{ "openapi": "3.0.1", "info": { "title": "Wayback Machine URL Extractor - Archived URLs", "description": "Extract every archived URL of any domain from the Internet Archive's Wayback Machine (CDX API). Recover lost or old pages, build redirect maps and run OSINT, with date and status filters. No API key, export to CSV or JSON.", "version": "1.0", "x-build-id": "NOT2n5L3EBwYQc2UU" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/logiover~wayback-machine-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-logiover-wayback-machine-url-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/logiover~wayback-machine-url-extractor/runs": { "post": { "operationId": "runs-sync-logiover-wayback-machine-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/logiover~wayback-machine-url-extractor/run-sync": { "post": { "operationId": "run-sync-logiover-wayback-machine-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "domains" ], "properties": { "domains": { "title": "Domains", "type": "array", "description": "One or more domains (or full URLs) to extract archived URLs for. Examples: nasa.gov, bbc.com, https://example.com. Do not include trailing wildcards.", "items": { "type": "string" } }, "matchType": { "title": "Match Type", "enum": [ "subdomains", "host", "domain", "prefix" ], "type": "string", "description": "How the domain is matched against the archive. 'subdomains' = the host and all of its subdomains and paths (broadest, default). 'host' = only the exact host (no subdomains). 'domain' = exact host only. 'prefix' = URLs that start with the given path prefix.", "default": "subdomains" }, "fromDate": { "title": "From Date (YYYYMMDD)", "type": "string", "description": "Optional. Only return snapshots captured on or after this date. Format: YYYYMMDD (e.g. 20100101). Leave empty for no lower bound." }, "toDate": { "title": "To Date (YYYYMMDD)", "type": "string", "description": "Optional. Only return snapshots captured on or before this date. Format: YYYYMMDD (e.g. 20201231). Leave empty for no upper bound." }, "filterStatus": { "title": "HTTP Status Filter", "type": "string", "description": "Optional. Only return URLs whose archived snapshot returned this HTTP status code (e.g. 200 to exclude dead/redirected captures). Leave empty for all." }, "maxResults": { "title": "Max Results Per Domain", "minimum": 0, "type": "integer", "description": "Maximum number of unique URLs to extract per domain. Use 0 for unlimited (warning: large sites can yield hundreds of thousands of URLs).", "default": 5000 }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Recommended to avoid rate limiting from the Internet Archive.", "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 } } }, "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 } } } } } } } } } }