{ "openapi": "3.0.1", "info": { "title": "Sitemap & Indexability Auditor: Noindex, Canonical, Hreflang", "description": "Audit every URL in your sitemaps for indexability: HTTP status and redirects, noindex (meta and X-Robots-Tag), canonical, robots.txt, hreflang and lastmod. Get a verdict with reasons per URL, a summary per page template and regression alerts between scheduled runs.", "version": "0.1", "x-build-id": "QccSnxthQxEDkjm7S" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/benexe~sitemap-indexability-auditor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-benexe-sitemap-indexability-auditor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/benexe~sitemap-indexability-auditor/runs": { "post": { "operationId": "runs-sync-benexe-sitemap-indexability-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/benexe~sitemap-indexability-auditor/run-sync": { "post": { "operationId": "run-sync-benexe-sitemap-indexability-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "domains": { "title": "Domains", "type": "array", "description": "Sites to audit, e.g. example.com or example.com/blog. Sitemaps are discovered from robots.txt, then /sitemap_index.xml, /sitemap.xml and /wp-sitemap.xml. With a path, only sitemaps under that path are used.", "items": { "type": "string" } }, "sitemapUrls": { "title": "Sitemaps", "type": "array", "description": "XML sitemap or sitemap index URLs (gzip supported). These are read before discovered sitemaps.", "items": { "type": "string" } }, "urls": { "title": "Extra URLs", "type": "array", "description": "Individual URLs to audit (in addition to, or instead of, sitemaps).", "items": { "type": "string" } }, "maxUrls": { "title": "Max URLs per run", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Hard cap after sampling. Never more than your max-charge limit allows.", "default": 500 }, "samplesPerTemplate": { "title": "Samples per template", "minimum": 0, "maximum": 1000, "type": "integer", "description": "0 = audit every sitemap URL (up to Max URLs). Otherwise, the number of URLs per site and page template (product, post, category…), chosen deterministically.", "default": 0 }, "templateRules": { "title": "Template rules (optional)", "type": "array", "description": "Override template detection. Items: {\"name\": \"product\", \"pattern\": \"/shop/\"} (regex tested on the URL)." }, "requestsPerSecondPerHost": { "title": "Requests per second per site", "minimum": 1, "maximum": 10, "type": "integer", "description": "Politeness limit per host. A robots.txt Crawl-delay of 1 s or more is honoured (capped at 10 s).", "default": 4 }, "checkHreflang": { "title": "Check hreflang", "type": "boolean", "description": "Validate language codes, self-reference, x-default and reciprocity between audited pages.", "default": true }, "monitorId": { "title": "Monitor ID (for regression alerts)", "type": "string", "description": "Set a name (letters, digits, hyphens) to compare each run with the previous one and flag URLs that became non-indexable. Stored in your account in the key-value store \"indexability-monitor-\"." }, "healthCheck": { "title": "Health check mode", "type": "boolean", "description": "Internal: runs a fixed known-good input. Never charged.", "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 }, "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 } } } } } } } } } }