{ "openapi": "3.0.1", "info": { "title": "Baidu Tieba Public Threads Scraper", "description": "Scrape public forum threads and posts from Baidu Tieba (tieba.baidu.com). Extracts thread titles, content, author, replies, and metadata from public forum listings and individual threads.", "version": "2.0", "x-build-id": "ujYMD7wLet3qFnU8r" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/searchapi~baidu-tieba-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-searchapi-baidu-tieba-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/searchapi~baidu-tieba-scraper/runs": { "post": { "operationId": "runs-sync-searchapi-baidu-tieba-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/searchapi~baidu-tieba-scraper/run-sync": { "post": { "operationId": "run-sync-searchapi-baidu-tieba-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "query": { "title": "Forum name", "type": "string", "description": "The forum name to enter in Tieba search, for example 人工智能." }, "queries": { "title": "Multiple forum names", "type": "array", "description": "Optional batch of forum names. Results are selected fairly across forums.", "items": { "type": "string" } }, "threadUrls": { "title": "Direct public thread URLs", "type": "array", "description": "Optional HTTPS tieba.baidu.com/p/ URLs. Direct threads can be combined with forum searches.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxItems": { "title": "Maximum threads", "minimum": 1, "maximum": 200, "type": "integer", "description": "Maximum number of normalized thread records across all inputs.", "default": 20 }, "maxItemsPerQuery": { "title": "Maximum threads per forum", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum candidates selected from each forum before fair batch merging.", "default": 20 }, "maxPages": { "title": "Maximum listing pages per forum", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum number of forum listing pages to inspect for each forum.", "default": 3 }, "maxConcurrency": { "title": "Concurrent thread pages", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum number of public thread pages processed concurrently.", "default": 4 }, "maxPostsPerThread": { "title": "Maximum loaded posts per thread", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum post objects retained from the rendered thread page.", "default": 50 }, "minReplies": { "title": "Minimum reply count", "minimum": 0, "maximum": 10000000, "type": "integer", "description": "Skip listing candidates whose published reply count is below this value.", "default": 0 }, "includeThreadDetails": { "title": "Enrich individual thread pages", "type": "boolean", "description": "Open each public thread for posts and richer metadata. Leave disabled for the fastest and most block-resistant listing mode.", "default": false }, "includePosts": { "title": "Include loaded post objects", "type": "boolean", "description": "Include normalized post objects loaded on each public thread page.", "default": true }, "includeImages": { "title": "Include image URLs", "type": "boolean", "description": "Include public image URLs found in loaded posts.", "default": true }, "includeVideos": { "title": "Include video URLs", "type": "boolean", "description": "Include public video or poster URLs found in loaded posts.", "default": true }, "includeSticky": { "title": "Include sticky threads", "type": "boolean", "description": "Include threads marked sticky in forum listings.", "default": true }, "featuredOnly": { "title": "Featured threads only", "type": "boolean", "description": "Keep only threads marked as featured or 精品 in forum listings.", "default": false }, "failOnNoResults": { "title": "Fail when no results are available", "type": "boolean", "description": "Throw an error instead of returning an empty dataset when no public threads are available.", "default": false }, "maxRequestRetries": { "title": "Maximum request retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Bounded retries for temporary network, proxy, rate-limit, or browser failures.", "default": 2 }, "navigationTimeoutSecs": { "title": "Navigation timeout (seconds)", "minimum": 15, "maximum": 120, "type": "integer", "description": "Maximum time allowed for each browser navigation.", "default": 45 }, "requestHandlerTimeoutSecs": { "title": "Handler timeout (seconds)", "minimum": 30, "maximum": 180, "type": "integer", "description": "Maximum time allowed for each listing or thread handler.", "default": 90 }, "waitAfterLoadMillis": { "title": "Post-load wait (milliseconds)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Small bounded wait for public DOM content that appears immediately after navigation.", "default": 750 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Use Apify Residential or custom HTTP proxies when authorized. GOOGLE_SERP is not compatible with Tieba." } } }, "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 } } } } } } } } } }