{ "openapi": "3.0.1", "info": { "title": "Wikipedia Scraper", "description": "[💰 $0.6 / 1K] Search Wikipedia or fetch exact articles by URL or title, and extract clean structured data — summaries, full plain text, categories, 30-day pageviews, thumbnails, coordinates, and language counts — across 300+ language editions.", "version": "1.0", "x-build-id": "dR8H4sfMgNjkaoIvS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/solidcode~wikipedia-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-solidcode-wikipedia-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/solidcode~wikipedia-scraper/runs": { "post": { "operationId": "runs-sync-solidcode-wikipedia-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/solidcode~wikipedia-scraper/run-sync": { "post": { "operationId": "run-sync-solidcode-wikipedia-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": "Keywords to look up on Wikipedia, for example 'artificial intelligence' or 'climate change'. Each query runs its own search and returns the best-matching articles. Leave empty if you only want to fetch specific articles below.", "items": { "type": "string" } }, "articleUrls": { "title": "Article URLs or Titles", "type": "array", "description": "Fetch exact articles you already know. Paste full Wikipedia URLs (e.g. 'https://en.wikipedia.org/wiki/Alan_Turing') or just the page title (e.g. 'Alan Turing'). When a full URL is used, its language is detected automatically; bare titles use the language selected below.", "items": { "type": "string" } }, "language": { "title": "Language", "enum": [ "en", "de", "fr", "es", "it", "pt", "nl", "pl", "ru", "uk", "sv", "no", "da", "fi", "cs", "sk", "hu", "ro", "bg", "el", "tr", "ar", "he", "fa", "hi", "id", "vi", "th", "ja", "ko", "zh", "ca", "eu", "gl", "sr", "hr", "et", "lt", "lv", "sl" ], "type": "string", "description": "Which Wikipedia edition to use for searches and for bare titles above. Full URLs override this automatically.", "default": "en" }, "maxResultsPerSearch": { "title": "Max Results Per Search", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum number of articles to return for each search query (1-500; higher values are capped at 500). Articles fetched directly by URL or title are always included on top of this. Recommended 50-200 to keep runs fast and affordable.", "default": 50 }, "sortBy": { "title": "Sort Search Results By", "enum": [ "relevance", "popularity" ], "type": "string", "description": "How to order search results. Popularity favours articles with more incoming links and traffic.", "default": "relevance" }, "fullText": { "title": "Include Full Article Text", "type": "boolean", "description": "Return the complete plain-text body of each article instead of just the introductory summary. Useful for analysis and dataset building; increases dataset size.", "default": false }, "includeCategories": { "title": "Include Categories", "type": "boolean", "description": "Include the list of categories each article belongs to (e.g. 'British computer scientists', '1912 births'). Helpful for classification and topic mapping.", "default": true } } }, "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 } } } } } } } } } }