{ "openapi": "3.0.1", "info": { "title": "Baidu Search Scraper", "description": "Scrape organic search results from Baidu, China's leading search engine. Extracts page titles, URLs, snippets, source sites, dates, knowledge cards, and related searches. Supports configurable result limits with proxy support.", "version": "3.2", "x-build-id": "L1LritZeJf9ftXiT0" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/searchapi~baidu-search-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-searchapi-baidu-search-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/searchapi~baidu-search-scraper/runs": { "post": { "operationId": "runs-sync-searchapi-baidu-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/searchapi~baidu-search-scraper/run-sync": { "post": { "operationId": "run-sync-searchapi-baidu-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Search query", "type": "string", "description": "Keywords to enter in Baidu Search." }, "queries": { "title": "Multiple search queries", "maxItems": 10, "type": "array", "description": "Optional batch of up to 10 queries. Duplicates are removed and output is interleaved fairly.", "items": { "type": "string" } }, "startUrls": { "title": "Legacy Baidu search URLs", "type": "array", "description": "Optional backward-compatible Baidu search URLs. Each must use baidu.com and contain a wd query parameter; query fields are preferred.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxItems": { "title": "Maximum total records", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum unique results across all queries.", "default": 50 }, "maxItemsPerQuery": { "title": "Maximum records per query", "minimum": 1, "maximum": 500, "type": "integer", "description": "Optional per-query cap. Defaults to a fair share of maxItems." }, "maxPages": { "title": "Maximum pages per query", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum Baidu pages to inspect for each query.", "default": 5 }, "requestDelayMs": { "title": "Delay between pages (milliseconds)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Optional pause before enqueueing the next page for a query.", "default": 0 }, "market": { "title": "Market", "type": "string", "description": "Language or language-country locale, such as zh-CN.", "default": "zh-CN" }, "includeAds": { "title": "Include ads", "type": "boolean", "description": "Include results Baidu explicitly marks as paid or sponsored.", "default": false }, "includeRelated": { "title": "Include related searches", "type": "boolean", "description": "Include Baidu related-search suggestions when supplied.", "default": true }, "resultTypes": { "title": "Result types", "maxItems": 12, "type": "array", "description": "Optional allow-list for organic, baike, video, image, official, journal, finance, live, recommend, ai-tool, rich, or relatedSearch records.", "items": { "type": "string" } }, "siteDomainContains": { "title": "Source domain contains", "type": "string", "description": "Keep results whose normalized domain or source label contains this text." }, "includeKeywords": { "title": "Required result keywords", "maxItems": 20, "type": "array", "description": "Keep results containing every listed term in title, snippet, source, or domain.", "items": { "type": "string" } }, "excludeKeywords": { "title": "Excluded result keywords", "maxItems": 20, "type": "array", "description": "Remove results containing any listed term in title, snippet, source, or domain.", "items": { "type": "string" } }, "minRating": { "title": "Minimum rating", "minimum": 0, "maximum": 5, "type": "number", "description": "Keep results with a source rating at or above this value." }, "sortBy": { "title": "Output sort order", "enum": [ "relevance", "nameAsc", "nameDesc", "dateDesc", "ratingDesc" ], "type": "string", "description": "Sort after fair query interleaving and global deduplication.", "default": "relevance" }, "maxConcurrency": { "title": "Maximum browser concurrency", "minimum": 1, "maximum": 5, "type": "integer", "description": "Maximum Baidu pages processed simultaneously.", "default": 2 }, "maxRequestRetries": { "title": "Maximum request retries", "minimum": 0, "maximum": 3, "type": "integer", "description": "Bounded retries for temporary failures. Challenge pages are never retried.", "default": 1 }, "navigationTimeoutSecs": { "title": "Navigation timeout", "minimum": 15, "maximum": 120, "type": "integer", "description": "Navigation timeout per Baidu page in seconds.", "default": 45 }, "requestHandlerTimeoutSecs": { "title": "Handler timeout", "minimum": 30, "maximum": 180, "type": "integer", "description": "Total processing timeout per Baidu page in seconds.", "default": 90 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Direct, Apify Residential/Datacenter, or custom proxy settings. GOOGLE_SERP is not applicable to Baidu." }, "blockMedia": { "title": "Block media and fonts", "type": "boolean", "description": "Abort media/font resources after navigation setup while preserving HTML, scripts, and result metadata.", "default": 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 }, "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 } } } } } } } } } }