{ "openapi": "3.0.1", "info": { "title": "Wikipedia Articles Scraper", "description": "Wikipedia articles with daily pageview history and Wikidata facts attached. Flags the silent redirects Wikipedia never reports - asking for 'AI' returns 'Artificial intelligence' with nothing saying so - and reports the 10,000-result retrieval cap that sits under a far larger hit count.", "version": "0.1", "x-build-id": "307Hb0bNz0angVZa3" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapyx~wikipedia-articles-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapyx-wikipedia-articles-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapyx~wikipedia-articles-scraper/runs": { "post": { "operationId": "runs-sync-scrapyx-wikipedia-articles-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapyx~wikipedia-articles-scraper/run-sync": { "post": { "operationId": "run-sync-scrapyx-wikipedia-articles-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "What to collect", "enum": [ "search", "articles" ], "type": "string", "description": "search = search the encyclopedia. articles = look up titles you name.", "default": "search" }, "searchTerm": { "title": "Search term", "type": "string", "description": "For mode='search'. Note Wikipedia reports the true match count but caps RETRIEVAL at 10,000 results — a query matching 57,800 articles can only ever hand back 10,000 of them, and it says so with a named error rather than an empty page." }, "titles": { "title": "Article titles or URLs", "type": "array", "description": "For mode='articles'. A title like `Machine learning` or a full wikipedia.org/wiki/ URL. NOTE that a title which merely redirects resolves SILENTLY — asking for 'AI' returns 'Artificial intelligence' with nothing in the response saying so. Every row carries requestedTitle, resolvedTitle and wasRedirected.", "items": { "type": "string" } }, "language": { "title": "Language edition", "type": "string", "description": "Wikipedia language code — en, de, fr, id, es and so on.", "default": "en" }, "includePageviews": { "title": "Include daily pageview history", "type": "boolean", "description": "Adds how much traffic each article actually gets — daily series, total and mean — at one extra request per article. This is the field that turns an article dump into an attention dataset.", "default": false }, "includeWikidata": { "title": "Include Wikidata facts", "type": "boolean", "description": "Adds the linked Wikidata entity's label, description, claim count and instance-of types. The join key is free — the summary response already carries it — but the lookup costs one extra request per article.", "default": false }, "pageviewDays": { "title": "Days of pageview history", "minimum": 1, "maximum": 365, "type": "integer", "description": "Up to 365. Data lags by one day.", "default": 30 }, "maxResults": { "title": "Max articles", "minimum": 0, "type": "integer", "description": "A CEILING, not a promise: search pages overlap and Wikipedia's live index shifts between requests, so a capped walk can finish a row or two short. Set 0 for unlimited (still bounded by the 10,000 retrieval cap).", "default": 50 }, "maxConcurrency": { "title": "Max concurrent requests", "minimum": 1, "maximum": 10, "type": "integer", "description": "Article lookups in flight at once. Keep it modest — Wikimedia asks automated clients to be identifiable and well-behaved.", "default": 4 }, "minRequestInterval": { "title": "Min seconds between request starts", "minimum": 0, "maximum": 30, "type": "integer", "description": "Politeness pacing shared across all workers. 0 uses the built-in default.", "default": 0 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "OFF by default, deliberately. These are public APIs with no WAF, and Wikimedia's policy asks automated clients to be identifiable — routing this traffic through a shared residential pool would make it harder for them to attribute and rate-limit fairly.", "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 } } }, "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 } } } } } } } } } }