{ "openapi": "3.0.1", "info": { "title": "Wayback Machine Scraper: Snapshots, Archived URLs & History", "description": "Get Internet Archive Wayback Machine snapshots of any page, every archived URL of a domain, or the capture closest to a date, with optional archived page text. Date, status, MIME and change filters. $0.30 per 1,000 snapshots.", "version": "1.0", "x-build-id": "tSeLhxdnTE80UPerI" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/best_apis~wayback-machine-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-best_apis-wayback-machine-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/best_apis~wayback-machine-scraper/runs": { "post": { "operationId": "runs-sync-best_apis-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/best_apis~wayback-machine-scraper/run-sync": { "post": { "operationId": "run-sync-best_apis-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 (https://example.com/pricing) or domains (example.com). Each one is looked up in the Internet Archive Wayback Machine.", "items": { "type": "string" } }, "mode": { "title": "What to get", "enum": [ "snapshots", "urls", "closest" ], "type": "string", "description": "Snapshots lists captures over time. Archived URLs lists the unique URLs the archive holds for a site (with its first capture). Closest returns one capture per URL nearest to the date below.", "default": "snapshots" }, "matchType": { "title": "Match", "enum": [ "auto", "exact", "prefix", "host", "domain" ], "type": "string", "description": "Which archived URLs count as a match for each input.", "default": "auto" }, "from": { "title": "From date", "type": "string", "description": "Only captures on or after this date: 2015, 2020-06, 2024-01-31, or relative like \"30 days\", \"2 years\"." }, "to": { "title": "To date", "type": "string", "description": "Only captures on or before this date (same formats)." }, "closestTo": { "title": "Closest to date", "type": "string", "description": "For the Closest snapshot mode: the target date (for example 2019-01-01). Defaults to now." }, "onlyChanges": { "title": "Only when the page changed", "type": "boolean", "description": "Skip consecutive captures with identical content (same digest). Turn off to list every single capture.", "default": true }, "frequency": { "title": "At most one capture per", "enum": [ "any", "hour", "day", "month", "year" ], "type": "string", "description": "Thin out the history, for example one snapshot per month.", "default": "any" }, "statusCodes": { "title": "HTTP status codes", "type": "array", "description": "Keep only captures with these status codes, for example 200 or 301. Leave empty for all.", "items": { "type": "string" } }, "mimeTypes": { "title": "MIME types", "type": "array", "description": "Keep only these content types, for example text/html or application/pdf. Leave empty for all.", "items": { "type": "string" } }, "urlContains": { "title": "URL contains", "type": "string", "description": "Keep only archived URLs containing this text (case-insensitive), for example /blog/ or .pdf." }, "maxResultsPerUrl": { "title": "Max results per input", "minimum": 1, "type": "integer", "description": "Newest first is not available in the archive index: results run oldest to newest.", "default": 1000 }, "maxResults": { "title": "Max results in total", "minimum": 1, "type": "integer", "description": "Hard cap for the whole run (keeps cost predictable).", "default": 10000 }, "includeContent": { "title": "Include archived page text", "type": "boolean", "description": "Download each archived HTML page and add its title, meta description, plain text and links count. Charged separately per page.", "default": false }, "maxContentChars": { "title": "Max text characters per page", "minimum": 100, "type": "integer", "description": "Longer page text is truncated.", "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 } } } } } } } } } }