{ "openapi": "3.0.1", "info": { "title": "Wikipedia Scraper — Search, Summaries & Full Text", "description": "Search Wikipedia and get article summaries or full plain-text content in any language: title, extract, description, thumbnail, coordinates, categories, links count, last edit. Built for research and RAG agents. No API key.", "version": "0.1", "x-build-id": "zPCibRznydeJLFXlD" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/yadroo~wikipedia-search/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-yadroo-wikipedia-search", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/yadroo~wikipedia-search/runs": { "post": { "operationId": "runs-sync-yadroo-wikipedia-search", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/yadroo~wikipedia-search/run-sync": { "post": { "operationId": "run-sync-yadroo-wikipedia-search", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "queries" ], "properties": { "queries": { "title": "Search queries or page titles", "type": "array", "description": "One entry per lookup: a free-text query, a company/person/place name, or an exact page title. Each query yields up to resultsPerQuery pages.", "items": { "type": "string" } }, "lang": { "title": "Language edition", "type": "string", "description": "Wikipedia language code: en, de, fr, es, ru, zh, ja, ar, kk, uz, simple, zh-yue… (any of ~340 editions; the ~100 major ones are listed in the README). Lower-case.", "default": "en" }, "searchMode": { "title": "How to match queries", "enum": [ "text", "title", "nearmatch", "exact" ], "type": "string", "description": "`text` ranks pages by relevance (like the site search box). `exact` treats each query as a page title and fetches it directly — use it when you already know the title (e.g. from a previous run or Wikidata).", "default": "text" }, "resultsPerQuery": { "title": "Pages per query", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many top search hits to save per query (ignored for exact).", "default": 1 }, "skipDisambiguation": { "title": "Skip disambiguation pages", "type": "boolean", "description": "Do not save pages that are disambiguation lists (they are still flagged with isDisambiguation when kept).", "default": false }, "mode": { "title": "Text content", "enum": [ "summary", "full", "metadata" ], "type": "string", "description": "`summary` = lead paragraph(s) via the REST summary endpoint; `full` = the complete article as plain text (headings kept as == Heading ==); `metadata` = title/description/url only.", "default": "summary" }, "maxTextChars": { "title": "Max full-text characters", "minimum": 0, "maximum": 2000000, "type": "integer", "description": "Truncate fullText at this length (0 = whole article). fullTextChars always holds the original length.", "default": 0 }, "includeSections": { "title": "Include section outline", "type": "boolean", "description": "Table of contents: [{level, title, chars}] (chars only in full mode).", "default": false }, "includeCategories": { "title": "Include categories", "type": "boolean", "description": "Visible categories of the page (up to 100).", "default": false }, "includeLinks": { "title": "Include internal links", "type": "boolean", "description": "Titles of linked articles (entity graph / related pages).", "default": false }, "maxLinks": { "title": "Max links", "minimum": 1, "maximum": 500, "type": "integer", "description": "Cap for includeLinks.", "default": 50 }, "includeLangLinks": { "title": "Include other-language versions", "type": "boolean", "description": "languages (codes), languagesCount and langLinks [{lang, title, url}] — e.g. to fetch the Russian or Kazakh article next.", "default": false }, "includeImages": { "title": "Include images list", "type": "boolean", "description": "Up to 20 images with URL and caption (thumbnail/originalImage are always included when available).", "default": false }, "includeWikidata": { "title": "Include Wikidata facts", "type": "boolean", "description": "Structured facts from the linked Wikidata item: instance of, country, headquarters, inception, founders, CEO, industry, employees, revenue, website, ticker/ISIN/LEI, social handles, coordinates, birth/death dates, occupation… (see README). Item values are resolved to labels.", "default": false }, "includePageviews": { "title": "Include pageviews", "type": "boolean", "description": "Daily human pageviews (all platforms) for the last pageviewsDays: total, average per day, peak day — a free popularity/attention signal.", "default": false }, "pageviewsDays": { "title": "Pageviews window (days)", "minimum": 1, "maximum": 365, "type": "integer", "description": "Window ending yesterday (UTC).", "default": 30 }, "includeDailyPageviews": { "title": "Include daily pageview series", "type": "boolean", "description": "Add pageviews.daily [{date, views}] for charting/anomaly detection.", "default": false }, "dedupe": { "title": "Deduplicate pages across queries", "type": "boolean", "description": "Save each page once even if several queries resolve to it.", "default": true }, "fields": { "title": "Output fields", "type": "array", "description": "Keep only these output fields, e.g. [\"query\",\"title\",\"extract\",\"url\"]. Empty = all.", "items": { "type": "string" } } } }, "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 } } } } } } } } } }