{ "openapi": "3.0.1", "info": { "title": "Baidu Search Scraper — China SERP Results API", "description": "Scrape Baidu (百度) search results pages — organic ranks, titles, real URLs, snippets, ads, related queries, and answer boxes. China Residential proxy recommended. MCP-ready.", "version": "0.1", "x-build-id": "skUiVzZMUMbeQeWyJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/khadinakbar~scrape-baidu-serp/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-khadinakbar-scrape-baidu-serp", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/khadinakbar~scrape-baidu-serp/runs": { "post": { "operationId": "runs-sync-khadinakbar-scrape-baidu-serp", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/khadinakbar~scrape-baidu-serp/run-sync": { "post": { "operationId": "run-sync-khadinakbar-scrape-baidu-serp", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Use this when the user provides Baidu keywords. Prefer Simplified Chinese terms for best yield (e.g. 苹果手机). Each query produces one dataset row per results page. Do not put baidu.com/s URLs here — use startUrls.", "items": { "type": "string" } }, "startUrls": { "title": "Direct Baidu Search URLs", "type": "array", "description": "Use when the user pastes a Baidu search URL such as https://www.baidu.com/s?wd=.... Pagination and language are taken from the URL. Prefer queries for plain keywords.", "default": [], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPagesPerQuery": { "title": "Max Result Pages Per Query", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many Baidu result pages to scrape per query. Page 1 = pn=0, page 2 = pn=10 when resultsPerPage=10. Each successful page is one serp-page billing event.", "default": 1 }, "resultsPerPage": { "title": "Results Per Page (rn)", "minimum": 10, "maximum": 50, "type": "integer", "description": "Baidu rn parameter. Default 10. Baidu often ignores values above 10–50.", "default": 10 }, "device": { "title": "Device", "enum": [ "desktop", "mobile" ], "type": "string", "description": "desktop and mobile both use www.baidu.com/s; mobile swaps in a mobile User-Agent (m.baidu path dropped for yield).", "default": "desktop" }, "languageFilter": { "title": "Language Filter", "enum": [ "any", "simplified", "traditional" ], "type": "string", "description": "Bias Baidu toward Simplified or Traditional Chinese results, or leave any.", "default": "any" }, "timeRange": { "title": "Time Range", "enum": [ "any", "day", "week", "month", "year" ], "type": "string", "description": "Optional Baidu recency filter via gpc (day / week / month / year).", "default": "any" }, "includeAds": { "title": "Extract Ad Results", "type": "boolean", "description": "Include Baidu commercial/ad blocks (广告) in ad_results when present.", "default": true }, "includeRelatedSearches": { "title": "Extract Related Searches", "type": "boolean", "description": "Extract 相关搜索 suggestions from the bottom of the SERP into related_searches.", "default": true }, "includeAnswerBox": { "title": "Extract Answer / Baike Box", "type": "boolean", "description": "Extract Baidu answer/百科/exact-QA boxes when present into answer_box.", "default": true }, "resolveRealUrls": { "title": "Resolve Real Destination URLs", "type": "boolean", "description": "Follow baidu.com/link?url= redirects to the destination URL. Uses extra proxy requests; disable to keep redirect URLs only.", "default": true }, "maxConcurrency": { "title": "Max Concurrency", "minimum": 1, "maximum": 5, "type": "integer", "description": "Parallel Baidu requests. Keep low (1–2) to reduce captchas. Max 5.", "default": 2 }, "maxTotalChargeUsd": { "title": "Max Total Charge (USD)", "minimum": 0.01, "type": "number", "description": "Optional hard cost precheck. If worst-case serp-page charges exceed this amount, the run exits INVALID_INPUT without scraping." }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Use Apify Residential with country China (CN). Datacenter and non-CN IPs are frequently blocked by Baidu.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ], "apifyProxyCountry": "CN" } } } }, "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 } } } } } } } } } }