{ "openapi": "3.0.1", "info": { "title": "Sitemap Extractor & Change Monitor (new/removed/updated URLs)", "description": "Extract every URL from any website's sitemaps (robots.txt, sitemap index, nested, .gz, news/image/video, RSS/Atom fallback) with lastmod, changefreq and priority. Schedule it to get only added, removed and updated URLs, and optional page-content change checks.", "version": "0.1", "x-build-id": "azCY47AuEPaL90W5j" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datlab~sitemap-change-monitor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datlab-sitemap-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datlab~sitemap-change-monitor/runs": { "post": { "operationId": "runs-sync-datlab-sitemap-change-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datlab~sitemap-change-monitor/run-sync": { "post": { "operationId": "run-sync-datlab-sitemap-change-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "type": "array", "description": "Domains or any page URL (e.g. `example.com`, `https://www.example.com/blog`). Sitemaps are found from robots.txt `Sitemap:` lines, then common paths (/sitemap.xml, /sitemap_index.xml, /wp-sitemap.xml, …), then RSS/Atom feeds. A URL that is itself a sitemap or feed (ends in .xml, .xml.gz, .txt, /feed …) is read directly.", "items": { "type": "string" } }, "sitemapUrls": { "title": "Sitemap or feed URLs", "type": "array", "description": "Optional. Exact sitemap, sitemap index, .gz, RSS or Atom URLs to read as-is (no discovery).", "items": { "type": "string" } }, "includePatterns": { "title": "Include URLs matching", "type": "array", "description": "Keep only URLs matching at least one pattern. Plain text or a path like `/blog/` = substring (case-insensitive); `*` = wildcard over the whole URL (e.g. `https://example.com/blog/*`); `/regex/i` = regular expression.", "items": { "type": "string" } }, "excludePatterns": { "title": "Exclude URLs matching", "type": "array", "description": "Drop URLs matching any of these patterns (same syntax as include).", "items": { "type": "string" } }, "maxUrls": { "title": "Max URLs per site", "minimum": 0, "type": "integer", "description": "Stop reading a site after this many URLs (after filters). 0 = no limit. When the cap is hit, the newest child sitemaps (by lastmod) are read first and removals are not reported for that run.", "default": 10000 }, "maxSitemapsPerSite": { "title": "Max sitemap files per site", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Safety cap on the number of sitemap files (including nested ones) read per site.", "default": 500 }, "discoverSitemaps": { "title": "Probe common sitemap paths", "type": "boolean", "description": "When robots.txt lists no sitemap, try /sitemap.xml, /sitemap_index.xml, /wp-sitemap.xml, /sitemap.xml.gz, /sitemap.txt and similar.", "default": true }, "rssFallback": { "title": "Fall back to RSS/Atom feeds", "type": "boolean", "description": "When no sitemap exists, use the RSS/Atom feed linked from the home page (or /feed, /rss.xml, /atom.xml …).", "default": true }, "includeExtensions": { "title": "Include news / image / video fields", "type": "boolean", "description": "Add Google News (title, publication, date), image URLs and video titles when the sitemap has them.", "default": true }, "trackChanges": { "title": "Monitor changes between runs", "type": "boolean", "description": "Save the URL list after each run and mark every URL as added, lastmodChanged or unchanged, plus removed URLs. The first run records the baseline.", "default": false }, "onlyChanges": { "title": "Output only changes", "type": "boolean", "description": "Output only added, removed and lastmod-changed URLs (and changed pages). Turns on monitoring. Ideal for schedules + webhooks/integrations.", "default": false }, "outputBaseline": { "title": "Output all URLs on the first (baseline) run", "type": "boolean", "description": "With 'Output only changes', the first run normally outputs nothing and only records the baseline. Turn on to output the full list on that run too.", "default": false }, "stateKey": { "title": "Monitor name", "type": "string", "description": "Name of the saved state. Use a different name for each separate monitor (e.g. per task/schedule). State is kept in your named key-value store `sitemap-change-monitor-state`.", "default": "default" }, "pageCheckUrls": { "title": "Pages to check for content changes", "type": "array", "description": "Optional. These pages are downloaded and their main text is hashed (scripts, navigation, header/footer removed) to detect content changes between runs. Max 1000. Respects robots.txt.", "items": { "type": "string" } }, "pageCheckOnlyChanged": { "title": "Only check pages whose sitemap entry changed", "type": "boolean", "description": "With monitoring on, fetch only pages from the list that are new or whose sitemap lastmod changed (plus never-checked pages). Saves requests and cost.", "default": false }, "pageCheckDetails": { "title": "Include title & meta", "type": "boolean", "description": "Also compare and output title, meta description, canonical URL and meta robots.", "default": true }, "contentSelector": { "title": "Content CSS selector", "type": "string", "description": "Optional. Hash only the text inside this CSS selector (e.g. `#pricing`, `article .price`). Default:
, [role=main] or
, else the body without header/footer/nav." }, "ignoreTextPatterns": { "title": "Ignore text matching", "type": "array", "description": "Text removed before hashing so it doesn't count as a change, e.g. `/\\d+ views/` or `Last updated`. Plain text or `/regex/flags`.", "items": { "type": "string" } }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Parallel requests across all sites.", "default": 5 }, "perHostDelaySecs": { "title": "Seconds between requests to the same host", "minimum": 0.25, "maximum": 60, "type": "number", "description": "Polite per-host delay (min 0.25). A robots.txt Crawl-delay is honoured up to 30 s.", "default": 1 }, "maxRequestsPerMinute": { "title": "Max requests per minute (total)", "minimum": 1, "maximum": 600, "type": "integer", "description": "Upper limit on requests per minute across all hosts. A host's robots.txt Crawl-delay is always respected on top of this.", "default": 120 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Usually not needed: sitemaps are public. Use a proxy only if a site blocks datacenter IPs." } } }, "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 } } } } } } } } } }