{ "openapi": "3.0.1", "info": { "title": "Baidu Search Scraper", "description": "Scrape Baidu search results - web, image, and news. Extract titles, URLs, snippets, dates, and image metadata for any query with advanced filters (time range, filetype, language, site restriction, exact phrase, exclude words).", "version": "1.0", "x-build-id": "LRuWQF9X9KmxGrhyH" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/crawlerbros~baidu-search-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-crawlerbros-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/crawlerbros~baidu-search-scraper/runs": { "post": { "operationId": "runs-sync-crawlerbros-baidu-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/crawlerbros~baidu-search-scraper/run-sync": { "post": { "operationId": "run-sync-crawlerbros-baidu-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "queries" ], "properties": { "mode": { "title": "Search mode", "enum": [ "webSearch", "imageSearch", "newsSearch" ], "type": "string", "description": "Which Baidu vertical to scrape.", "default": "webSearch" }, "queries": { "title": "Search queries", "type": "array", "description": "One or more search terms. Each query is scraped independently up to maxResults.", "default": [ "artificial intelligence" ], "items": { "type": "string" } }, "maxResults": { "title": "Max results per query", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum number of results to return for each query (across all pages).", "default": 50 }, "timeRange": { "title": "Time range", "enum": [ "any", "day", "week", "month", "year" ], "type": "string", "description": "Restrict results to a publication time window. Applies to webSearch and newsSearch modes only; Baidu image search has no time filter.", "default": "any" }, "language": { "title": "Language filter", "enum": [ "any", "simplified", "traditional" ], "type": "string", "description": "Restrict results to pages in a specific Chinese script. Only applies to webSearch mode.", "default": "any" }, "filetype": { "title": "File type filter", "enum": [ "any", "pdf", "doc", "xls", "ppt", "rtf" ], "type": "string", "description": "Restrict results to a specific document format. Only applies to webSearch mode.", "default": "any" }, "siteRestrict": { "title": "Restrict to domain", "type": "string", "description": "Limit results to a specific website domain (e.g. wikipedia.org). Equivalent to the site: operator. Only applies to webSearch mode." }, "exactPhrase": { "title": "Exact phrase", "type": "string", "description": "Require results containing this exact phrase. Wrapped in quotes automatically. Only applies to webSearch mode." }, "excludeWords": { "title": "Exclude words", "type": "array", "description": "Words to exclude from results. Each is prefixed with the minus (-) operator. Only applies to webSearch mode.", "default": [], "items": { "type": "string" } }, "titleOnly": { "title": "Search title only", "type": "boolean", "description": "When enabled, Baidu matches search terms in page titles only (intitle: operator). Only applies to webSearch mode.", "default": false }, "resolveUrls": { "title": "Resolve Baidu redirect URLs", "type": "boolean", "description": "When enabled, follows Baidu redirect links to extract the actual destination URL. The real URL is always extracted from the page when available, so this mainly affects fallback behaviour. Only applies to webSearch mode.", "default": true }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings for accessing Baidu. Using Apify Proxy (AUTO datacenter group) is strongly recommended for non-Chinese IP addresses to avoid blocks." } } }, "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 } } } } } } } } } }