{ "openapi": "3.0.1", "info": { "title": "Wikipedia Scraper | $5 / 1k | Fast & Reliable", "description": "Get full articles and detailed search results with the Wikipedia Scraper. Extract structured data including titles, summaries, citations, and full content. Ideal for market research, AI training, and competitive intelligence.", "version": "0.0", "x-build-id": "Ych4WJHuOJ4zgjxiC" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/fatihtahta~wikipedia-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-fatihtahta-wikipedia-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/fatihtahta~wikipedia-scraper/runs": { "post": { "operationId": "runs-sync-fatihtahta-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/fatihtahta~wikipedia-scraper/run-sync": { "post": { "operationId": "run-sync-fatihtahta-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": { "articleInputs": { "title": "Enter Wikipedia article URLs or slugs", "type": "array", "description": "Paste one or more Wikipedia article URLs or slugs to scrape directly.", "items": { "type": "string" } }, "searchInputs": { "title": "Enter Wikipedia search URLs or queries", "type": "array", "description": "Provide search terms or Wikipedia search result URLs. The scraper will discover the matching articles and scrape them.", "items": { "type": "string" } }, "language": { "title": "Select Wikipedia language - Applicable to queries. Doesn't overrides the URL countries.", "enum": [ "ab", "ace", "ady", "af", "sq", "als", "am", "ami", "anp", "ar", "an", "rki", "arc", "hy", "roa-rup", "frp", "as", "ast", "tay", "atj", "av", "awa", "ay", "az", "ban", "bm", "bn", "bjn", "map-bms", "ba", "eu", "btm", "bbc", "bar", "be", "be-tarask", "bew", "bh", "bpy", "bi", "bs", "br", "bug", "bg", "my", "zh-yue", "ca", "ceb", "bcl", "dtp", "knc", "ckb", "ch", "cbk-zam", "ce", "chr", "chy", "zh", "cu", "cv", "ksh", "kw", "co", "cr", "crh", "hr", "cs", "dag", "da", "diq", "din", "dv", "dty", "nl", "dz", "mhr", "arz", "eml", "en", "myv", "eo", "et", "ee", "ext", "fat", "fo", "hif", "fj", "fi", "fon", "gur", "fr", "fur", "ff", "gag", "gl", "gan", "lg", "ka", "de", "gpe", "glk", "gom", "gor", "got", "el", "gn", "gcr", "gu", "guw", "ht", "hak", "ha", "haw", "he", "hi", "hu", "iba", "is", "io", "igl", "ig", "ilo", "smn", "id", "inh", "ia", "ie", "iu", "ik", "ga", "it", "jam", "ja", "jv", "kbd", "kbp", "kab", "kl", "xal", "kn", "kaa", "krc", "ks", "csb", "kk", "km", "ki", "rw", "kge", "kv", "koi", "kg", "ko", "avk", "ku", "kus", "ky", "lld", "lad", "lbe", "lo", "ltg", "la", "lv", "lez", "lij", "li", "ln", "lfn", "zh-classical", "lt", "olo", "jbo", "lmo", "nds", "nds-nl", "dsb", "lb", "mk", "mad", "mai", "mg", "ms", "ml", "mt", "mni", "gv", "mr", "mzn", "min", "cdo", "xmf", "zh-min-nan", "mwl", "mdf", "mnw", "mn", "ary", "mos", "mi", "nah", "nv", "nap", "ne", "new", "nia", "pcm", "nrm", "frr", "se", "nso", "no", "nn", "nov", "nup", "ny", "nqo", "ann", "oc", "or", "ang", "om", "os", "pwn", "pfl", "pi", "pam", "pag", "rsk", "pap", "ps", "blk", "pdc", "fa", "pcd", "pms", "pl", "pnt", "pt", "pa", "qu", "ro", "rm", "rn", "bxr", "ru", "rue", "szy", "sm", "bat-smg", "sg", "sa", "sat", "skr", "sc", "stq", "sco", "gd", "sr", "sh", "shn", "sn", "scn", "szl", "simple", "sd", "si", "sk", "sl", "so", "azb", "nr", "alt", "dga", "st", "es", "srn", "zgh", "su", "sw", "ss", "sv", "syl", "shi", "tl", "ty", "tdd", "tg", "tly", "ta", "roa-tara", "trv", "tt", "te", "tet", "th", "bo", "tig", "ti", "tpi", "to", "ts", "tn", "tcy", "tum", "tr", "tk", "tyv", "tw", "kcg", "udm", "uk", "hsb", "ur", "ug", "uz", "ve", "vec", "vep", "vi", "rmy", "vo", "fiu-vro", "wa", "war", "guc", "cy", "bdr", "vls", "hyw", "fy", "mrj", "pnb", "wo", "wuu", "xh", "sah", "yi", "yo", "zea", "za", "zu" ], "type": "string", "description": "Choose the Wikipedia language edition to combine with the slug and target.", "default": "en" }, "limit": { "title": "Maximum listings to collect", "minimum": 10, "type": "integer", "description": "Stop the run after this number of listings has been saved per input.", "default": 50000 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "The default Apify Datacenter proxy keeps the scraper reliable.", "default": { "useApifyProxy": true, "apifyProxyGroups": [] } } } }, "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 } } } } } } } } } }