{ "openapi": "3.0.1", "info": { "title": "Dead Link Checker & Wayback URL Recovery", "description": "Pulls every URL the Internet Archive captured for a site, checks each one against the live site today, and suggests where the dead ones should redirect. Catches the two losses other tools call healthy: 200s that say \"not found\", and 301s that dump every old path on the home page.", "version": "0.1", "x-build-id": "f01sMGHBmo3ZHideI" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/aiqlabs~dead-link-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-aiqlabs-dead-link-checker", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/aiqlabs~dead-link-checker/runs": { "post": { "operationId": "runs-sync-aiqlabs-dead-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/aiqlabs~dead-link-checker/run-sync": { "post": { "operationId": "run-sync-aiqlabs-dead-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "domains" ], "properties": { "domains": { "title": "Sites to recover", "type": "array", "description": "One host per line (example.com), or a URL prefix to limit the search to part of a site (https://example.com/blog/). A prefix needs \"Archive match\" set to prefix.", "default": [ "docs.apify.com" ], "items": { "type": "string" } }, "matchType": { "title": "Archive match", "enum": [ "domain", "host", "prefix", "exact" ], "type": "string", "description": "domain covers the host and every subdomain, host covers only the exact host, prefix covers one path subtree, exact covers a single URL.", "default": "domain" }, "archivedFrom": { "title": "Archived on or after", "type": "string", "description": "Optional yyyyMMdd, for example 20180101. Leave empty to include the whole archive.", "default": "" }, "archivedTo": { "title": "Archived on or before", "type": "string", "description": "Optional yyyyMMdd, for example 20231231. Leave empty to include the whole archive.", "default": "" }, "maxArchivedUrls": { "title": "Archived URLs to check per site", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Each one costs a request to the live site, so this is the main control over how long a run takes.", "default": 3000 }, "suggestRedirects": { "title": "Suggest a destination for each dead URL", "type": "boolean", "description": "Reads the site's current sitemap and matches each dead URL against it. Turn off to get the status check alone.", "default": true }, "minSimilarity": { "title": "Similarity needed for a name match", "minimum": 0.1, "maximum": 0.95, "type": "number", "description": "How much of a page name has to match before a rewritten name counts as the same page. Higher is stricter. Exact paths and identical names are matched regardless of this setting.", "default": 0.5 }, "onlyLost": { "title": "Only output lost URLs", "type": "boolean", "description": "Skip the archived URLs that still work, so the dataset is the worklist.", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip URLs the site disallows and report them as skipped.", "default": true }, "robotsAgent": { "title": "robots.txt user agent to obey", "type": "string", "description": "Which robots.txt group applies. Googlebot is the useful answer for SEO work.", "default": "Googlebot" }, "maxConcurrency": { "title": "Parallel requests", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many archived URLs are checked at once. Lower this if the site you are auditing is small or slow.", "default": 8 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "How long to wait for one response before recording the URL as unreachable.", "default": 20 } } }, "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 } } }, "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 } } } } } } } } } }