{ "openapi": "3.0.1", "info": { "title": "Broken Link Checker: 404s, Redirects & Anchor Text", "description": "Crawl a website and find broken links (404, 5xx, dead domains), redirect chains and blocked links, with the source page and anchor text for every link. Polite, respects robots.txt. Pay only per link that got a definitive result.", "version": "0.1", "x-build-id": "FHoO960JwK1A8JBhW" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/blond_terrarium~broken-link-checker-pro/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-blond_terrarium-broken-link-checker-pro", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/blond_terrarium~broken-link-checker-pro/runs": { "post": { "operationId": "runs-sync-blond_terrarium-broken-link-checker-pro", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/blond_terrarium~broken-link-checker-pro/run-sync": { "post": { "operationId": "run-sync-blond_terrarium-broken-link-checker-pro", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrl" ], "properties": { "startUrl": { "title": "Website URL", "type": "string", "description": "Page to start crawling from. Only pages on this domain are crawled; links to other sites are checked but not crawled." }, "maxPages": { "title": "Max pages to crawl", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Internal HTML pages to crawl for links. Links found beyond this are still checked.", "default": 100 }, "maxLinks": { "title": "Max links to check (0 = unlimited)", "minimum": 0, "type": "integer", "description": "Stop queuing new links after this many unique links. Also use 'Max total charge' to cap spend.", "default": 0 }, "checkExternalLinks": { "title": "Check external links", "type": "boolean", "description": "Check links to other websites (HEAD request, GET fallback). They are never crawled.", "default": true }, "includeSubdomains": { "title": "Treat subdomains as internal", "type": "boolean", "description": "Crawl blog.example.com etc. as part of example.com.", "default": false }, "checkImages": { "title": "Check images", "type": "boolean", "description": "Also check image URLs (img src).", "default": false }, "checkScriptsAndStyles": { "title": "Check scripts & stylesheets", "type": "boolean", "description": "Also check JavaScript (script src) and CSS stylesheet URLs.", "default": false }, "reportMode": { "title": "Rows to output", "enum": [ "all", "problems", "broken" ], "type": "string", "description": "Which rows go to the dataset. Every checked link is still billed once; the SUMMARY record always has full totals.", "default": "all" }, "maxSourcesPerLink": { "title": "Max source pages listed per link", "minimum": 1, "maximum": 500, "type": "integer", "description": "How many (page, anchor text) occurrences to list per link. sourceCount always has the full count.", "default": 20 }, "excludeUrlPatterns": { "title": "Exclude URL patterns (regex)", "type": "array", "description": "Links matching any pattern are neither crawled nor checked (e.g. /logout, \\?sort=).", "default": [], "items": { "type": "string" } }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip URLs disallowed by robots.txt (reported, not charged) and honor Crawl-delay. Turn off only for sites you own.", "default": true }, "requestDelayMs": { "title": "Delay between requests to the same host (ms)", "minimum": 0, "maximum": 30000, "type": "integer", "description": "Politeness delay per host. A larger robots.txt Crawl-delay wins (max 10 s); 429/503 Retry-After is honored.", "default": 500 }, "maxConcurrency": { "title": "Max parallel requests", "minimum": 1, "maximum": 20, "type": "integer", "description": "Across all hosts. Requests to one host are still spaced by the delay.", "default": 5 }, "requestTimeoutSecs": { "title": "Request timeout (s)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeouts are reported as 'error' and not charged.", "default": 20 }, "maxRetries": { "title": "Max retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Retries for timeouts, connection resets, 429 and 5xx.", "default": 1 }, "maxRedirects": { "title": "Max redirects", "minimum": 1, "maximum": 30, "type": "integer", "description": "Longer chains are reported as broken.", "default": 10 }, "userAgent": { "title": "User-Agent", "type": "string", "description": "Defaults to an honest bot User-Agent (BrokenLinkChecker/1.0)." }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. Only needed if a site blocks datacenter IPs. Proxy traffic is billed by Apify separately." } } }, "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 } } } } } } } } } }