{ "openapi": "3.0.1", "info": { "title": "Wayback Machine Scraper - Snapshot History of Any URL", "description": "Every capture the Wayback Machine holds of the pages or sites you list, one row each: when it was taken, HTTP status, content type, size, digest and a link to the archived copy. Filter by date, status and type, or keep one per day, month or year. $0.13 per 1,000 captures.", "version": "0.1", "x-build-id": "Vzr8wjVtS93i6GRak" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dami_studio~wayback-machine-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dami_studio-wayback-machine-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/dami_studio~wayback-machine-scraper/runs": { "post": { "operationId": "runs-sync-dami_studio-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/dami_studio~wayback-machine-scraper/run-sync": { "post": { "operationId": "run-sync-dami_studio-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "urls": { "title": "Web addresses", "maxItems": 500, "type": "array", "description": "The pages or sites to look up, one per line. A full link and a bare address find the same captures: https://www.nasa.gov/ and nasa.gov are one page to the archive. End an address with /* for everything under that path, or start it with *. for a whole domain and its subdomains. Up to 500 addresses a run.", "items": { "type": "string" } }, "matchType": { "title": "What each address covers", "enum": [ "exact", "prefix", "host", "domain" ], "type": "string", "description": "Exact is that one page. A path takes every page whose address starts with it. A host takes everything on that host, and a domain adds every subdomain. A /* or *. typed into an entry wins over this for that entry.", "default": "exact" }, "from": { "title": "From", "pattern": "^\\s*(?:(?:199\\d|2\\d{3})(?:-(?:0[1-9]|1[0-2])(?:-(?:0[1-9]|[12]\\d|3[01])(?:[Tt ]\\d{2}:\\d{2}(?::\\d{2}(?:\\.\\d+)?)?(?:[Zz]|[+-]\\d{2}:?\\d{2})?)?)?)?|(?:199\\d|2\\d{3})(?:0[1-9]|1[0-2])(?:(?:0[1-9]|[12]\\d|3[01])(?:(?:[01]\\d|2[0-3])(?:[0-5]\\d(?:[0-5]\\d)?)?)?)?)?\\s*$", "type": "string", "description": "Only captures taken on or after this date, in UTC. Write 2015, 2015-06 or 2015-06-01. A date in any other format is refused before the run starts. Leave it empty to start at the first capture." }, "to": { "title": "To", "pattern": "^\\s*(?:(?:199\\d|2\\d{3})(?:-(?:0[1-9]|1[0-2])(?:-(?:0[1-9]|[12]\\d|3[01])(?:[Tt ]\\d{2}:\\d{2}(?::\\d{2}(?:\\.\\d+)?)?(?:[Zz]|[+-]\\d{2}:?\\d{2})?)?)?)?|(?:199\\d|2\\d{3})(?:0[1-9]|1[0-2])(?:(?:0[1-9]|[12]\\d|3[01])(?:(?:[01]\\d|2[0-3])(?:[0-5]\\d(?:[0-5]\\d)?)?)?)?)?\\s*$", "type": "string", "description": "Only captures taken up to and including this date, in UTC. 2019 means through the last day of 2019. Leave it empty to run to the latest capture." }, "statusCodes": { "title": "HTTP status", "maxItems": 20, "type": "array", "description": "Only captures that got these answers when the archive took them, such as 200 or 404, or a whole class written 3xx. Leave it empty for all. Captures the archive stored as unchanged since the one before carry no status, so any status filter leaves them out.", "items": { "type": "string" } }, "mimeTypes": { "title": "Content type", "maxItems": 20, "type": "array", "description": "Only captures of these content types, written in full: text/html, application/pdf, or a family such as image/*. A bare \"html\" matches nothing. Leave it empty for all.", "items": { "type": "string" } }, "collapse": { "title": "Thin the list", "enum": [ "none", "digest", "day", "month", "year", "url" ], "type": "string", "description": "Every capture lists them all. Only when the content changed drops a capture identical to the one before it. One per day, month or year keeps the first capture of each period, page by page. One per address lists every archived address once with its first capture, which is the quick way to list every page a site ever had.", "default": "none" }, "maxCapturesPerUrl": { "title": "Captures per address", "minimum": 1, "maximum": 100000, "type": "integer", "description": "The most captures from one address, or from one path, host or domain. A busy home page has hundreds of thousands, so this is your main spending cap.", "default": 1000 }, "maxCaptures": { "title": "Captures in total", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "The most captures in the whole run, across all your entries. Each capture returned is one charge.", "default": 100000 }, "newestFirst": { "title": "Newest first", "type": "boolean", "description": "Start from the latest capture and work back. Only for exact pages. With a thinning option on, it keeps the latest capture of each period instead of the first.", "default": false } } }, "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 } } } } } } } } } }