{ "openapi": "3.0.1", "info": { "title": "Wayback Machine Scraper: Snapshots, Changes & Page Text", "description": "List every Internet Archive Wayback Machine capture of any URL, path or whole domain: dates, HTTP status, MIME type, content hash and playback links. Filter by date, status and type, keep one per day, month or year or only changed versions, and optionally get each archived page's text.", "version": "1.0", "x-build-id": "l1eJul9AHPUeealH7" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/private_image_hg9~wayback-machine-snapshots/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-private_image_hg9-wayback-machine-snapshots", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/private_image_hg9~wayback-machine-snapshots/runs": { "post": { "operationId": "runs-sync-private_image_hg9-wayback-machine-snapshots", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/private_image_hg9~wayback-machine-snapshots/run-sync": { "post": { "operationId": "run-sync-private_image_hg9-wayback-machine-snapshots", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "URLs or domains", "type": "array", "description": "One per line: a page (https://www.example.com/about), a domain (example.com) or a wildcard: example.com/blog/* for everything under a path, *.example.com for a domain and all its subdomains. Each one is looked up separately; repeats are looked up once.", "items": { "type": "string" } }, "matchType": { "title": "Match", "enum": [ "exact", "prefix", "host", "domain" ], "type": "string", "description": "How each entry is matched (a wildcard in the entry overrides this). Exact: that page only. Prefix: every URL that starts with it. Host: every URL on that host name. Domain: every URL on the domain and its subdomains.", "default": "exact" }, "from": { "title": "From date", "type": "string", "description": "Only captures on or after this date (UTC): 2015, 2015-06, 2015-06-30 or 20150630123000. Leave empty for the first capture ever." }, "to": { "title": "To date", "type": "string", "description": "Only captures on or before this date (UTC). 2019 means up to the end of 2019. Leave empty for today." }, "statusCodes": { "title": "HTTP status codes", "type": "array", "description": "Keep only captures whose archived answer had one of these codes, e.g. 200, or a class like 3xx. Empty keeps all (including deduplicated 'revisit' records, whose status is empty).", "items": { "type": "string" } }, "mimeTypes": { "title": "MIME types", "type": "array", "description": "Keep only captures of these types, e.g. text/html, application/pdf or image/*. Empty keeps all.", "items": { "type": "string" } }, "collapse": { "title": "Keep one capture per", "enum": [ "none", "hour", "day", "month", "year", "digest", "url" ], "type": "string", "description": "Thin out the list. Hour, day, month or year: the first capture of each period. Changed content only: drops a capture when its content hash equals the one just before it. URL: one capture per distinct URL (handy with prefix, host or domain to list every archived URL).", "default": "none" }, "maxSnapshotsPerInput": { "title": "Max snapshots per input", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after this many snapshots for each URL or domain. The SUMMARY record says when more exist.", "default": 1000 }, "fetchContent": { "title": "Get archived page text", "type": "boolean", "description": "Also download each archived page as it was captured and return its title and visible text (HTML stripped). Costs a small extra per page where text was extracted, and is slower: about two pages per second.", "default": false }, "maxTextChars": { "title": "Max text characters per page", "minimum": 500, "maximum": 200000, "type": "integer", "description": "Longer text is cut here (textTruncated is then true).", "default": 20000 } } }, "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 } } } } } } } } } }