{ "openapi": "3.0.1", "info": { "title": "Baidu Search Scraper - Web & News SERP Results", "description": "Scrape Baidu web and news search results with the real destination URL, title, snippet, source, publish date and rank. No redirect resolving, no login, no cookies.", "version": "0.1", "x-build-id": "cHnu3ywyfxz5i8NL6" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapesage~baidu-search-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapesage-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapesage~baidu-search-scraper/runs": { "post": { "operationId": "runs-sync-scrapesage-baidu-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapesage~baidu-search-scraper/run-sync": { "post": { "operationId": "run-sync-scrapesage-baidu-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "queries": { "title": "Search queries", "type": "array", "description": "What to search for on Baidu. Chinese queries return far more results than English ones - Baidu's index is overwhelmingly Chinese.", "items": { "type": "string" } }, "searchType": { "title": "Search type", "enum": [ "web", "news", "both" ], "type": "string", "description": "Web results, Baidu News results, or both.", "default": "web" }, "maxPagesPerQuery": { "title": "Max pages per query", "minimum": 1, "maximum": 50, "type": "integer", "description": "How deep to page for each query. Baidu returns about 10 results per page.", "default": 3 }, "resultsPerPage": { "title": "Results per page", "minimum": 10, "maximum": 50, "type": "integer", "description": "Ask Baidu for more results per request (10-50). Higher values mean fewer requests, but Baidu sometimes trims the page.", "default": 10 }, "onlyOrganic": { "title": "Only organic results", "type": "boolean", "description": "Drop Baidu's rich 'featured' blocks and keep plain organic web results only.", "default": false }, "excludeBaiduModules": { "title": "Exclude Baidu's own modules", "type": "boolean", "description": "Drop recommendation strips and other blocks that point back into baidu.com rather than a real destination site.", "default": true }, "requireQueryMatch": { "title": "Require query match", "type": "boolean", "description": "Baidu answers a term it cannot match with a page of unrelated filler instead of an empty page. With this on, a query whose first page contains no result mentioning the term is treated as having no genuine matches - nothing is stored and nothing is billed. Turn off to keep whatever Baidu returns.", "default": true }, "includeRelatedSearches": { "title": "Include related searches", "type": "boolean", "description": "Also output the 'related searches' terms Baidu suggests for each query, as rows with type = relatedSearch.", "default": false }, "maxResults": { "title": "Max results (whole run)", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Total cap across every query and page. Set 0 for no limit (explicit opt-in).", "default": 100 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Baidu throttles per IP, so a residential proxy is strongly recommended.", "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 } } }, "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 } } } } } } } } } }