{ "openapi": "3.0.1", "info": { "title": "Airbnb Reviews Scraper — Most Comprehensive", "description": "From $0.30 per 1,000 reviews — 16x cheaper than the $5/1k incumbent. Star rating, full text, translations, host responses, dates, review tags. Keyword + date filters with early stop, GDPR-safe PII strip, and a new-review monitor with Slack/email/webhook alerts. No login or API key.", "version": "0.1", "x-build-id": "LTyvUxJsA4rNMWHK2" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapersdelight~airbnb-reviews-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapersdelight-airbnb-reviews-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/scrapersdelight~airbnb-reviews-scraper/runs": { "post": { "operationId": "runs-sync-scrapersdelight-airbnb-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/scrapersdelight~airbnb-reviews-scraper/run-sync": { "post": { "operationId": "run-sync-scrapersdelight-airbnb-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", "required": [ "listingUrls" ], "properties": { "listingUrls": { "title": "Listing URLs or IDs", "type": "array", "description": "Airbnb listing page URLs (any country domain, e.g. https://www.airbnb.com/rooms/20669368) or bare numeric listing IDs. One dataset row per review, for every listing.", "items": { "type": "string" } }, "maxReviews": { "title": "Max reviews per listing", "minimum": 0, "type": "integer", "description": "Hard cap on reviews scraped per listing (cost/safety guard). Defaults to 50 for a fast first run — set to 0 to pull EVERY review the listing has.", "default": 50 }, "sortBy": { "title": "Sort results by", "enum": [ "newest", "oldest", "rating-high", "rating-low" ], "type": "string", "description": "Order of the output dataset. Reviews are always fetched newest-first from Airbnb (which is what makes the 'Reviews from date' early-stop possible); this re-orders the final dataset.", "default": "newest" }, "dateFrom": { "title": "Reviews from date (early stop)", "type": "string", "description": "Only reviews written on/after this date, format YYYY-MM-DD. Because Airbnb serves reviews newest-first, the scraper STOPS paginating the moment it hits an older review — you don't pay for pages you don't need." }, "dateTo": { "title": "Reviews up to date", "type": "string", "description": "Only reviews written on/before this date, format YYYY-MM-DD (client-side filter)." }, "keyword": { "title": "Keyword filter", "type": "string", "description": "Only output reviews whose text, translation, or host response contains this word/phrase (case-insensitive). E.g. 'wifi', 'dirty', 'check-in'." }, "minRating": { "title": "Min star rating", "minimum": 0, "maximum": 5, "type": "integer", "description": "Only reviews with this per-review star rating or higher (1–5). 0 = no floor.", "default": 0 }, "maxRating": { "title": "Max star rating", "minimum": 0, "maximum": 5, "type": "integer", "description": "Only reviews with this per-review star rating or lower (1–5) — e.g. 3 to study complaints. 0 = no cap.", "default": 0 }, "stripPersonalData": { "title": "Strip personal data (GDPR-safe)", "type": "boolean", "description": "ON (default): reviewer name, user id, profile URL, and avatar are removed from the output — you keep the full review text, rating, dates, and host response. Turn OFF only if you have a lawful basis to process the reviewer's personal data (GDPR/CCPA — your responsibility).", "default": true }, "includeRaw": { "title": "Include raw API object", "type": "boolean", "description": "Attach the original Airbnb API review object (minus UI noise) as a `raw` sub-object on every record — future-proofs you against any field we didn't flatten.", "default": false }, "monitorMode": { "title": "Monitor mode (new-review watcher)", "type": "boolean", "description": "Recurring watcher: diff against the prior run's seen reviews (per listing) and output/alert ONLY reviews posted since the last run. Pair with an Apify Schedule.", "default": false }, "alertOnNewReview": { "title": "Alert on new reviews", "type": "boolean", "description": "In monitor mode, deliver an alert for each new review via the channels below.", "default": true }, "webhookUrl": { "title": "Webhook URL", "type": "string", "description": "POST endpoint for new-review alert payloads (Make / Zapier / n8n / custom). One JSON body per alert." }, "slackWebhookUrl": { "title": "Slack webhook URL", "type": "string", "description": "Slack incoming-webhook URL for formatted new-review cards (stars + excerpt + listing link)." }, "emailRecipients": { "title": "Email recipients", "type": "array", "description": "Email addresses for the new-review digest (sent via apify/send-mail).", "items": { "type": "string" } }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Proxy settings. Datacenter rotation worked in testing; switch to residential if you scrape thousands of listings per day.", "default": { "useApifyProxy": true } }, "requestConcurrency": { "title": "Listing concurrency", "minimum": 1, "maximum": 8, "type": "integer", "description": "How many listings to scrape in parallel. Keep modest (4–8) to stay polite.", "default": 4 }, "diagnose": { "title": "Diagnostic mode (dev)", "type": "boolean", "description": "Dev only. Dumps the raw reviews API JSON to the key-value store (DEBUG_REVIEWS_JSON) and logs the parsed first record, then exits. Leave off for normal runs.", "default": false } } }, "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 } } } } } } } } } }