{ "openapi": "3.0.1", "info": { "title": "🔍 Baidu Search Scraper", "description": "Scrape Baidu search results at scale. Extract organic listings, answer boxes, related videos, related searches, and top searches. Supports bulk queries, proxy fallback, date filters, and device/language options for SEO and market research.", "version": "0.1", "x-build-id": "hDm9hX581xdvEqhX6" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scraper-engine~baidu-search-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scraper-engine-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scraper-engine~baidu-search-scraper/runs": { "post": { "operationId": "runs-sync-scraper-engine-baidu-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scraper-engine~baidu-search-scraper/run-sync": { "post": { "operationId": "run-sync-scraper-engine-baidu-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "🔎 Search Queries (required)", "type": "array", "description": "📝 **What to enter:** Baidu search URLs (e.g. https://www.baidu.com/s?wd=python) OR plain search terms (e.g. python tutorial, machine learning). Add one per line for bulk scraping.\n\n💡 **Tip:** Use plain terms for simplicity. URLs are parsed automatically to extract the query.", "items": { "type": "string" } }, "deviceType": { "title": "📱 Device Type", "enum": [ "desktop", "mobile", "tablet" ], "type": "string", "description": "đŸ–Ĩī¸ **Desktop** = www.baidu.com (default). 📱 **Mobile/Tablet** = m.baidu.com. Use to scrape mobile vs desktop SERP (different layouts & results).", "default": "desktop" }, "languageLocalization": { "title": "🌐 Language", "minimum": 1, "maximum": 3, "type": "integer", "description": "1 = All languages (default). 2 = Simplified Chinese (įŽ€äŊ“中文). 3 = Traditional Chinese (įšéĢ”中文). Affects search result language/region.", "default": 1 }, "startPage": { "title": "📄 Starting Page", "minimum": 1, "type": "integer", "description": "Page number to start scraping from. 1 = first page (default). Use 2+ to skip earlier pages (e.g. for pagination continuation).", "default": 1 }, "numResults": { "title": "📊 Results Per Page", "minimum": 1, "maximum": 50, "type": "integer", "description": "Number of results requested per page (1–50) via Baidu's own `rn` parameter, and the stride used to page forward. Baidu's actual returned count per page varies with query and device and is not guaranteed to match this number exactly. Use with maxPagination for total result cap.", "default": 10 }, "timePeriod": { "title": "📅 Time Period Filter", "type": "object", "description": "Optional date range filter. Leave empty for no filter (all results). Use Start Date + End Date for custom range, OR Days Ago for \"last N days\" (e.g. 7 = last week).", "properties": { "startDate": { "title": "📆 Start Date", "type": "string", "editor": "datepicker", "description": "From date (YYYY-MM-DD). Used with End Date for custom range. Ignored if Days Ago is set.", "default": "" }, "endDate": { "title": "📆 End Date", "type": "string", "editor": "datepicker", "description": "To date (YYYY-MM-DD). Used with Start Date for custom range. Ignored if Days Ago is set.", "default": "" }, "daysAgo": { "title": "⏱ī¸ Days Ago", "type": "integer", "description": "Alternative: filter to last N days. e.g. 7 = last week, 30 = last month. Set to 0 to disable (use Start/End dates or no filter).", "minimum": 0, "default": 0 } } }, "maxPagination": { "title": "📑 Maximum Pages", "minimum": 0, "maximum": 10, "type": "integer", "description": "Max pages to scrape per query. 0 = no limit (capped at 10). 3 = first 3 pages. More pages = more results but longer run time.", "default": 3 }, "outputFile": { "title": "💾 Output File", "type": "string", "description": "Optional custom key for key-value store. Results are always saved to Apify dataset. If set, also saves to KVS with this name for easy retrieval.", "default": "" }, "proxyConfiguration": { "title": "🔒 Proxy Configuration", "type": "object", "description": "By default: no proxy. If Baidu blocks → datacenter → residential (3 retries). Enable Apify proxy here if you want to start with proxy. Fallback still applies when blocked." } } }, "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 } } } } } } } } } }