{ "openapi": "3.0.1", "info": { "title": "Zhihu Q&A Tracker - China Hot List & Knowledge Mining", "description": "Scrape Zhihu (知乎), China's Quora: the daily hot list plus keyword Q&A search. Each record has the question, top-answer excerpt, voteup count, view count and category. For China social listening, consumer research and brand monitoring. No CN account needed.", "version": "0.0", "x-build-id": "81GwGd519dUefo2Y3" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/nexgendata~zhihu-qa-tracker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-nexgendata-zhihu-qa-tracker", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/nexgendata~zhihu-qa-tracker/runs": { "post": { "operationId": "runs-sync-nexgendata-zhihu-qa-tracker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/nexgendata~zhihu-qa-tracker/run-sync": { "post": { "operationId": "run-sync-nexgendata-zhihu-qa-tracker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "Collection mode", "enum": [ "hot", "search", "both" ], "type": "string", "description": "How to seed the Q&A crawl. 'hot' = pull from Zhihu's daily hot-list (api.zhihu.com/topstory/hot-list) — best for trend monitoring. 'search' = keyword search across zhihu.com/search — best for brand monitoring and topic-specific mining; this surface requires a residential (ideally CN) proxy exit and the run FAILS loudly if Zhihu blocks every attempt. 'both' = hot list first, then top up with keyword searches. With no keywords supplied, 'both' runs the hot list only.", "default": "hot" }, "keywords": { "title": "Keywords to search (Chinese or English)", "type": "array", "description": "Search terms to run against Zhihu's content search. Use Chinese characters for native-quality hits (e.g. [\"人工智能\", \"电动汽车\"]). Required when mode='search' — if it is empty the run succeeds with 0 rows and tells you the field is missing, and nothing is charged. Ignored when mode='hot'.", "items": { "type": "string" } }, "categories": { "title": "Category / topic filter", "type": "array", "description": "Optional output filter. Zhihu records are classified into: tech, finance, business, automotive, education, career, lifestyle, health, entertainment, science, politics. Empty (the default) = no filter, return everything fetched. Note this is a filter, not a query — setting it can only reduce the rows you are charged for.", "items": { "type": "string" } }, "limit": { "title": "Limit (max Q&A records)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum number of question/answer records to return per run. Each delivered record costs $0.10. 20-50 is typical for daily monitoring; 100-300 for one-off research sweeps.", "default": 30 }, "min_voteup": { "title": "Minimum top-answer voteup count", "minimum": 0, "type": "integer", "description": "Drop records whose top answer has fewer than N voteups. Voteup counts are only surfaced on the search surface, so a non-zero value here will filter out hot-list records (which carry heat, not voteups). Default 0 = keep everything.", "default": 0 }, "include_hot_only": { "title": "Restrict to hot-list questions only", "type": "boolean", "description": "When true, keep only records that appeared on Zhihu's hot list (is_hot=true). Useful for a pure trend signal without keyword-search noise.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify proxy configuration. RESIDENTIAL with a CN/HK/SG exit is strongly recommended: www.zhihu.com returns HTTP 403 with an anti-bot interstitial to datacenter IPs (verified live). The hot-list JSON API does answer datacenter IPs, so mode='hot' works without a proxy. If every attempt is blocked the run FAILS rather than returning a placeholder row.", "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 } } } } } } } } } }