{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor & New Page Monitor", "description": "Extract every URL from a website's XML sitemaps (auto-discovered from robots.txt, sitemap indexes, .gz, hreflang, news and image sitemaps) or monitor sitemaps for new, modified and removed pages. Fast HTTP-only, pay per URL.", "version": "1.0", "x-build-id": "gOvNE9ftSfOHIDczL" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/moha-tah~sitemap-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-moha-tah-sitemap-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/moha-tah~sitemap-extractor/runs": { "post": { "operationId": "runs-sync-moha-tah-sitemap-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/moha-tah~sitemap-extractor/run-sync": { "post": { "operationId": "run-sync-moha-tah-sitemap-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 website (https://example.com: sitemaps are discovered from robots.txt and common paths) or a direct sitemap / sitemap index URL (.xml, .xml.gz, .txt, RSS).", "default": [ "https://apify.com" ], "items": { "type": "string" } }, "mode": { "title": "Mode", "enum": [ "extract", "monitor" ], "type": "string", "description": "Extract = list every URL. Monitor = only report URLs added, modified or removed since the previous run with the same monitor name (schedule it daily or weekly). The first monitor run stores a baseline.", "default": "extract" }, "monitorName": { "title": "Monitor name", "type": "string", "description": "Monitor mode only. Runs with the same name share state. Use different names for independent watchlists.", "default": "default" }, "includeUrlPatterns": { "title": "Only URLs matching (regex)", "type": "array", "description": "Keep URLs matching at least one regular expression, e.g. /blog/ or /products/.", "default": [], "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URLs matching (regex)", "type": "array", "description": "Drop URLs matching any of these regular expressions, e.g. /tag/ or \\?page=.", "default": [], "items": { "type": "string" } }, "lastmodAfter": { "title": "Modified after", "type": "string", "description": "Keep only URLs whose is after this date. Accepts 2026-01-31 or a relative value like '7 days' or '24 hours'. URLs without lastmod are dropped when set." }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 0, "type": "integer", "description": "Stop collecting a site after this many URLs (0 = unlimited). Keeps test runs cheap.", "default": 10000 }, "includeAlternates": { "title": "Include hreflang alternates", "type": "boolean", "description": "Adds the language/region alternate URLs declared in the sitemap.", "default": true }, "includeImages": { "title": "Include image URLs", "type": "boolean", "description": "Adds up to 20 image URLs per page from image sitemaps.", "default": false }, "reportModified": { "title": "Report modified pages", "type": "boolean", "description": "Monitor mode: report URLs whose lastmod changed.", "default": true }, "reportRemoved": { "title": "Report removed pages", "type": "boolean", "description": "Monitor mode: report URLs that disappeared from the sitemaps (skipped when a limit truncated the crawl).", "default": true }, "emitBaseline": { "title": "Output all URLs on the first run", "type": "boolean", "description": "Monitor mode: also output every URL (changeType 'baseline') on the first run.", "default": false }, "maxSitemapsPerSite": { "title": "Max sitemap files per site", "minimum": 1, "type": "integer", "description": "Safety limit for very large sitemap indexes.", "default": 500 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip sitemap files disallowed by robots.txt.", "default": true }, "maxConcurrency": { "title": "Sites in parallel", "minimum": 1, "maximum": 20, "type": "integer", "description": "Sites processed at the same time. Each site is fetched politely, one sitemap after another.", "default": 5 } } }, "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 } } } } } } } } } }