{ "openapi": "3.0.1", "info": { "title": "Wikipedia Article Extractor", "description": "Extract Wikipedia articles via MediaWiki API. Get full text, summaries, sections, categories, images, links. Multi-language. Perfect for AI/ML training data and RAG.", "version": "0.1", "x-build-id": "YtXv5EeUHuouPEB8o" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/glassventures~wikipedia-article-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-glassventures-wikipedia-article-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/glassventures~wikipedia-article-extractor/runs": { "post": { "operationId": "runs-sync-glassventures-wikipedia-article-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/glassventures~wikipedia-article-extractor/run-sync": { "post": { "operationId": "run-sync-glassventures-wikipedia-article-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Wikipedia URLs", "type": "array", "description": "Direct URLs to Wikipedia articles. Supports any language Wikipedia.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "articleTitles": { "title": "Article Titles", "type": "array", "description": "Wikipedia article titles to extract (e.g., \"Albert Einstein\", \"Machine learning\"). Uses the selected language.", "items": { "type": "string" } }, "searchTerms": { "title": "Search Terms", "type": "array", "description": "Search Wikipedia for articles matching these terms. Returns the top results for each query.", "items": { "type": "string" } }, "categories": { "title": "Category Names", "type": "array", "description": "Extract all articles from Wikipedia categories (e.g., \"Machine learning\", \"Natural language processing\"). Don't include the \"Category:\" prefix.", "items": { "type": "string" } }, "language": { "title": "Language", "enum": [ "en", "es", "fr", "de", "ja", "pt", "it", "ru", "zh", "ko", "ar", "hi" ], "type": "string", "description": "Wikipedia language edition to use.", "default": "en" }, "includeFullText": { "title": "Include Full Text", "type": "boolean", "description": "Extract the complete article text in plain text format. Ideal for AI/ML training data and RAG pipelines.", "default": true }, "includeSections": { "title": "Include Sections", "type": "boolean", "description": "Extract article sections with headings and text. Useful for structured content analysis.", "default": true }, "includeCategories": { "title": "Include Categories", "type": "boolean", "description": "Extract the list of categories the article belongs to.", "default": true }, "includeLinks": { "title": "Include Links", "type": "boolean", "description": "Extract internal Wikipedia links from the article. Can produce large output.", "default": false }, "includeImages": { "title": "Include Images", "type": "boolean", "description": "Extract image URLs from the article via Wikimedia Commons.", "default": false }, "maxItems": { "title": "Max Articles", "minimum": 0, "type": "integer", "description": "Maximum number of articles to extract. Use 0 for unlimited.", "default": 100 }, "proxyConfig": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings. Wikipedia API is public so proxies are optional, but can help avoid rate limits at scale." } } }, "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 } } } } } } } } } }