{ "openapi": "3.0.1", "info": { "title": "Wayback Machine Scraper - Snapshots & Every Archived URL", "description": "For site migrations, redirect maps, recovering deleted pages and domain diligence: every snapshot of a URL, or every archived URL under a domain, from the official Wayback CDX API - first and last capture, capture count, status codes and a link to the copy. One page alone can return 768,693 rows.", "version": "0.1", "x-build-id": "WnvanmpKzlmhnf7Sl" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/neverempty~wayback-machine-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-neverempty-wayback-machine-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/neverempty~wayback-machine-scraper/runs": { "post": { "operationId": "runs-sync-neverempty-wayback-machine-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/neverempty~wayback-machine-scraper/run-sync": { "post": { "operationId": "run-sync-neverempty-wayback-machine-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "URLs or domains", "type": "array", "description": "Pages or domains to look up, such as apify.com, https://www.nytimes.com/section/technology or docs.python.org. In URL-list mode you can also write *.example.com (every subdomain) or example.com/blog/* (everything under a path). A malformed entry is reported as its own row and never sent to the archive, because the archive would silently answer it with captures of a different address.", "items": { "type": "string" } }, "mode": { "title": "What to return", "enum": [ "snapshots", "urls" ], "type": "string", "description": "Snapshots: one row per archived capture of each URL, with its date, HTTP status, content type, size and a link to the archived copy. URL list: one row per distinct URL the archive holds under a domain, host or path, with when it was first and last captured, how many times, and every status code it has returned.", "default": "snapshots" }, "matchType": { "title": "URL list scope", "enum": [ "domain", "host", "prefix" ], "type": "string", "description": "Only used for the URL list. Domain covers the host and all its subdomains, host covers exactly that host, and prefix covers everything under the path you give.", "default": "domain" }, "from": { "title": "From date", "type": "string", "description": "Only captures on or after this date. YYYY, YYYY-MM, YYYY-MM-DD or the archive's own digits (for example 2021 or 20210315). An impossible date is rejected with a reason rather than sent - the archive answers one with an empty result that looks exactly like 'nothing archived'.", "default": "" }, "to": { "title": "To date", "type": "string", "description": "Only captures on or before this date, in the same forms as From date. The range is inclusive: 2021 means up to the end of 2021.", "default": "" }, "collapse": { "title": "Thin out snapshots", "enum": [ "month", "change", "day", "year", "none" ], "type": "string", "description": "Snapshots only. The archive often holds many captures a day of the same page. Month keeps one capture per month (the latest of each month in newest-first order, the earliest in oldest-first), change keeps only the captures where the content changed, none returns every capture. For the most heavily archived pages (such as google.com) thinning out can time out at the archive; a narrower date range or none works there.", "default": "month" }, "order": { "title": "Order", "enum": [ "newest", "oldest" ], "type": "string", "description": "Snapshots only. Newest returns the most recent captures first; oldest starts from the first capture the archive holds.", "default": "newest" }, "statusFilter": { "title": "HTTP status", "enum": [ "any", "ok", "redirect", "error" ], "type": "string", "description": "Snapshots only. Keep captures whose recorded HTTP status is a success (2xx), a redirect (3xx) or an error (4xx/5xx). The archive applies this filter before thinning out, so with one-per-month you get one matching capture for each month rather than losing the months whose first capture was a redirect. About one capture in eight is a revisit that records no status at all; those only appear when this is set to any.", "default": "any" }, "maxResultsPerUrl": { "title": "Maximum rows per URL", "minimum": 1, "maximum": 10000, "type": "integer", "description": "The most snapshot rows, or distinct URLs in URL-list mode, returned for each entry. Up to 10,000.", "default": 100 } } }, "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 } } } } } } } } } }