{ "openapi": "3.0.1", "info": { "title": "Sitemap Extractor & Change Monitor (No Proxy)", "description": "Every URL in a site's sitemaps with lastmod, changefreq and priority. Finds sitemaps via robots.txt, reads indexes, gzip, RSS and Atom, validates the protocol, checks llms.txt, and monitors added, removed and changed pages.", "version": "1.0", "x-build-id": "KviCs8n6c9vXdDoFH" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/saiberops~sitemap-extractor-change-monitor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-saiberops-sitemap-extractor-change-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/saiberops~sitemap-extractor-change-monitor/runs": { "post": { "operationId": "runs-sync-saiberops-sitemap-extractor-change-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/saiberops~sitemap-extractor-change-monitor/run-sync": { "post": { "operationId": "run-sync-saiberops-sitemap-extractor-change-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "startUrls": { "title": "Websites or sitemap URLs", "type": "array", "description": "Domains (example.com), sitemap or sitemap-index URLs (including .xml.gz), robots.txt URLs, or RSS/Atom feed URLs. For a domain, sitemaps are found through robots.txt, then common locations.", "items": { "type": "string" } }, "mode": { "title": "Mode", "enum": [ "map", "monitor" ], "type": "string", "description": "map: every URL found. monitor: compare with the snapshot saved by your previous run and output only URLs that were added, removed or had their lastmod change. The first monitor run saves the baseline.", "default": "map" }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Stops reading a site's sitemaps after this many URLs (the site report says truncated). Each output URL is one charged event.", "default": 50000 }, "checkStatus": { "title": "Check each URL's HTTP status", "type": "boolean", "description": "Sends a HEAD request to each output URL and records status code, final URL, content type and Last-Modified. Charged per URL with a definitive answer.", "default": false }, "includePatterns": { "title": "Only include URLs containing", "type": "array", "description": "Substrings, or regular expressions starting with re:, e.g. /blog/ or re:/products?/. Leave empty for all URLs.", "items": { "type": "string" } }, "excludePatterns": { "title": "Exclude URLs containing", "type": "array", "description": "Substrings or re: regular expressions. Excluded URLs are not output or charged.", "items": { "type": "string" } }, "checkLlmsTxt": { "title": "Check llms.txt", "type": "boolean", "description": "Adds /llms.txt and /llms-full.txt presence, size, title and section count to each site report.", "default": true }, "probeCommonPaths": { "title": "Probe common sitemap locations", "type": "boolean", "description": "When robots.txt lists no sitemap, try /sitemap.xml, /sitemap_index.xml, /wp-sitemap.xml and similar.", "default": true }, "emitBaselineRows": { "title": "Monitor: output all URLs on the first run", "type": "boolean", "description": "On the first monitor run for a site, output every URL as a baseline row. Turn off to only save the snapshot (you then pay only for the site report).", "default": true }, "emitUnchanged": { "title": "Monitor: also output unchanged URLs", "type": "boolean", "description": "Unchanged URLs are normally skipped (and free).", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "On by default. Sitemaps declared in robots.txt are read even if a Disallow rule covers them (flagged in the output); probed paths and status checks obey Disallow. Turn off only for sites you own.", "default": true }, "maxIndexDepth": { "title": "Max nested sitemap-index levels", "minimum": 1, "maximum": 5, "type": "integer", "description": "How many levels of sitemap indexes to follow.", "default": 3 }, "maxSitemapFilesPerSite": { "title": "Max sitemap files per site", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Guards against huge indexes. The site report says when the limit was reached.", "default": 500 }, "maxConcurrency": { "title": "Max parallel requests", "minimum": 1, "maximum": 50, "type": "integer", "description": "Total parallel connections.", "default": 10 }, "maxConcurrencyPerHost": { "title": "Max parallel status checks per site", "minimum": 1, "maximum": 20, "type": "integer", "description": "Keeps the load on each website polite.", "default": 4 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 3, "maximum": 60, "type": "integer", "description": "Per request; sitemap files get twice this.", "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 } } } } } } } } } }