{ "openapi": "3.0.1", "info": { "title": "Trip.com & Ctrip Hotel Reviews Scraper", "description": "Trip.com & Ctrip hotel reviews scraper ā€” pull guest reviews with overall + sub-ratings, review text, check-in dates, travel type, photos and hotel replies. Search by city or hotel URL. Structured JSON/CSV for analytics and AI.", "version": "1.0", "x-build-id": "EMsDITpRNcm1y6MQL" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sian.agency~ctrip-trip-hotel-reviews-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sian.agency-ctrip-trip-hotel-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sian.agency~ctrip-trip-hotel-reviews-scraper/runs": { "post": { "operationId": "runs-sync-sian.agency-ctrip-trip-hotel-reviews-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sian.agency~ctrip-trip-hotel-reviews-scraper/run-sync": { "post": { "operationId": "run-sync-sian.agency-ctrip-trip-hotel-reviews-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "operation" ], "properties": { "operation": { "title": "šŸŽÆ Operation ā€” what do you want to scrape?", "enum": [ "hotelReviews", "cityHotels" ], "type": "string", "description": "šŸŽÆ **PICK ONE OPERATION PER RUN.** Each run produces one clean dataset matching the chosen mode.\n\n- **šŸØ Hotel Reviews** ā€” all guest reviews for one hotel, by hotel URL or ID (paginated, ~10 reviews/page, with owner replies and photos)\n- **šŸ”Ž City Hotels** ā€” discover hotels in a city by name (e.g. `Beijing`) with score/review-count/location, then scrape their reviews\n\nšŸ’” **TIP:** Run City Hotels first to get hotelIds, then run Hotel Reviews per hotel.", "default": "hotelReviews" }, "hotelUrlOrId": { "title": "šŸØ Hotel URL or ID (for Hotel Reviews)", "type": "string", "description": "šŸØ **Required for `Hotel Reviews`.**\n\nPaste any Trip.com / Ctrip hotel detail URL or just the numeric hotel ID:\n- `https://us.trip.com/hotels/detail/?hotelId=702258`\n- `702258`\n\nThe ID is extracted automatically from either form.\n\nāš ļø **Ignored** for City Hotels." }, "cityName": { "title": "šŸ™ļø City name (for City Hotels)", "type": "string", "description": "šŸ™ļø **Required for `City Hotels`.**\n\nAny city you could type into Trip.com's search box, in English or Chinese: `Beijing`, `Tokyo`, `Barcelona`, `香ęøÆ`.\n\nThe actor looks the city up the way the site does, then fetches its top hotels with guest score, review count and location. Turn on review scraping to also pull each hotel's reviews.\n\nāš ļø **Ignored** for Hotel Reviews." }, "scrapeReviewsForCityHotels": { "title": "šŸ’¬ Also scrape reviews for discovered hotels", "type": "boolean", "description": "šŸ’¬ **For `City Hotels` only.** After discovering hotels, also pull guest reviews for each one (up to `maxPages` review pages per hotel).\n\nOff = discovery only (hotel rows are cheaper). On = discovery + full reviews.", "default": false }, "maxHotels": { "title": "šŸØ Max hotels to discover (City Hotels)", "minimum": 1, "maximum": 25, "type": "integer", "description": "šŸØ **For `City Hotels`.** Most hotels to return per city. Trip.com shows its top 5 hotels for a city here, so anything above 5 still returns 5.", "default": 10 }, "maxPages": { "title": "šŸ“„ Max review pages per hotel", "minimum": 1, "maximum": 100, "type": "integer", "description": "šŸ“„ **Applies to review fetching** (Hotel Reviews, or City Hotels with review scraping on).\n\n~10 reviews per page.\n\nšŸ’” Start with 1-3 pages to preview before scaling.\n\nāš ļø Hard cap: 100 pages (= ~1,000 reviews) per hotel.", "default": 5 }, "language": { "title": "šŸŒ Output language for tags & labels", "enum": [ "en-US", "zh-CN" ], "type": "string", "description": "šŸŒ Request locale used upstream. `en-US` returns English text, translated review labels and English city names. `zh-CN` returns Chinese.", "default": "en-US" } } }, "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 } } } } } } } } } }