{
"openapi": "3.0.1",
"info": {
"title": "Sitemap Extractor & Change Tracker",
"description": "Extract every URL from a website's sitemaps (finds them even when they're hidden) and track new, updated and removed pages between runs. Reports blocked or broken sitemaps instead of failing.",
"version": "0.1",
"x-build-id": "lQb6s42zpXnvBIJLe"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/codemagnet~sitemap-change-tracker/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-codemagnet-sitemap-change-tracker",
"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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/codemagnet~sitemap-change-tracker/runs": {
"post": {
"operationId": "runs-sync-codemagnet-sitemap-change-tracker",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/codemagnet~sitemap-change-tracker/run-sync": {
"post": {
"operationId": "run-sync-codemagnet-sitemap-change-tracker",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": "Websites (like example.com) or direct sitemap addresses. For a website, the Actor finds the sitemaps itself: robots.txt first, then common locations like /sitemap.xml and /wp-sitemap.xml, then the home page.",
"default": [
"https://crawlee.dev"
],
"items": {
"type": "string"
}
},
"output": {
"title": "What to save",
"enum": [
"all",
"changes"
],
"type": "string",
"description": "All URLs: every URL, each marked new, updated, unchanged or removed. Only changes: just new, updated and removed pages since the last run (the first run only records a starting point). Best for scheduled monitoring.",
"default": "all"
},
"trackChanges": {
"title": "Track changes between runs",
"type": "boolean",
"description": "Remember each site's URLs (in a storage on your own account) and compare with the previous run. Turn off for a one-off list.",
"default": true
},
"includePatterns": {
"title": "Only URLs containing",
"type": "array",
"description": "Keep only URLs matching at least one pattern. A pattern matches anywhere in the URL; * is a wildcard. Examples: /blog/, /products/*/reviews. Start with re: for a regular expression, e.g. re:/20(25|26)/.",
"items": {
"type": "string"
}
},
"excludePatterns": {
"title": "Skip URLs containing",
"type": "array",
"description": "Drop URLs matching any of these patterns (same syntax as above). Example: /tag/, ?page=.",
"items": {
"type": "string"
}
},
"modifiedSince": {
"title": "Modified since",
"type": "string",
"description": "Only save URLs whose sitemap date (lastmod) is on or after this date, e.g. 2026-09-01, or a period like 7 days. URLs without a date are left out. Removed pages are always reported."
},
"maxUrlsPerSite": {
"title": "Max URLs per site",
"minimum": 1,
"type": "integer",
"description": "Stop reading a site's sitemaps after this many URLs. Leave empty for no limit. (When a scan stops early, removed pages are not reported for that run.)"
},
"historyName": {
"title": "History name",
"type": "string",
"description": "Name of the storage (on your account) that remembers URLs between runs. Use a different name to keep separate histories, for example one per project.",
"default": "sitemap-change-tracker"
},
"resetHistory": {
"title": "Start history fresh",
"type": "boolean",
"description": "Ignore what was remembered before and treat this run as the first one.",
"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
}
}
}
}
}
}
}
}
}
}