{ "openapi": "3.0.1", "info": { "title": "Sitemap Extractor, URL Status Checker & New Page Monitor", "description": "Extract every URL from any website's XML sitemaps (auto-discovered, indexes, gzip, text, RSS), optionally check each URL's status, redirects, noindex and canonical, or schedule it to report only new, updated and removed pages. No browser, no login.", "version": "1.0", "x-build-id": "kTAe82yNhwNO8eglt" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/mercury_ops~sitemap-url-monitor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-mercury_ops-sitemap-url-monitor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/mercury_ops~sitemap-url-monitor/runs": { "post": { "operationId": "runs-sync-mercury_ops-sitemap-url-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/mercury_ops~sitemap-url-monitor/run-sync": { "post": { "operationId": "run-sync-mercury_ops-sitemap-url-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 homepage (sitemaps are found via robots.txt, then /sitemap.xml, /sitemap_index.xml, /wp-sitemap.xml, /sitemap.txt) or a direct sitemap URL (.xml, .xml.gz, .txt, RSS/Atom). Sitemap indexes are followed automatically.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "mode": { "title": "Mode", "enum": [ "all", "changes" ], "type": "string", "description": "'All URLs' lists every URL (one billable row per URL). 'Changes only' compares with the previous run of the same monitor and outputs only new, updated (lastmod changed) and removed URLs; the first run saves a baseline. Schedule it daily to watch competitors' new pages.", "default": "all" }, "checkStatus": { "title": "Check each URL (status, redirects, noindex, canonical)", "type": "boolean", "description": "Requests each output URL once and reports HTTP status, redirect chain, X-Robots-Tag, meta robots, canonical, response time and an 'indexable' flag. Billed per URL checked. In 'Changes only' mode only new and updated URLs are checked.", "default": false }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 1, "maximum": 200000, "type": "integer", "description": "Stop after this many unique URLs per site.", "default": 5000 }, "includePattern": { "title": "Only URLs matching (regex)", "type": "string", "description": "Optional. Case-insensitive regular expression, e.g. /blog/ or /products/. Non-matching URLs are skipped and not billed." }, "excludePattern": { "title": "Skip URLs matching (regex)", "type": "string", "description": "Optional. Case-insensitive regular expression, e.g. /tag/|/author/." }, "monitorName": { "title": "Monitor name", "type": "string", "description": "Changes only: snapshots are kept per monitor name and site in a key-value store named 'sitemap-url-monitor-state' in your account. Use different names for separate monitors on the same site.", "default": "default" }, "maxConcurrency": { "title": "Status-check concurrency per site", "minimum": 1, "maximum": 10, "type": "integer", "description": "Parallel requests when checking URLs. Keep it low to be polite to the site.", "default": 4 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Not needed for most sites. Enable it if a site rate-limits you.", "default": { "useApifyProxy": 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 } } } } } } } } } }