{ "openapi": "3.0.1", "info": { "title": "Wayback URL Finder: Lost Pages, History & Redirect Gaps", "description": "Find archived URLs, domain history and relaunch redirect gaps from the Wayback Machine, then check which of them still resolve. Metadata only. Failed, blocked and duplicate URLs are free.", "version": "1.0", "x-build-id": "EWEZ6PacsE8gRGvG5" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/urlwright~wayback-url-finder/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-urlwright-wayback-url-finder", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/urlwright~wayback-url-finder/runs": { "post": { "operationId": "runs-sync-urlwright-wayback-url-finder", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/urlwright~wayback-url-finder/run-sync": { "post": { "operationId": "run-sync-urlwright-wayback-url-finder", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Domains or URL prefixes", "type": "array", "description": "Domains (example.com) or URL prefixes (https://example.com/blog/). Scheme, port and query are removed for domains. At least one value is required unless datasetId is set.", "items": { "type": "string" } }, "datasetId": { "title": "Dataset ID", "type": "string", "description": "Read more targets from an Apify dataset, for example the output of Sitemap URL Extractor, Tech Stack Detector or Brand Kit." }, "datasetField": { "title": "Dataset field", "type": "string", "description": "Field that holds the domain or URL. When that field is missing on a row, url, finalUrl, domain and inputUrl are tried, in that order.", "default": "url" }, "sitemapDatasetId": { "title": "Sitemap dataset ID", "type": "string", "description": "Dataset from Sitemap URL Extractor. Rows are read from the url field and matched to archived URLs (http and https, www and a trailing slash count as the same URL). Used for redirect gaps." }, "mode": { "title": "Mode", "enum": [ "lostUrls", "history", "lookup" ], "type": "string", "description": "lostUrls lists archived URLs. history returns one domain history row per target. lookup returns the capture closest to lookupDate.", "default": "lostUrls" }, "lookupDate": { "title": "Lookup date", "type": "string", "description": "Required for lookup mode. YYYY, YYYY-MM or YYYY-MM-DD. The closest archived capture to the start of that period is returned." }, "includeSubdomains": { "title": "Include subdomains", "type": "boolean", "description": "When true, the archive query uses matchType domain (the host and its subdomains). When false, a domain is one matchType domain query filtered to the apex host and www. A path is still queried on the host and its www twin. Hosts with more than two labels are queried as written.", "default": false }, "from": { "title": "From", "type": "string", "description": "Earliest capture to include. YYYY, YYYY-MM or YYYY-MM-DD. Must be on or before To." }, "to": { "title": "To", "type": "string", "description": "Latest capture to include. YYYY, YYYY-MM or YYYY-MM-DD." }, "mimeTypes": { "title": "MIME types", "type": "array", "description": "Archived MIME types to keep in lost URL and lookup modes. Empty means all types. History mode reports the distribution and does not apply this filter.", "items": { "type": "string" }, "default": [ "text/html" ] }, "statusCodes": { "title": "Archive status codes", "type": "array", "description": "Archived HTTP status codes to keep. Use a code such as 200 or a class such as 2xx, 3xx, 4xx or 5xx. Empty means all codes.", "items": { "type": "string" }, "default": [ "200" ] }, "maxUrlsPerTarget": { "title": "Max URLs per target", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop listing archived URLs for a target after this many rows. Further captures are not returned and the run is marked truncated.", "default": 1000 }, "maxTargets": { "title": "Max targets", "minimum": 1, "maximum": 200, "type": "integer", "description": "Maximum number of targets after normalisation and deduplication. The run rejects the input when there are more.", "default": 25 }, "checkLiveStatus": { "title": "Check live status", "type": "boolean", "description": "Request each archived URL today (HEAD, then GET if the server rejects HEAD) and fill httpStatus, finalUrl and redirectGap. Respects robots.txt unless you turn that off.", "default": true }, "maxLiveChecksPerTarget": { "title": "Max live checks per target", "minimum": 1, "maximum": 10000, "type": "integer", "description": "How many archived URLs per target are requested on the live web. The rest keep a null httpStatus.", "default": 200 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Read robots.txt for UrlwrightBot before each live check. A disallow, or a robots.txt that cannot be fetched, skips the check and is not billed.", "default": true } } }, "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 } } } } } } } } } }