{ "openapi": "3.0.1", "info": { "title": "Toutiao Scraper - Chinese News & Article Data API", "description": "Scrape Toutiao (Jinri Toutiao) at scale: keyword-search Chinese news articles, extract full article content, engagement metrics (reads, comments, likes) and creator profiles. Export clean structured JSON for media monitoring, content intelligence and ByteDance research.", "version": "1.0", "x-build-id": "gu1tFLCQX5VtRyzGe" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sian.agency~toutiao-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sian.agency-toutiao-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sian.agency~toutiao-scraper/runs": { "post": { "operationId": "runs-sync-sian.agency-toutiao-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sian.agency~toutiao-scraper/run-sync": { "post": { "operationId": "run-sync-sian.agency-toutiao-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "operation": { "title": "Operation", "enum": [ "searchArticles", "articleDetail", "userProfile", "resolveUserId" ], "type": "string", "description": "Which Toutiao data to scrape. Each operation reads its own input field(s) below.", "default": "searchArticles" }, "keyword": { "title": "Keyword (Search Articles)", "type": "string", "description": "πŸ” A single search keyword β€” returns Toutiao articles with title, link, author, publish time and engagement metrics. Used by the Search Articles operation.", "default": "δΊΊε·₯智能" }, "articleId": { "title": "Article ID or URL (Article Detail)", "type": "string", "description": "πŸ“° A single Toutiao article ID (the 19-digit group ID) or a full toutiao.com article URL β€” returns the complete article content, images and author. Used by the Article Detail operation." }, "userId": { "title": "User ID (User Profile)", "type": "string", "description": "πŸ‘€ A single Toutiao creator user ID β€” returns the creator profile (name, avatar, follower/publish counts, external links). Used by the User Profile operation." }, "profileUrl": { "title": "Profile URL (Resolve User ID)", "type": "string", "description": "πŸ”— A single Toutiao creator profile URL (e.g. https://www.toutiao.com/c/user/token/…) β€” returns the numeric creator ID. Used by the Resolve User ID operation." }, "keywords": { "title": "Keywords β€” bulk (Search Articles)", "type": "array", "description": "πŸ” Multiple search keywords to process in one run (one search each). Used by the Search Articles operation.", "items": { "type": "string" } }, "articleIds": { "title": "Article IDs or URLs β€” bulk (Article Detail)", "type": "array", "description": "πŸ“° Multiple article IDs or URLs to fetch in one run. Used by the Article Detail operation.", "items": { "type": "string" } }, "userIds": { "title": "User IDs β€” bulk (User Profile)", "type": "array", "description": "πŸ‘€ Multiple creator user IDs to fetch in one run. Used by the User Profile operation.", "items": { "type": "string" } }, "profileUrls": { "title": "Profile URLs β€” bulk (Resolve User ID)", "type": "array", "description": "πŸ”— Multiple creator profile URLs to resolve in one run. Used by the Resolve User ID operation.", "items": { "type": "string" } } } }, "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 } } } } } } } } } }