{
"openapi": "3.0.1",
"info": {
"title": "Toutiao News Search Scraper (今日头条)",
"description": "Search Toutiao (今日头条) news by keyword or link: headline, publisher and verification, publish time, summary, Toutiao and original links, image, reads, comments, likes, categories. ~50-130 results per query, only-new mode for daily monitoring. Pay per result: $1 per 1,000 articles.",
"version": "1.0",
"x-build-id": "hqkVPVIrtftGdBtn1"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/brii3343~toutiao-news-search-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-brii3343-toutiao-news-search-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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/brii3343~toutiao-news-search-scraper/runs": {
"post": {
"operationId": "runs-sync-brii3343-toutiao-news-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/brii3343~toutiao-news-search-scraper/run-sync": {
"post": {
"operationId": "run-sync-brii3343-toutiao-news-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": {
"searchQueries": {
"title": "Search queries",
"type": "array",
"description": "What to search in Toutiao news (头条资讯), one per line, in Chinese or English, for example 人工智能 or 新能源汽车. Each query is one search, read page by page (Toutiao shows about 50-130 news results per query, depending on the term).",
"items": {
"type": "string"
}
},
"startUrls": {
"title": "Toutiao search URLs",
"type": "array",
"description": "Toutiao news search links, for example https://so.toutiao.com/search?keyword=%E6%96%B0%E8%83%BD%E6%BA%90%E6%B1%BD%E8%BD%A6&pd=information. Reading starts from the page in the link (page_num).",
"items": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"title": "URL of a web page",
"format": "uri"
}
}
}
},
"maxItemsPerSource": {
"title": "Max results per search or URL",
"minimum": 0,
"type": "integer",
"description": "Results to save for each search query and each URL. 0 = everything the site shows.",
"default": 50
},
"onlyNewArticles": {
"title": "Only new articles (skip ones from earlier runs)",
"type": "boolean",
"description": "For scheduled monitoring: when on, the Actor remembers the ids of the articles it delivered (in a named key-value store of your account, see Memory name) and delivers and charges only articles not delivered in earlier runs. It reads every page of the search (Toutiao does not sort by date, so new articles can be anywhere in the list). If nothing is new you get a free no_results row. Off = every run returns all results.",
"default": false
},
"maxItems": {
"title": "Max results in total",
"minimum": 0,
"type": "integer",
"description": "Stop after this many results in the whole run. 0 = no limit.",
"default": 0
},
"memoryName": {
"title": "Memory name (for Only new articles)",
"type": "string",
"description": "Name of the key-value store that keeps the delivered article ids when Only new articles is on (3-63 letters, digits and hyphens). Use a different name for each task you schedule, so that tasks do not skip each other's articles. Empty = toutiao-delivered-ids."
},
"proxyConfiguration": {
"title": "Proxy",
"type": "object",
"description": "Not needed: the scraper connects directly and switches to Apify Proxy by itself only when Toutiao blocks it. Set a proxy here only to force one.",
"default": {
"useApifyProxy": false
}
}
}
},
"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
}
}
}
}
}
}
}
}
}
}