{ "openapi": "3.0.1", "info": { "title": "Zhihu Scraper (Q&A, Answers, Articles)", "description": "Zhihu Scraper (Q&A, Answers, Articles) SD - Zhihu Scraper (Q&A, Answers, Articles) is a Chinese Q&A data tool that extracts Zhihu column articles with full text, the hot-list questions, related articles and author profiles with follower counts. No login.", "version": "1.0", "x-build-id": "U3EKUsdJnRPW6H8cx" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/neuro-scraper~zhihu-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-neuro-scraper-zhihu-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/neuro-scraper~zhihu-scraper/runs": { "post": { "operationId": "runs-sync-neuro-scraper-zhihu-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/neuro-scraper~zhihu-scraper/run-sync": { "post": { "operationId": "run-sync-neuro-scraper-zhihu-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "operation": { "title": "Operation", "enum": [ "columnArticles", "hotList", "profiles", "relatedArticles", "search" ], "type": "string", "description": "What to collect. Column articles: every article of a Zhihu column (zhuanlan), newest first. Hot list: the current 知乎热榜 questions. Profiles: author profiles with follower / answer / article counts. Related articles: articles Zhihu recommends next to an article. Search: keyword search through Zhihu's official open API - needs your own developer.zhihu.com access secret. Links in Start URLs are routed by their type whatever is selected (column link -> column articles, /people/ link -> profile, /p/ link -> related articles).", "default": "columnArticles" }, "startUrls": { "title": "Start URLs or IDs", "type": "array", "description": "Zhihu links or ids, one per line: column (https://zhuanlan.zhihu.com/xuehy or the slug xuehy), profile (https://www.zhihu.com/people/zhang-jia-wei or zhang-jia-wei), article (https://zhuanlan.zhihu.com/p/2088191236226261891 or the number). Bare slugs / numbers are read as the selected operation's kind.", "items": { "type": "string" } }, "keyword": { "title": "Search keywords (search operation)", "type": "array", "description": "Keywords for the search operation, e.g. 人工智能 or Python. Zhihu's official API returns up to 10 results per keyword (no further pages exist on that API).", "items": { "type": "string" } }, "zhihuAccessSecret": { "title": "Your Zhihu open-platform access secret (search only)", "type": "string", "description": "Only for the search operation: the access secret from your own account at https://developer.zhihu.com/profile. Zhihu's website search needs a login, so keyword search goes through Zhihu's official API with your key. Never stored or logged." }, "maxItems": { "title": "Max items per target", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum rows per column / article / keyword (the hot list counts as one target). Column and related-article lists follow Zhihu's own next-page cursor until this limit or the end of the list.", "default": 20 }, "includeAuthorProfile": { "title": "Add author follower counts", "type": "boolean", "description": "For article rows, read each author's profile once (one extra request per unique author) to add author follower, answer, article and received-upvote counts, verification label and IP location.", "default": true }, "publishTimeRange": { "title": "Published in", "enum": [ "all", "day", "week", "month", "three_months", "half_year", "year" ], "type": "string", "description": "Only articles created in this period (applied by the Actor to the creation date; column lists are newest first, so paging stops at the first older article). Not applied to the hot list or profiles.", "default": "all" }, "contentType": { "title": "Content type (search only)", "enum": [ "all", "answer", "article", "question", "video" ], "type": "string", "description": "Keep only search results of this type (applied by the Actor to the ContentType the official API returns).", "default": "all" }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Residential proxy is the default: Zhihu flags data-center and over-used IPs (code 40352). On a flag the Actor switches to a new proxy session.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ], "apifyProxyCountry": "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 } } } } } } } } } }