{ "openapi": "3.0.1", "info": { "title": "Wikipedia & Wikidata API — Articles, Search & Pageviews", "description": "Wikipedia search, article text (intro or full), descriptions, categories and Wikidata ids; daily human pageviews and a day's top 1,000; Wikidata entities with flattened properties. Any language edition, no API key, no browser. Diagnostics and empty runs are free.", "version": "0.1", "x-build-id": "f3I0MPZlE8tMwofWV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/insight.solutions~wikipedia-api/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-insight.solutions-wikipedia-api", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/insight.solutions~wikipedia-api/runs": { "post": { "operationId": "runs-sync-insight.solutions-wikipedia-api", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/insight.solutions~wikipedia-api/run-sync": { "post": { "operationId": "run-sync-insight.solutions-wikipedia-api", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "language": { "title": "Wikipedia language", "pattern": "^[a-zA-Z-]{2,12}$", "type": "string", "description": "The Wikipedia edition to read, as its subdomain: `en`, `de`, `fr`, `es`, `ja`, `zh`, `pt`, `simple` … Every edition works. Used for search, titles, categories, pageviews, the top list and the language of Wikidata labels. A title given as a URL keeps the language of its own URL.", "default": "en" }, "queries": { "title": "Search queries", "type": "array", "description": "Full-text Wikipedia searches, one per entry, e.g. `[\"web scraping\"]`. Each hit is one `search-result` row with its snippet, size, word count and last-edit time, up to `maxResults` per query.", "default": [], "items": { "type": "string" } }, "titles": { "title": "Article titles or URLs", "type": "array", "description": "Articles to fetch, as titles (`Web scraping`, `Web_scraping`) or URLs (`https://de.wikipedia.org/wiki/Screen_Scraping`). Each becomes one `article` row. Duplicates and redirects to the same page are fetched and charged once.", "default": [], "items": { "type": "string" } }, "categories": { "title": "Categories", "type": "array", "description": "Categories whose articles to fetch, e.g. `Category:Web scraping` (the prefix is optional). Only the category's own articles are read — subcategories are not descended into — up to `maxResults` per category, and each becomes an `article` row.", "default": [], "items": { "type": "string" } }, "maxResults": { "title": "Max results per entry", "minimum": 1, "maximum": 10000, "type": "integer", "description": "The most rows one query, category, top-views day or Wikidata search may return. Searches page 50 at a time, categories 500 at a time.", "default": 50 }, "articleContent": { "title": "Article text", "enum": [ "intro", "full", "none" ], "type": "string", "description": "`intro` returns the lead section as plain text (titles are fetched twenty per request). `full` returns the whole article as plain text, up to `maxTextChars` (one request per article). `none` returns no article rows at all — use it when you only want search results or pageviews.", "default": "intro" }, "fetchArticlesForSearch": { "title": "Fetch an article for every search hit", "type": "boolean", "description": "Also return an `article` row (with the text chosen above) for every search hit. Adds one request per 20 hits for intros, one per hit for full text.", "default": false }, "maxTextChars": { "title": "Max text characters", "minimum": 100, "maximum": 1000000, "type": "integer", "description": "Cap on `text`. A longer article is cut here and marked `textTruncated: true`; `textChars` and `wordCount` still describe the whole extract.", "default": 50000 }, "includeCategories": { "title": "Include categories", "type": "boolean", "description": "The article's visible categories (up to 50; hidden maintenance categories are excluded). No extra request.", "default": true }, "includeSections": { "title": "Include section outline", "type": "boolean", "description": "The table of contents as `sections[] { level, title, anchor, index, number }`. One extra request per article.", "default": false }, "includeLinks": { "title": "Include links", "type": "boolean", "description": "The first 500 article links, first 100 external links and the number of pages linking here (first 100). `linksCountIsPartial` is true when any list had more. One extra request per article.", "default": false }, "includeRevisions": { "title": "Include recent revisions", "type": "boolean", "description": "The last 20 revisions as `lastRevisions[] { revid, timestamp, comment, size }`. Editor usernames are never read or returned, and names inside edit summaries are replaced with `[editor]`. One extra request per article.", "default": false }, "pageviews": { "title": "Pageviews", "enum": [ "none", "last30", "last90", "range" ], "type": "string", "description": "Daily pageviews for every article in the run (titles, category members, and search hits when articles are fetched for them): one `pageviews` row per title with the series, total, daily average and peak day. Human traffic only (agent `user`): crawlers and bots are excluded. `last30` and `last90` end yesterday, the newest day the API has.", "default": "none" }, "pageviewsFrom": { "title": "Pageviews from", "type": "string", "description": "First day of the `range` window, `YYYYMMDD` or `YYYY-MM-DD`. Data starts on 2015-07-01." }, "pageviewsTo": { "title": "Pageviews to", "type": "string", "description": "Last day of the `range` window, `YYYYMMDD` or `YYYY-MM-DD`." }, "topViews": { "title": "Top articles of a day", "type": "array", "description": "Dates (`YYYY-MM-DD`) whose most-read articles to return: up to 1,000 per day from the pageviews API, one `pageviews` row each with `rank` and `views`, capped by `maxResults`. The main page, `Special:` pages and other non-article pages are left out unless you tick the box below.", "default": [], "items": { "type": "string" } }, "keepSpecialPages": { "title": "Keep non-article pages in top lists", "type": "boolean", "description": "Keep `Main_Page`, `Special:Search`, `Wikipedia:`, `File:`, `Portal:` and similar entries in a top list.", "default": false }, "wikidataIds": { "title": "Wikidata ids", "type": "array", "description": "Entities to fetch, e.g. `[\"Q42\", \"Q95\"]` or `https://www.wikidata.org/wiki/Q42`. Each becomes one `entity` row with its label, description, aliases, Wikipedia link and the properties below.", "default": [], "items": { "type": "string" } }, "wikidataSearch": { "title": "Wikidata search", "type": "array", "description": "Names to look up on Wikidata, e.g. `[\"Apify\"]`. Up to `maxResults` matching entities per name, each an `entity` row.", "default": [], "items": { "type": "string" } }, "entityProperties": { "title": "Entity properties", "type": "array", "description": "Wikidata properties to flatten into `properties`, as ids (`P31`) or the bundled names (`instanceOf`). Item values come back as `{ id, label }`, dates at their real precision, images and logos as Commons URLs. Contact details (email, phone, address, personal social handles) are never extracted.", "default": [ "P31", "P17", "P131", "P159", "P571", "P856", "P1128", "P452", "P112", "P169", "P1454", "P625", "P18" ], "items": { "type": "string" } }, "includeRawClaims": { "title": "Include raw claims", "type": "boolean", "description": "Also return every statement in Wikidata's own JSON as `claimsRaw` (large: Q42 has 354). Contact-detail properties are removed from it too.", "default": false }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Requests in flight at once, across everything the run is doing. Requests also start at least 100 ms apart, so a run never exceeds 10 requests a second.", "default": 4 }, "maxRunSecs": { "title": "Time budget (seconds)", "minimum": 30, "maximum": 3600, "type": "integer", "description": "Stop after this many seconds. Rows already returned are kept and a free `deadline` row says what was left.", "default": 240 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Every Wikimedia endpoint answered from the Apify datacenter proxy (and with no proxy at all), so datacenter is the default and residential buys nothing here.", "default": { "useApifyProxy": 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 }, "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 } } } } } } } } } }