{ "openapi": "3.0.1", "info": { "title": "Autohome Koubei Scraper: 汽车之家口碑 Owner Reviews", "description": "Extract Autohome 口碑 (koubei) owner reviews: category star ratings, pros/cons text, purchase price/date, reviewer info, and model/trim data for any car series on autohome.com.cn.", "version": "0.1", "x-build-id": "iwLAJ3m9ncQm9V24h" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/getascraper~autohome-koubei-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-getascraper-autohome-koubei-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/getascraper~autohome-koubei-scraper/runs": { "post": { "operationId": "runs-sync-getascraper-autohome-koubei-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/getascraper~autohome-koubei-scraper/run-sync": { "post": { "operationId": "run-sync-getascraper-autohome-koubei-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "seriesIds": { "title": "Series IDs or model URLs", "type": "array", "description": "One or more Autohome car-model series to scrape. Accepts a bare series ID (e.g. \"6172\") or a full model URL (e.g. \"https://k.autohome.com.cn/6172/\" or \"https://car.autohome.com.cn/config/series/6172.html\"). Find the series ID in any k.autohome.com.cn/{id}/ or car.autohome.com.cn URL for the model.", "default": [ "6172" ], "items": { "type": "string" } }, "since": { "title": "Only reviews posted on/after", "type": "string", "description": "Optional. Only include reviews posted on or after this date (YYYY-MM-DD). Leave blank to include all reviews found within the page-scan limit." }, "onlyNewReviews": { "title": "Only new reviews (incremental mode)", "type": "boolean", "description": "When on, the Actor remembers which review IDs it has already emitted for each series (persisted in the key-value store) and only pushes reviews it hasn't seen before. Combine with an Apify Schedule for a daily/weekly recurring monitor of new owner reviews.", "default": false }, "includeSeriesSummary": { "title": "Include series summary row", "type": "boolean", "description": "When on, emits one extra row per series (rowType: \"series_summary\") with aggregate data: brand, average score, total review count, on-sale review count, problems-per-hundred (PPH), and category-average ratings.", "default": true }, "maxReviews": { "title": "Max reviews per series", "minimum": 1, "type": "integer", "description": "Maximum number of review rows to emit per series. Reviews are dense on popular models (thousands per series), so keep this modest for a preview run.", "default": 200 }, "maxPagesToScan": { "title": "Max pages to scan per series", "minimum": 1, "type": "integer", "description": "Safety cap on how many list pages the Actor will scan per series (the API's actual page size varies, ~10-20 reviews/page — don't assume a fixed count). The Actor stops early once \"Max reviews per series\" is reached, so raising this cap has no cost unless it's actually needed. Raise it for high-volume series, or if \"Since\"/\"Only new reviews\" filtering isn't finding as many matches as expected.", "default": 50 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Datacenter proxy is sufficient for this target — no residential IP requirement was found during recon (no WAF, no TLS/JA3 gate, no geo-block). Leave this on the default.", "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 } } }, "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 } } } } } } } } } }