{ "openapi": "3.0.1", "info": { "title": "Hostelworld Reviews Scraper - Hostel Guest Reviews, Ratings", "description": "Hostelworld hostel and backpacker reviews by property URL or id. One row per review: 0-100 score, seven sub-ratings (safety, location, staff, cleanliness), text, owner reply, group type, age, nationality, date. Free hostel row: address, lowest price. Free filters: lowest rated, only new, group type.", "version": "1.0", "x-build-id": "ihRwX2phXlCC3FnKE" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/kestrel~hostelworld-reviews-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-kestrel-hostelworld-reviews-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/kestrel~hostelworld-reviews-scraper/runs": { "post": { "operationId": "runs-sync-kestrel-hostelworld-reviews-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/kestrel~hostelworld-reviews-scraper/run-sync": { "post": { "operationId": "run-sync-kestrel-hostelworld-reviews-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Hostelworld property URLs", "uniqueItems": true, "type": "array", "description": "Hostelworld property pages, e.g. [\"https://www.hostelworld.com/hostels/p/15529/home-lisbon-hostel/\"] (the older hosteldetails.php form works too). Every URL form carries the numeric property id, so no page is loaded first. Use for \"reviews of this hostel\". A URL from another site ends the run with the reason on the run card and nothing charged. One of startUrls or propertyIds is required.", "default": [], "items": { "type": "string" } }, "propertyIds": { "title": "Hostelworld property ids", "uniqueItems": true, "type": "array", "description": "Hostelworld's numeric property ids, e.g. [\"15529\", \"1150\"]: the number in /hostels/p// and the property_id on an earlier run's rows. The fastest input for scheduled runs over a known list. An id Hostelworld no longer serves costs nothing and is reported as a status row with status \"not_found\". One of startUrls or propertyIds is required.", "default": [], "items": { "type": "string" } }, "maxReviewsPerProperty": { "title": "Max reviews per hostel", "minimum": 0, "maximum": 20000, "type": "integer", "description": "Reviews fetched per hostel in reviewsSort order, e.g. 50 (default 100). 0 = every review the hostel has (Hostelworld pages them 50 at a time; a busy hostel has a few thousand, i.e. several dollars). The main cost control: at most N x $0.004 per hostel. minRating, maxRating, groupTypes, sinceDate and requireText apply to these N fetched rows, so set 0 to scan a whole history; for \"the 20 worst reviews\" set 20 with reviewsSort \"rating\".", "default": 100 }, "reviewsSort": { "title": "Review order", "enum": [ "-date", "date", "rating", "-rating" ], "type": "string", "description": "The order Hostelworld returns reviews in: \"-date\" (default, newest first; the only order in which sinceDate stops paging early), \"date\" (oldest first), \"rating\" (lowest rated first: use with a small maxReviewsPerProperty for \"the worst reviews\" or a complaints feed), \"-rating\" (highest rated first). These four are the only values the API honours.", "default": "-date" }, "sinceDate": { "title": "Only reviews published on or after", "type": "string", "description": "Empty (default) = no date limit. \"2026-09-01\" (YYYY-MM-DD) or relative to the day the run starts: \"30 days\", \"2 weeks\", \"6 months\". Use for \"only new reviews\" on a schedule: with the default newest-first order the run stops reading once a whole page predates the date, so a daily run reads one page per hostel. Older reviews are never billed.", "default": "" }, "maxRating": { "title": "Only reviews at or below this score", "minimum": 0, "maximum": 100, "type": "integer", "description": "0 (default) = no ceiling. 1-100 = keep only reviews whose 0-100 overall score is at or below it, e.g. 70 for \"negative reviews\", \"complaints\", \"what guests disliked\" (rating_5 = score / 20, so 70 is 3.5 stars). Combine with reviewsSort \"rating\" so the worst arrive first. Applied to the rows fetched, before billing; filtered reviews are never billed.", "default": 0 }, "minRating": { "title": "Only reviews at or above this score", "minimum": 0, "maximum": 100, "type": "integer", "description": "0 (default) = no floor. 1-100 = keep only reviews scored at or above it, e.g. 90 for \"praise\", \"the raves\", quotes for marketing. Combine with maxRating for a band (minRating must not be above maxRating). Applied before billing; filtered reviews are never billed.", "default": 0 }, "groupTypes": { "title": "Who was travelling", "uniqueItems": true, "type": "array", "description": "Empty (default) = every guest. Otherwise keep only these group types, e.g. [\"FEMALE\"] for \"what solo female travellers say\": MALE and FEMALE (solo travellers), COUPLE, ALLFEMALEGROUP, ALLMALEGROUP, MIXEDGROUP, FAMILY; friendly spellings work (solo_female, female_group, mixed_group, couples, family). Hostelworld has no server-side filter, so the pages are still read; filtered reviews are never billed.", "default": [], "items": { "type": "string" } }, "requireText": { "title": "Only reviews with a written text", "type": "boolean", "description": "false (default) = every review. true = drop score-only reviews (empty text) before billing. Hostelworld reviews nearly always carry a sentence or two, so this rarely removes much; set it when every billed row must carry text.", "default": false }, "includePropertyRow": { "title": "Include a hostel row", "type": "boolean", "description": "true (DEFAULT) = one free row per hostel (type \"property\") with name, type, city, country, address, coordinates, star rating, aggregate 0-100 score and sub-ratings, total ratings, facilities, what it is best for, lowest nightly price and the solo/couples/groups split of reviewers. No charge; the record is read either way (it names the review rows). false = review and status rows only.", "default": true }, "sessions": { "title": "Parallel sessions", "minimum": 1, "maximum": 16, "type": "integer", "description": "Proxy sessions (egress IPs) run in parallel, 1-16, e.g. 2 (default 2). More is faster; each session is paced separately.", "default": 2 }, "perIp": { "title": "Requests per second per session", "minimum": 0.1, "maximum": 5, "type": "number", "description": "Requests per second per session, 0.1-5, e.g. 1 (default 1). Hostelworld's API answered 10 of 10 at 1/s from one datacenter IP; 1-2 is comfortable.", "default": 1 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Apify Proxy datacenter group is enough and is the default: Hostelworld's public JSON API answers plain requests with no key, no login and no bot gate. Residential works too and costs more.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }