{ "openapi": "3.0.1", "info": { "title": "Wayback Machine Search", "description": "Query Internet Archive's Wayback Machine for historical snapshots of any URL or domain. Filter by date, HTTP status, MIME type, and deduplicate. Optionally fetch the archived page text. Free public CDX API, no authentication.", "version": "1.0", "x-build-id": "h9mXCHbzYwfM9qkcl" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/crawlerbros~wayback-machine-search/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-crawlerbros-wayback-machine-search", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/crawlerbros~wayback-machine-search/runs": { "post": { "operationId": "runs-sync-crawlerbros-wayback-machine-search", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/crawlerbros~wayback-machine-search/run-sync": { "post": { "operationId": "run-sync-crawlerbros-wayback-machine-search", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "url" ], "properties": { "url": { "title": "URL or domain", "type": "string", "description": "The URL or domain to search for historical snapshots. Examples: 'apify.com', 'https://example.com/blog', 'nytimes.com/2024/01/15/story.html'. Combine with 'Match type' to broaden or narrow the search." }, "matchType": { "title": "Match type", "enum": [ "exact", "prefix", "host", "domain" ], "type": "string", "description": "How the input URL is matched against archived snapshots. 'exact' = only the exact URL. 'prefix' = the URL and anything beneath it (e.g., example.com/blog/*). 'host' = all snapshots on the same host. 'domain' = the host and all its subdomains.", "default": "exact" }, "dateFrom": { "title": "From date", "type": "string", "description": "Earliest snapshot date (inclusive). Accepts YYYY, YYYYMM, or YYYYMMDD (e.g., '2020', '202001', '20200115'). Leave blank for no lower bound." }, "dateTo": { "title": "To date", "type": "string", "description": "Latest snapshot date (inclusive). Accepts YYYY, YYYYMM, or YYYYMMDD (e.g., '2024', '202412', '20241231'). Leave blank for no upper bound." }, "statusFilter": { "title": "HTTP status filter", "type": "string", "description": "Only return snapshots matching this HTTP status code (e.g., '200' for successful fetches, '404' for not-found, '301' for redirects). Leave blank to include all status codes." }, "mimeFilter": { "title": "MIME type filter", "type": "string", "description": "Only return snapshots matching this MIME type (e.g., 'text/html', 'application/pdf', 'image/png'). Leave blank to include all MIME types." }, "collapseBy": { "title": "Collapse (deduplicate) by", "enum": [ "none", "digest", "monthly", "daily", "hourly" ], "type": "string", "description": "Deduplicate adjacent snapshots. 'digest' drops duplicates with identical content fingerprint (best for unchanged pages). 'monthly' / 'daily' / 'hourly' keep one snapshot per time bucket. 'none' returns every raw snapshot.", "default": "digest" }, "maxResults": { "title": "Max results", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of snapshot records to return (1-10000).", "default": 500 }, "includeContent": { "title": "Fetch archived page text", "type": "boolean", "description": "When enabled, downloads the archived HTML for the first N snapshots (see 'Max content fetch') and extracts the readable text. Adds latency and bandwidth but yields searchable content.", "default": false }, "maxContentFetch": { "title": "Max content fetches", "minimum": 0, "maximum": 500, "type": "integer", "description": "Upper bound on how many archived pages to download when 'Fetch archived page text' is enabled. Each fetch is rate-limited to be polite to the Wayback Machine.", "default": 10 } } }, "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 } } } } } } } } } }