{ "openapi": "3.0.1", "info": { "title": "Wayback Machine URL History & Removed Pages Finder", "description": "List every URL the Wayback Machine archived for a domain, with first/last seen dates and archive links. Find removed pages (404, gone, redirected to home) for SEO link reclamation, redirect maps and content recovery. Fast, no browser.", "version": "1.0", "x-build-id": "vwqYOlqHlff5loSne" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/thomson-digital~wayback-url-history/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-thomson-digital-wayback-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/thomson-digital~wayback-url-history/runs": { "post": { "operationId": "runs-sync-thomson-digital-wayback-url-history", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/thomson-digital~wayback-url-history/run-sync": { "post": { "operationId": "run-sync-thomson-digital-wayback-url-history", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Domains or URLs", "type": "array", "description": "One per line, e.g. example.com, blog.example.com or https://example.com/blog/. How each entry is matched is set by 'Scope'.", "default": [ "apify.com" ], "items": { "type": "string" } }, "scope": { "title": "Scope", "enum": [ "domain", "host", "prefix", "exact" ], "type": "string", "description": "What to look up in the Wayback Machine for each entry.", "default": "domain" }, "mode": { "title": "Output", "enum": [ "urls", "snapshots" ], "type": "string", "description": "'Unique URLs' gives one row per archived page with its history. 'Every snapshot' gives one row per capture (use with granularity).", "default": "urls" }, "maxResultsPerTarget": { "title": "Max results per domain/URL", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Maximum rows output for each entry. Keep small for testing.", "default": 100 }, "fromDate": { "title": "Captured from", "type": "string", "description": "Optional. Only captures on or after this date (YYYY-MM-DD)." }, "toDate": { "title": "Captured until", "type": "string", "description": "Optional. Only captures on or before this date (YYYY-MM-DD)." }, "statusFilter": { "title": "HTTP status of captures", "enum": [ "200", "2xx3xx", "any" ], "type": "string", "description": "Which captures to consider, by the HTTP status the archive recorded.", "default": "200" }, "mimeTypes": { "title": "Content types", "type": "array", "description": "Only captures with these MIME types. Default text/html (web pages). Add application/pdf for PDFs. Empty list = everything (images, CSS, JS...).", "default": [ "text/html" ], "items": { "type": "string" } }, "includeUrlPatterns": { "title": "Only include URLs matching (regex)", "type": "array", "description": "Optional, case-insensitive regular expressions, e.g. /blog/.", "default": [], "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URLs matching (regex)", "type": "array", "description": "Optional, e.g. \\?utm_ or /wp-json/.", "default": [], "items": { "type": "string" } }, "checkLiveStatus": { "title": "Check if each URL still exists today", "type": "boolean", "description": "Requests every archived URL on the live site and adds liveStatus (live, redirected, redirected-to-home, not-found, gone, unreachable...) and isRemoved. Charged as an extra 'live check' event.", "default": false }, "onlyRemovedPages": { "title": "Output only removed pages", "type": "boolean", "description": "Find pages that existed in the past but are gone now (404/410, unreachable, or redirected to the homepage) - great for SEO link reclamation, redirect maps and content recovery. Implies the live check.", "default": false }, "snapshotGranularity": { "title": "Snapshot granularity (snapshots mode)", "enum": [ "all", "day", "month", "year", "content-change" ], "type": "string", "description": "In 'Every snapshot' mode, collapse captures of the same URL to reduce noise and cost.", "default": "month" }, "maxCdxPages": { "title": "Max archive index pages per entry", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Safety cap on Wayback CDX API requests per entry (each returns up to 5,000 index rows).", "default": 20 }, "liveCheckConcurrency": { "title": "Live check concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Parallel requests to the live website when checking status.", "default": 10 }, "requestTimeoutSecs": { "title": "Archive request timeout (s)", "minimum": 10, "maximum": 300, "type": "integer", "description": "The archive index can be slow for big domains.", "default": 90 }, "maxRetries": { "title": "Max retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "Retries when the Internet Archive rate-limits (429) or is temporarily offline, with exponential backoff.", "default": 5 }, "retryBudgetSecs": { "title": "Max time per archive request incl. retries (s)", "minimum": 30, "maximum": 3600, "type": "integer", "description": "Upper bound on how long the Actor keeps retrying one archive index request (rate limits / outages) before giving up on that entry. Keeps runs short when the archive is down.", "default": 210 } } }, "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 } } } } } } } } } }