{
"openapi": "3.0.1",
"info": {
"title": "Internet Archive & Wayback Machine Scraper",
"description": "Search archive.org and the Wayback Machine for OSINT, journalism, and research — books, movies, audio, software, item metadata, file lists, and URL snapshots. Official public APIs, no login. Unofficial — not affiliated with the Internet Archive.",
"version": "0.1",
"x-build-id": "RG6IIVsdiGXxfx5A4"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/bakos_bence~internet-archive/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-bakos_bence-internet-archive",
"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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/bakos_bence~internet-archive/runs": {
"post": {
"operationId": "runs-sync-bakos_bence-internet-archive",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/bakos_bence~internet-archive/run-sync": {
"post": {
"operationId": "run-sync-bakos_bence-internet-archive",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"queries": {
"title": "What to look up",
"type": "array",
"description": "One query per line. Examples: the sketch show, collection:nasa, an archive.org/details/… URL, bbc.co.uk (Wayback), or snapshotOf:bbc.co.uk@20150601.",
"items": {
"type": "string"
},
"default": [
"https://archive.org/details/the-sketch-show-s1-e3"
]
},
"mode": {
"title": "Processing mode",
"enum": [
"auto",
"search",
"metadata",
"files",
"snapshots",
"available"
],
"type": "string",
"description": "Leave Auto unless every line should use the same handler (e.g. all Wayback snapshots).",
"default": "auto"
},
"mediaType": {
"title": "Library media type",
"enum": [
"all",
"texts",
"movies",
"audio",
"image",
"software",
"data",
"web",
"collection",
"etree"
],
"type": "string",
"description": "Filters library search only — ignored for item URLs and Wayback lines.",
"default": "all"
},
"collection": {
"title": "Collection id",
"type": "string",
"description": "Optional Lucene filter — same as typing collection:nasa in the query line."
},
"creator": {
"title": "Creator",
"type": "string",
"description": "Match the bibliographic creator / author field."
},
"language": {
"title": "Language",
"type": "string",
"description": "Language code as stored by the Archive — pick a common code or type another."
},
"dateFrom": {
"title": "From date",
"type": "string",
"description": "Start of range (YYYY-MM-DD from the date picker, or compact YYYYMMDD). Search uses item date; Wayback strips to capture timestamps."
},
"dateTo": {
"title": "To date",
"type": "string",
"description": "End of range (inclusive). Same formats as From date. Leave empty for no upper bound."
},
"sort": {
"title": "Search sort",
"enum": [
"downloads desc",
"downloads asc",
"publicdate desc",
"publicdate asc",
"date desc",
"date asc",
"titleSorter asc"
],
"type": "string",
"description": "Sort library hits. Leave empty for relevance. Wayback ignores this."
},
"maxItems": {
"title": "Maximum rows",
"minimum": 1,
"type": "integer",
"description": "Cap rows across all queries (minimum 1). Prefill 5 for multi-query trials; a single item URL often yields one row before the cap.",
"default": 5
},
"includeFiles": {
"title": "Emit file rows",
"type": "boolean",
"description": "Also push one dataset row per file (name, format, size in bytes, download URL).",
"default": false
},
"enrichMetadata": {
"title": "Enrich search hits",
"type": "boolean",
"description": "For each search hit, fetch full item metadata (extra Archive request per item).",
"default": false
},
"matchType": {
"title": "Wayback match",
"enum": [
"exact",
"prefix",
"host",
"domain"
],
"type": "string",
"description": "How CDX matches the URL. Domain covers every host under the site."
},
"collapseSnapshots": {
"title": "Collapse duplicate captures",
"type": "boolean",
"description": "Collapse consecutive Wayback captures with the same content digest.",
"default": false
},
"filterStatus": {
"title": "HTTP status filter",
"type": "string",
"description": "Keep only CDX rows with this status (e.g. 200)."
},
"query": {
"title": "Query (alias)",
"type": "string",
"description": "Single-query alias merged into Queries."
},
"maxResults": {
"title": "Max results (alias)",
"minimum": 1,
"type": "integer",
"description": "Alias of Maximum rows when maxItems is omitted. Same cap; minimum 1.",
"default": 5
},
"proxyConfiguration": {
"title": "Proxy configuration",
"type": "object",
"description": "Ignored at runtime — the Actor uses direct egress. Leave default.",
"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
},
"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
}
}
}
}
}
}
}
}
}
}