{ "openapi": "3.0.1", "info": { "title": "Broken Link Checker — Recursive Site Crawler", "description": "Recursively crawl your website and find every broken link, 404, redirect, and timeout. Checks internal and external links with configurable depth. 100 links free per run.", "version": "0.1", "x-build-id": "7SRoDFaY8adrdi2af" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/accurate_pouch~broken-link-checker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-accurate_pouch-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/accurate_pouch~broken-link-checker/runs": { "post": { "operationId": "runs-sync-accurate_pouch-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/accurate_pouch~broken-link-checker/run-sync": { "post": { "operationId": "run-sync-accurate_pouch-broken-link-checker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrl" ], "properties": { "startUrl": { "title": "Start URL", "type": "string", "description": "The URL to start crawling from. All internal links will be followed up to maxDepth." }, "maxDepth": { "title": "Max Crawl Depth", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum link depth to follow from the start URL. 1 = only links on the start page. 3 = three levels deep.", "default": 3 }, "maxPages": { "title": "Max Pages", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of pages to crawl. Prevents runaway crawls on large sites.", "default": 500 }, "checkExternalLinks": { "title": "Check External Links", "type": "boolean", "description": "Also check links pointing to other domains (uses HEAD requests — fast and lightweight).", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages disallowed by the site's robots.txt file.", "default": true }, "ignoredPatterns": { "title": "Ignored URL Patterns", "type": "array", "description": "URL patterns to skip. Uses glob-style matching. Example: *logout*, *admin*, *.pdf", "items": { "type": "string" } }, "outputFormat": { "title": "Output Format", "enum": [ "broken-only", "all" ], "type": "string", "description": "broken-only: only report broken/redirect/error links. all: include every link checked.", "default": "broken-only" }, "sitemapUrl": { "title": "Sitemap URL", "type": "string", "description": "URL to a sitemap.xml file. All URLs from the sitemap will be crawled. If not provided, the actor auto-detects /sitemap.xml and /sitemap_index.xml." }, "webhookUrl": { "title": "Webhook URL", "type": "string", "description": "POST full results (JSON) to this URL when the audit completes. Useful for alerts and integrations." }, "googleSheetsId": { "title": "Google Sheets Export — Spreadsheet ID", "type": "string", "description": "Export broken links to a Google Sheet. Paste the spreadsheet ID (from the URL between /d/ and /edit)." }, "googleServiceAccountKey": { "title": "Google Sheets Export — Service Account Key", "type": "string", "description": "Full JSON contents of your Google Service Account key file. Required for Sheets export. See google-sheets-rw actor README for 5-minute setup guide." }, "dryRun": { "title": "Dry Run", "type": "boolean", "description": "Preview what would be crawled without any charges. Results are still returned.", "default": false } } }, "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 } } } } } } } } } }