{ "openapi": "3.0.1", "info": { "title": "Broken Link Checker: Crawl Sites, Find Dead Links", "description": "Crawls whole websites and checks every link, image and optional script or stylesheet. Reports 404s, server errors, dead domains, timeouts and redirect chains with the exact page and anchor text, plus mixed content and links to localhost or staging hosts. Pay per crawled page.", "version": "0.1", "x-build-id": "H1SVhuQ54HasLeUCT" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/webify-lab~broken-link-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-webify-lab-broken-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/webify-lab~broken-link-checker/runs": { "post": { "operationId": "runs-sync-webify-lab-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/webify-lab~broken-link-checker/run-sync": { "post": { "operationId": "run-sync-webify-lab-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Websites", "type": "array", "description": "One start URL per website, e.g. https://www.example.com. The crawler follows links on the same host from there.", "items": { "type": "string" } }, "maxPagesPerSite": { "title": "Max pages per website", "minimum": 1, "maximum": 20000, "type": "integer", "description": "Safety limit. Only HTML pages that were crawled count. Links on those pages are all checked, even if the limit stops the crawler from opening them.", "default": 200 }, "includeSubdomains": { "title": "Crawl subdomains", "type": "boolean", "description": "Also crawl pages on subdomains of the start host (blog.example.com, shop.example.com). Links to subdomains are always checked.", "default": false }, "checkExternalLinks": { "title": "Check external links", "type": "boolean", "description": "Check links to other websites. Each unique external URL is requested once per run, no matter how many pages link to it.", "default": true }, "checkImages": { "title": "Check images", "type": "boolean", "description": "Check img src and srcset URLs.", "default": true }, "checkScriptsAndStyles": { "title": "Check scripts and stylesheets", "type": "boolean", "description": "Check script src, stylesheets, icons and preloads.", "default": false }, "outputMode": { "title": "Output", "enum": [ "problems", "all" ], "type": "string", "description": "Every run also adds one summary item per website.", "default": "problems" }, "reportRedirects": { "title": "Report redirects", "enum": [ "all", "internal", "none" ], "type": "string", "description": "Redirects of external links (for example wa.me or link shorteners) are often intended. Applies to output 'Problems only'; the summary always counts all redirects.", "default": "all" }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Do not crawl or check pages of the website that its robots.txt disallows for this bot.", "default": true }, "includePatterns": { "title": "Only crawl URLs matching", "type": "array", "description": "Regular expressions matched against the full URL, e.g. /blog/. If set, only matching pages are crawled (the start URL always is). Links on crawled pages are still checked.", "default": [], "items": { "type": "string" } }, "excludePatterns": { "title": "Exclude URLs matching", "type": "array", "description": "Regular expressions matched against the full URL, e.g. \\?sort= or linkedin\\.com. Matching URLs are neither crawled nor checked.", "default": [], "items": { "type": "string" } }, "concurrency": { "title": "Parallel requests", "minimum": 1, "maximum": 50, "type": "integer", "description": "Requests running at the same time across all hosts.", "default": 10 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 3, "maximum": 120, "type": "integer", "description": "A link that does not answer in this time is reported as timeout.", "default": 20 }, "maxRedirects": { "title": "Max redirects", "minimum": 1, "maximum": 30, "type": "integer", "description": "Longer chains and loops are reported as too-many-redirects.", "default": 10 }, "userAgent": { "title": "User agent", "type": "string", "description": "Sent with every request. The default names the bot honestly; robots.txt rules for BrokenLinkChecker apply.", "default": "Mozilla/5.0 (compatible; BrokenLinkChecker/1.0; +https://apify.com/store)" }, "proxyStrategy": { "title": "Proxy use", "enum": [ "fallback", "always" ], "type": "string", "description": "Only applies when a proxy is configured below.", "default": "fallback" }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. With the fallback strategy, links that answer 401, 403, 429 or 999 or fail to connect are retried once through the proxy." } } }, "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 } } } } } } } } } }