{
"openapi": "3.0.1",
"info": {
"title": "Wikipedia Data Scraper Pro",
"description": "An automated crawler that extracts textual content and metadata from Wikipedia pages for building knowledge bases.",
"version": "0.0",
"x-build-id": "El3QCPERcfBnkKdBA"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/moving_beacon-owner1~my-actor-39/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-moving_beacon-owner1-my-actor-39",
"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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/moving_beacon-owner1~my-actor-39/runs": {
"post": {
"operationId": "runs-sync-moving_beacon-owner1-my-actor-39",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/moving_beacon-owner1~my-actor-39/run-sync": {
"post": {
"operationId": "run-sync-moving_beacon-owner1-my-actor-39",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": [
"mode"
],
"properties": {
"mode": {
"title": "Scrape Mode",
"enum": [
"page",
"category",
"translations"
],
"type": "string",
"description": "Choose what to scrape:
page – one or more article pages
category – all pages inside a category tree
translations – compare one article across multiple languages",
"default": "page"
},
"topics": {
"title": "Article Titles",
"type": "array",
"description": "Exact Wikipedia article titles to scrape (used in page mode). E.g. Python (programming language), Alan Turing.",
"default": [
"Python (programming language)"
],
"items": {
"type": "string"
}
},
"categoryTitle": {
"title": "Category Title",
"type": "string",
"description": "Full category name to crawl (used in category mode). Must include the Category: prefix. E.g. Category:Physics."
},
"comparisonTitle": {
"title": "Article for Translation Comparison",
"type": "string",
"description": "English Wikipedia title to compare across languages (used in translations mode)."
},
"language": {
"title": "Wikipedia Language",
"enum": [
"en",
"de",
"fr",
"es",
"it",
"pt",
"ja",
"zh",
"ar",
"ru",
"pl",
"nl",
"sv",
"ko",
"fa"
],
"type": "string",
"description": "Language code for the Wikipedia edition to scrape (ISO 639-1). Ignored in translations mode.",
"default": "en"
},
"translationLanguages": {
"title": "Languages for Translation Comparison",
"type": "array",
"description": "Language codes to fetch in translations mode. Leave empty to fetch all available translations.",
"default": [
"en",
"de",
"fr",
"ja",
"ar",
"es",
"zh",
"ru"
],
"items": {
"type": "string"
}
},
"categoryMaxDepth": {
"title": "Category Depth",
"minimum": 0,
"maximum": 4,
"type": "integer",
"description": "How many subcategory levels to follow in category mode. 0 = top-level articles only.",
"default": 1
},
"maxPages": {
"title": "Max Pages (Category Mode)",
"minimum": 1,
"maximum": 500,
"type": "integer",
"description": "Maximum number of article pages to scrape in category mode.",
"default": 20
},
"includeSections": {
"title": "Include Nested Section Tree",
"type": "boolean",
"description": "Store the full nested section structure (title + text + subsections). Note: flat section text is always included in fullTextBySections regardless of this setting.",
"default": true
},
"includeLinks": {
"title": "Include Outbound Links",
"type": "boolean",
"description": "Collect links to other Wikipedia articles found on each page (capped at 50).",
"default": true
},
"includeCategories": {
"title": "Include Page Categories",
"type": "boolean",
"description": "Collect the Wikipedia categories each article belongs to.",
"default": true
},
"includeTranslations": {
"title": "Include Language Links",
"type": "boolean",
"description": "Collect URLs of the same article in other languages (langlinks). Adds one extra API call per page.",
"default": false
},
"requestDelay": {
"title": "Request Delay (seconds)",
"minimum": 0.1,
"maximum": 10,
"type": "number",
"description": "Seconds to wait between Wikipedia API calls. Increase if you encounter rate-limiting.",
"default": 0.5
},
"proxyConfiguration": {
"title": "Proxy Configuration",
"type": "object",
"description": "Optional proxy settings for Wikipedia API requests."
}
}
},
"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
}
}
}
}
}
}
}
}
}
}