{ "openapi": "3.0.1", "info": { "title": "Dead Link Fixer: Broken Link Checker with Wayback Replacements", "description": "Crawl your site or check a URL list for broken links (404, 410, soft-404, 5xx, DNS and TLS errors), then get an Internet Archive Wayback Machine copy to replace each dead link. Respects robots.txt; blocked or access-controlled links are never called broken.", "version": "0.1", "x-build-id": "x6MF4EdBK9MzMoVsZ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/chromy_dome~dead-link-fixer/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-chromy_dome-dead-link-fixer", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/chromy_dome~dead-link-fixer/runs": { "post": { "operationId": "runs-sync-chromy_dome-dead-link-fixer", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/chromy_dome~dead-link-fixer/run-sync": { "post": { "operationId": "run-sync-chromy_dome-dead-link-fixer", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Start URLs", "type": "array", "description": "Pages or sites to check. In 'Crawl site' mode these are starting points; in 'URL list' mode each URL is checked directly as a link.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "mode": { "title": "Mode", "enum": [ "crawlSite", "pagesOnly", "urlList" ], "type": "string", "description": "crawlSite: follow same-host links up to 'Max pages' and check every link found. pagesOnly: check links on the start pages only. urlList: check the start URLs themselves (no crawling).", "default": "crawlSite" }, "maxPages": { "title": "Max pages to crawl", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Upper limit on pages read in 'Crawl site' mode.", "default": 50 }, "maxLinksToCheck": { "title": "Max links to check", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Upper limit on unique links checked (each is billed as one 'link checked' event).", "default": 500 }, "checkExternalLinks": { "title": "Check external links", "type": "boolean", "description": "Check links that point to other websites.", "default": true }, "checkInternalLinks": { "title": "Check internal links", "type": "boolean", "description": "Check links that point to the same website.", "default": true }, "findArchivedCopies": { "title": "Find Wayback Machine replacements", "type": "boolean", "description": "For each link that needs attention, ask the Internet Archive's official Availability API for the closest archived copy.", "default": true }, "archiveTargetDate": { "title": "Preferred archive date", "type": "string", "description": "Optional. YYYY, YYYYMM or YYYYMMDD. The archive copy closest to this date is returned (for example, the date you first published the link). Leave empty for the most recent copy.", "default": "" }, "onlyProblems": { "title": "Output only links that need attention", "type": "boolean", "description": "When on, healthy, redirected and access-controlled links are counted in the summary but not written to the dataset. Turn off for a full link inventory.", "default": true }, "detectSoft404": { "title": "Detect soft 404s", "type": "boolean", "description": "Flag pages that return 200 OK but whose title or main heading says 'not found'.", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages and links disallowed by the target site's robots.txt. Skipped links are reported as 'unverified', never as broken.", "default": true }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Parallel requests. Keep low to be polite to small sites.", "default": 5 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "How long to wait for each page or link before calling it a timeout.", "default": 20 }, "userAgent": { "title": "User agent", "type": "string", "description": "User-Agent header sent with requests.", "default": "Mozilla/5.0 (compatible; DeadLinkFixer/1.0; +https://apify.com)" } } }, "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 } } } } } } } } } }