{ "openapi": "3.0.1", "info": { "title": "Hostelworld Hostels Scraper", "description": "Scrapes hostels, guesthouses and budget hotels from Hostelworld by city. Every row carries nightly dorm and private prices, an 8-axis rating breakdown, GPS coordinates, address, district, facilities and images. Optional per-property detail adds policies, house rules and check-in times.", "version": "0.1", "x-build-id": "mFhEf5pTuc0jIw7Kj" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapyx~hostelworld-hostels-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapyx-hostelworld-hostels-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapyx~hostelworld-hostels-scraper/runs": { "post": { "operationId": "runs-sync-scrapyx-hostelworld-hostels-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapyx~hostelworld-hostels-scraper/run-sync": { "post": { "operationId": "run-sync-scrapyx-hostelworld-hostels-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "locations": { "title": "Cities", "type": "array", "description": "One city per entry, each with its own SEARCH_SUMMARY row.\n\nThree accepted forms:\n\n- `Spain/Barcelona` — **recommended**. Country-scoped, unambiguous, and needs only one lookup request.\n- `Barcelona` — bare name. Works, but the first bare name in a run builds a global city index (one request per country, issued concurrently). Refused with a list of candidates if the name exists in more than one country.\n- `22418` — a raw Hostelworld city id, used as-is with no lookup.\n\nHostelworld has no city-search endpoint, so names are resolved through their own continents → countries → cities listing. That listing is not exhaustive: if a city you know exists is not found, pass its numeric id instead.", "default": [], "items": { "type": "string" } }, "propertyType": { "title": "Property type", "enum": [ "", "HOSTEL", "HOTEL", "GUESTHOUSE", "APARTMENT", "CAMPSITE" ], "type": "string", "description": "Restrict to one kind of property. Verified on Barcelona, where the types partition the city exactly: 93 hostels + 5 hotels + 15 guesthouses + 2 apartments = the full 115. An unrecognised type is refused by Hostelworld with HTTP 400 rather than being silently ignored, so anything outside this list is rejected before the run starts.", "default": "" }, "sort": { "title": "Sort order", "enum": [ "", "-rating", "rating", "price", "-price", "distance", "name" ], "type": "string", "description": "Each value here was verified to genuinely reorder results. `popularity` and `recommended` look plausible but are refused with HTTP 400, so they are not offered.", "default": "" }, "checkInDate": { "title": "Check-in date", "type": "string", "description": "Optional `YYYY-MM-DD`. Set this together with **Nights** to return only properties with real availability for those dates — on London this narrowed 94 properties to 80. Must be set as a pair: one without the other is answered with HTTP 400.", "default": "" }, "nights": { "title": "Nights", "minimum": 0, "maximum": 30, "type": "integer", "description": "Length of stay in nights, used with **Check-in date**. Leave at 0 to list every property regardless of availability.", "default": 0 }, "includePropertyDetails": { "title": "Fetch full property details", "type": "boolean", "description": "Adds one request per property and attaches a `detail` object carrying what the listing does not: full description, house rules and things to note, cancellation policy, payment methods, check-in/check-out window, the categorised facility list and a sample of recent reviews.\n\nOff by default — search rows already include prices, the 8-axis rating breakdown, coordinates, address, district and images, which is enough for most uses.", "default": false }, "maxItems": { "title": "Max properties per city", "minimum": 0, "type": "integer", "description": "Stop after this many properties per city. Set to 0 for unlimited — Hostelworld imposes no result-window ceiling, and the largest city measured (Bangkok) holds 326 properties.", "default": 100 }, "pageSize": { "title": "Rows per request", "minimum": 1, "maximum": 500, "type": "integer", "description": "How many properties to pull per API call. No server-side cap was found — 500 returns a whole city in a single request. 200 keeps responses around 1 MB while still covering most cities in one call.", "default": 200 }, "maxConcurrency": { "title": "Max concurrent requests", "minimum": 1, "maximum": 16, "type": "integer", "description": "Upper bound on requests in flight at once, across all cities and any detail fetches.", "default": 4 }, "minRequestInterval": { "title": "Minimum seconds between requests", "minimum": 0, "maximum": 30, "type": "integer", "description": "Paces how often requests START, without tying up a concurrency slot. No throttling was observed (12 back-to-back detail calls all returned 200), so this defaults to 0 — raise it to be gentler on large crawls.", "default": 0 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Hostelworld's API is fully open — no auth, no token, and no bot challenge on any of the 8 TLS profiles tested across every surface. Residential is still the cloud default, because container egress is a different posture than a home connection. No country pin: this is a global travel API with no geo gate.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }