{ "openapi": "3.0.1", "info": { "title": "Wayback Machine — Historical URLs and Snapshot History", "description": "Pull every URL the Internet Archive ever captured for a domain, with the dates, HTTP status and content type of each capture. Recover lost pages after a migration, audit a domain's past before buying it, or track when a single page changed.", "version": "0.1", "x-build-id": "X0cnGrwMHU3NtSueW" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dalbian~wayback-machine-url-history/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dalbian-wayback-machine-url-history", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/dalbian~wayback-machine-url-history/runs": { "post": { "operationId": "runs-sync-dalbian-wayback-machine-url-history", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/dalbian~wayback-machine-url-history/run-sync": { "post": { "operationId": "run-sync-dalbian-wayback-machine-url-history", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "Domains or URLs", "type": "array", "description": "One per line. A bare domain such as example.com, or a full URL. What is matched around it is decided by the Match type below.", "default": [ "apify.com" ], "items": { "type": "string" } }, "mode": { "title": "What to return", "enum": [ "urls", "snapshots", "overview" ], "type": "string", "description": "Unique URLs is the sitemap of everything that ever existed. Snapshots is the history of individual pages. Overview is a quick read on a domain you are considering buying.", "default": "urls" }, "matchType": { "title": "Match type", "enum": [ "domain", "host", "prefix", "exact" ], "type": "string", "description": "Use Exact when you are following the history of a single page.", "default": "domain" }, "dateFrom": { "title": "From", "type": "string", "description": "Earliest capture to consider. Accepts a year (2019), a month (201903) or a day (20190315)." }, "dateTo": { "title": "To", "type": "string", "description": "Latest capture to consider, same formats." }, "statusCodes": { "title": "HTTP status codes", "type": "array", "description": "Keep only captures that returned these codes, one per line — 200 for pages that worked, 301 for redirects, 404 for pages already broken when archived. Leave empty for all.", "items": { "type": "string" } }, "contentTypes": { "title": "Content types", "type": "array", "description": "Keep only these MIME types, one per line, such as text/html or application/pdf. Filtering to text/html is what turns a raw capture list into a page list.", "default": [ "text/html" ], "items": { "type": "string" } }, "urlContains": { "title": "URL must contain", "type": "array", "description": "Keep only URLs containing one of these strings, one per line. Combined with OR.", "items": { "type": "string" } }, "urlExcludes": { "title": "URL must not contain", "type": "array", "description": "Drop URLs containing any of these, one per line. Useful for stripping out ?replytocom, /wp-json/, /feed/ and other crawl noise.", "items": { "type": "string" } }, "onlyContentChanges": { "title": "Only captures where the content changed", "type": "boolean", "description": "In Snapshots mode, collapse consecutive identical captures so you get the dates a page actually changed rather than every crawl. Uses the Archive's own content checksum.", "default": false }, "maxResultsPerUrl": { "title": "Maximum rows per input", "minimum": 1, "maximum": 40000, "type": "integer", "description": "Cap per domain or URL. A large site can hold hundreds of thousands of captures, so this is both a cost and a run-time control.", "default": 1000 } } }, "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 } } } } } } } } } }