{ "openapi": "3.0.1", "info": { "title": "Wikipedia Scraper [$0.7💰 / 1k]", "description": "Extract structured data from Wikipedia articles only $0.7/1k: infobox fields, section headings, tables, and raw wikitext. Uses Wikipedia REST API for structured data. Supports all language editions. Ideal for researchers, educators, AI trainers, and knowledge graph builders", "version": "1.0", "x-build-id": "bkTLTzrtdayXdEq67" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ahmed_jasarevic~wikipedia-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ahmed_jasarevic-wikipedia-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/ahmed_jasarevic~wikipedia-scraper/runs": { "post": { "operationId": "runs-sync-ahmed_jasarevic-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/ahmed_jasarevic~wikipedia-scraper/run-sync": { "post": { "operationId": "run-sync-ahmed_jasarevic-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", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "minItems": 1, "type": "array", "description": "URLs to start scraping from (Wikipedia article URLs).", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "extractInfobox": { "title": "Extract Infobox", "type": "boolean", "description": "Whether to extract infobox key-value pairs from the top-right infobox.", "default": true }, "extractSectionHeadings": { "title": "Extract Section Headings", "type": "boolean", "description": "Whether to extract section headings (h2, h3) and their hierarchy.", "default": true }, "extractMainText": { "title": "Extract Article Text", "type": "boolean", "description": "Whether to extract the full article text plus per-section text of each page.", "default": true }, "maxSectionTextLength": { "title": "Max Text Length per Section", "minimum": 0, "type": "integer", "description": "Maximum number of characters stored per section's text (0 = unlimited).", "default": 50000 }, "extractTables": { "title": "Extract Tables", "type": "boolean", "description": "Whether to extract wikitext tables from the article content.", "default": true }, "extractWikitext": { "title": "Extract Wikitext", "type": "boolean", "description": "Whether to extract the raw wikitext of the article.", "default": false }, "maxInfoboxFields": { "title": "Max Infobox Fields", "minimum": 0, "type": "integer", "description": "Maximum number of infobox fields to extract (0 = all).", "default": 50 }, "maxSectionDepth": { "title": "Max Section Depth", "minimum": 1, "maximum": 6, "type": "integer", "description": "Maximum section heading depth to extract (1 = h2 only, 2 = h2+h3, etc.).", "default": 3 }, "maxTables": { "title": "Max Tables", "minimum": 0, "type": "integer", "description": "Maximum number of tables to extract (0 = all).", "default": 20 }, "useApiForInfobox": { "title": "Use Wikipedia API for Infobox", "type": "boolean", "description": "Use Wikipedia REST API to parse infobox from wikitext (more accurate). Disable to use HTML parsing only.", "default": true }, "useApiForSections": { "title": "Use Wikipedia API for Sections", "type": "boolean", "description": "Use Wikipedia REST API to get section hierarchy from TOC (more accurate). Disable to use HTML parsing only.", "default": true }, "language": { "title": "Wikipedia Language", "pattern": "^[a-z]{2,3}(-[a-z]{2,3})?$", "type": "string", "description": "Wikipedia language edition code (e.g., 'en', 'de', 'fr', 'es', 'ja', 'zh').", "default": "en" }, "maxRequestsPerCrawl": { "title": "Max Requests per Crawl", "minimum": 0, "type": "integer", "description": "Maximum number of pages to scrape (0 = unlimited).", "default": 100 }, "maxConcurrency": { "title": "Max Concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum concurrent requests (higher = faster but more likely to hit rate limits).", "default": 4 } } }, "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 } } } } } } } } } }