{ "openapi": "3.0.1", "info": { "title": "Wikipedia Scraper - Full Article Text and Search", "description": "Search Wikipedia by keyword, or fetch exact article titles in any language edition. Search rows give the snippet, word count, size and last edit. Title rows give the intro or the whole article as plain text, the lead image and the categories. $1.00 per 1,000 pages.", "version": "0.1", "x-build-id": "CZHhCQ783TW2jovQR" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dami_studio~wikipedia-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dami_studio-wikipedia-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/dami_studio~wikipedia-scraper/runs": { "post": { "operationId": "runs-sync-dami_studio-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/dami_studio~wikipedia-scraper/run-sync": { "post": { "operationId": "run-sync-dami_studio-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": { "searchQuery": { "title": "Search query", "type": "string", "description": "Keywords to search Wikipedia for (e.g. \"machine learning\"). Returns matching pages with snippet, word count, and URL. Leave empty if you instead provide exact Page titles below." }, "fullText": { "title": "Fetch full article text", "type": "boolean", "description": "Only applies in Page titles mode. When on, returns the whole article as plain text instead of just the intro paragraph(s).", "default": false }, "language": { "title": "Wikipedia language", "type": "string", "description": "Wikipedia language edition code, e.g. en, fr, de, es, ja. Picks the host {lang}.wikipedia.org.", "default": "en" }, "pageTitles": { "title": "Page titles (instead of search)", "type": "array", "description": "Exact Wikipedia article titles to fetch full data for (plain-text extract, thumbnail, categories, URL). Batched 50 at a time. Use this OR a search query.", "default": [], "items": { "type": "string" } }, "maxItems": { "title": "Max items", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Maximum number of pages to return. In search mode the actor paginates until it reaches this. In page-titles mode it caps how many titles are fetched.", "default": 50 }, "notionConnector": { "title": "Notion connector (optional)", "type": "string", "description": "Optional. Write each page as a page into your Notion when the run finishes. Authorize a Notion connector once in Settings → API & Integrations → MCP connectors, then pick it here. Leave empty to skip (default), results are always saved to the dataset regardless." }, "notionParentId": { "title": "Notion target data source ID", "type": "string", "description": "Optional. The Notion data source ID of the database to write into (only used if a Notion connector is set). Leave empty to create the pages privately in your workspace instead." }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional, and not needed for a normal run.", "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 } } } } } } } } } }