and cursor are preserved; explicit input options are applied on top." }, "startUrls": { "title": "Additional search URLs", "type": "array", "description": "Optional list of HTTPS Airbnb /s/... URLs. Each source gets its own pagination budget and contributes to one global deduplicated result set.", "items": { "type": "object", "properties": { "url": { "title": "Airbnb search URL", "type": "string", "description": "Approved HTTPS Airbnb /s/... search URL." } }, "required": [ "url" ], "additionalProperties": false } }, "productUrls": { "title": "Listing URLs", "maxItems": 500, "type": "array", "description": "Public HTTPS Airbnb /rooms/ URLs. Used in productUrl mode; duplicate listing IDs are removed.", "items": { "type": "string" } }, "checkIn": { "title": "Check-in date", "pattern": "^$|^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Optional stay date in YYYY-MM-DD format. Must be used with checkOut." }, "checkOut": { "title": "Check-out date", "pattern": "^$|^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Optional stay date in YYYY-MM-DD format. Must be after checkIn." }, "guests": { "title": "Guests", "minimum": 1, "maximum": 16, "type": "integer", "description": "Adult guest count included in the public Airbnb query.", "default": 2 }, "currency": { "title": "Currency", "enum": [ "USD", "EUR", "GBP", "CAD", "AUD", "INR", "JPY", "SGD" ], "type": "string", "description": "Requested display currency for visible prices.", "default": "USD" }, "locale": { "title": "Locale", "pattern": "^[a-z]{2}(?:-[A-Z]{2})?$", "maxLength": 10, "type": "string", "description": "Airbnb language or language-region preference, for example en-US or fr-FR.", "default": "en-US" }, "propertyType": { "title": "Property type", "enum": [ "any", "entire_home", "private_room", "shared_room" ], "type": "string", "description": "Optional Airbnb room-type query filter.", "default": "any" }, "priceMin": { "title": "Minimum nightly price", "minimum": 0, "type": "number", "description": "Optional lower bound in the requested currency. Applied to the visible price per night when available." }, "priceMax": { "title": "Maximum nightly price", "minimum": 0, "type": "number", "description": "Optional upper bound in the requested currency. Must be greater than or equal to priceMin." }, "keyword": { "title": "Keyword", "maxLength": 160, "type": "string", "description": "Case-insensitive text match across title, description, property type, location, neighbourhood, and collected amenities." }, "minRating": { "title": "Minimum rating", "minimum": 0, "maximum": 5, "type": "number", "description": "Keep listings with an average public rating at or above this value." }, "maxRating": { "title": "Maximum rating", "minimum": 0, "maximum": 5, "type": "number", "description": "Keep listings with an average public rating at or below this value." }, "minReviewCount": { "title": "Minimum review count", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Keep listings with at least this many public reviews." }, "guestFavouriteOnly": { "title": "Guest favourites only", "type": "boolean", "description": "Keep only cards/details visibly marked Guest favourite.", "default": false }, "superhostOnly": { "title": "Superhosts only", "type": "boolean", "description": "Keep only listings whose public card/detail data marks the host as a Superhost.", "default": false }, "freeCancellationOnly": { "title": "Free cancellation only", "type": "boolean", "description": "Keep only records that visibly expose free cancellation.", "default": false }, "sortBy": { "title": "Sort results", "enum": [ "recommended", "price_asc", "price_desc", "rating_desc", "review_count_desc", "title_asc" ], "type": "string", "description": "Global result order after all search pages and sources are collected. recommended preserves Airbnb order.", "default": "recommended" }, "deduplicate": { "title": "Deduplicate listings", "type": "boolean", "description": "Deduplicate by Airbnb listing ID across pages and sources.", "default": true }, "maxItems": { "title": "Maximum output records", "minimum": 1, "maximum": 500, "type": "integer", "description": "Global maximum dataset row count, including at most diagnostic rows when no listing data is available.", "default": 50 }, "maxPages": { "title": "Maximum pages per search URL", "minimum": 0, "maximum": 50, "type": "integer", "description": "Maximum observed cursor/page links to visit per search source. 0 follows observed next links until the source ends or maxItems is satisfied.", "default": 0 }, "deepScrape": { "title": "Enrich listing details", "type": "boolean", "description": "Visit selected listing pages for descriptions, amenities, host, policies, coordinates, availability, and bounded reviews.", "default": true }, "maxDetailItems": { "title": "Maximum detail pages", "minimum": 0, "maximum": 500, "type": "integer", "description": "Maximum selected listings to enrich. 0 enriches every selected listing; remaining selected rows are returned with detailEnriched=false.", "default": 0 }, "includeDescription": { "title": "Include descriptions", "type": "boolean", "description": "Include public listing/host description text when exposed.", "default": true }, "includeAmenities": { "title": "Include amenities", "type": "boolean", "description": "Collect visible amenities and expand the public amenities dialog when possible.", "default": true }, "includeImages": { "title": "Include image URLs", "type": "boolean", "description": "Include public image URLs, thumbnail, and imageCount.", "default": true }, "includeReviews": { "title": "Include reviews", "type": "boolean", "description": "Collect a bounded first-page sample of public review cards and rating categories.", "default": true }, "maxReviews": { "title": "Maximum reviews per listing", "minimum": 0, "maximum": 50, "type": "integer", "description": "Maximum public review cards per detail page when includeReviews is enabled.", "default": 10 }, "includeDiagnostics": { "title": "Include diagnostics", "type": "boolean", "description": "When no listing rows are available, emit rich run_diagnostic rows with access status, error codes, and fallback provenance.", "default": true }, "requestDelayMs": { "title": "Request delay (ms)", "minimum": 0, "maximum": 15000, "type": "integer", "description": "Delay before extracting a page. Increase for a gentler request profile.", "default": 0 }, "maxConcurrency": { "title": "Maximum concurrency", "minimum": 1, "maximum": 5, "type": "integer", "description": "Maximum concurrent browser requests. 1 is the gentlest setting.", "default": 1 }, "maxRequestRetries": { "title": "Maximum request retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "Crawlee retries for failed navigations and extraction requests.", "default": 3 }, "requestTimeoutSecs": { "title": "Request timeout (s)", "minimum": 30, "maximum": 300, "type": "integer", "description": "Preferred navigation timeout for browser and HTTP fallback requests.", "default": 120 }, "navigationTimeoutSecs": { "title": "Navigation timeout alias (s)", "minimum": 30, "maximum": 300, "type": "integer", "description": "Backward-compatible alias for requestTimeoutSecs. requestTimeoutSecs takes precedence when both are supplied." }, "requestHandlerTimeoutSecs": { "title": "Request handler timeout (s)", "minimum": 60, "maximum": 900, "type": "integer", "description": "Maximum time for one page's extraction, modal expansion, and review parsing.", "default": 300 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional Apify proxy configuration passed to browser requests. Credentials are never logged. HTTP fallback remains direct if the browser cannot use the proxy." } } }, "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 } } } } } } } } } }