{ "openapi": "3.0.1", "info": { "title": "Wayback Machine Scraper: Domain Age, Archived URLs & Content", "description": "Wayback Machine scraper and Internet Archive API for bulk domain age checks, snapshot timelines, every archived URL with live 404 detection, and archived page content as clean text/Markdown. No API key, no login, no proxy.", "version": "0.2", "x-build-id": "ywzjfnge7gJzUxEOK" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/classier_wholemeal~wayback-machine-toolkit/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-classier_wholemeal-wayback-machine-toolkit", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/classier_wholemeal~wayback-machine-toolkit/runs": { "post": { "operationId": "runs-sync-classier_wholemeal-wayback-machine-toolkit", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/classier_wholemeal~wayback-machine-toolkit/run-sync": { "post": { "operationId": "run-sync-classier_wholemeal-wayback-machine-toolkit", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "mode", "targets" ], "properties": { "mode": { "title": "What do you want?", "enum": [ "domainAge", "snapshots", "archivedUrls", "pageContent" ], "type": "string", "description": "domainAge = first/last archive date, site age and active years per domain. snapshots = capture history of a URL (optionally only when content changed). archivedUrls = every distinct URL ever archived for a domain, optionally checked live to find dead (404) pages. pageContent = archived page as clean text and Markdown at a chosen date.", "default": "domainAge" }, "targets": { "title": "Domains or URLs", "type": "array", "description": "Domains (example.com) or full URLs. One per line.", "items": { "type": "string" } }, "fromDate": { "title": "From date", "type": "string", "description": "Only captures on/after this date. Format YYYY, YYYYMM or YYYYMMDD. Used by snapshots and archivedUrls." }, "toDate": { "title": "To date", "type": "string", "description": "Only captures on/before this date. Format YYYY, YYYYMM or YYYYMMDD." }, "onlyChanges": { "title": "Only when content changed", "type": "boolean", "description": "snapshots mode: skip consecutive captures with identical content (uses the archive's content hash). Turns thousands of captures into a clean change timeline.", "default": true }, "statusFilter": { "title": "HTTP status filter", "type": "string", "description": "Keep only captures whose archived HTTP status matches, e.g. 200 or 404. Leave empty for all." }, "htmlOnly": { "title": "HTML pages only", "type": "boolean", "description": "archivedUrls mode: skip images, CSS, JS and other non-HTML files.", "default": true }, "checkLiveStatus": { "title": "Check live status (find dead pages)", "type": "boolean", "description": "archivedUrls mode: request each archived URL on the live site and report its current HTTP status and redirect target, so you can spot pages that now 404 and need redirects or content recovery.", "default": false }, "snapshotDate": { "title": "Snapshot date (page content)", "type": "string", "description": "pageContent mode: get the capture closest to this date (YYYYMMDD). Leave empty for the latest capture." }, "maxItemsPerTarget": { "title": "Max results per domain/URL", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Upper limit of snapshots or URLs returned for each target.", "default": 1000 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 8, "type": "integer", "description": "Parallel requests. Keep low; the Internet Archive rate-limits aggressive clients.", "default": 3 } } }, "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 } } } } } } } } } }