{ "openapi": "3.0.1", "info": { "title": "Broken Link Checker from Sitemap", "description": "Check every page in your XML sitemap for broken links. It reads the sitemap, visits each page and checks the links on it. You get 404s, server errors, redirect chains and slow pages, each with the page it was found on. If a site blocks the run, a row says why. Export to CSV or JSON.", "version": "0.0", "x-build-id": "LxC5puTU6sLerD2j3" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/bjgomes~broken-link-checker-from-sitemap/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-bjgomes-broken-link-checker-from-sitemap", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/bjgomes~broken-link-checker-from-sitemap/runs": { "post": { "operationId": "runs-sync-bjgomes-broken-link-checker-from-sitemap", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/bjgomes~broken-link-checker-from-sitemap/run-sync": { "post": { "operationId": "run-sync-bjgomes-broken-link-checker-from-sitemap", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 or sitemap URLs", "type": "array", "description": "A website (example.com) to find its sitemaps from robots.txt, /sitemap.xml and /sitemap_index.xml, or a sitemap URL to read directly. Every page listed is scanned for links.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Maximum pages to scan", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after scanning this many sitemap pages across all inputs.", "default": 100 }, "maxLinks": { "title": "Maximum links to check", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Stop after checking this many unique links. Each unique link is checked once, however many pages it's on.", "default": 5000 }, "checkExternalLinks": { "title": "Check external links", "type": "boolean", "description": "Also check links to other websites. Off: only links on the same site (www. or not) are checked.", "default": true }, "includeOkLinks": { "title": "Include working links", "type": "boolean", "description": "Also output links that answered 200 quickly with no redirect. Off: only broken, redirected, slow and error rows are output. Every link is checked either way.", "default": false }, "includeNotChecked": { "title": "Include links not checked", "type": "boolean", "description": "Also output a row for each link that wasn't requested (robots.txt said no, it was over maxLinks, or the run stopped first). Off: they're counted by reason in the run's status message instead. They're never charged.", "default": false }, "slowThresholdMs": { "title": "Slow response threshold (ms)", "minimum": 100, "maximum": 120000, "type": "integer", "description": "A page or link whose response takes longer than this is flagged slow and always output.", "default": 3000 }, "maxConcurrency": { "title": "Maximum concurrent requests", "minimum": 1, "maximum": 20, "type": "integer", "description": "Link checks in flight at once. Never more than 4 at a time to any one host, and robots.txt Crawl-delay is honoured.", "default": 5 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 1, "maximum": 120, "type": "integer", "description": "How long to wait for any single sitemap, robots.txt, page or link request.", "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 }, "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 } } } } } } } } } }