{
"openapi": "3.0.1",
"info": {
"title": "Sitemap and Broken Link Checker with On-Page SEO Audit",
"description": "Check your sitemap URLs, any list of URLs, or every link on your pages: status, redirect chain, noindex, canonical, robots.txt, and broken links with the page and anchor text they sit on. On-page SEO rules (title, meta description, H1, canonical, alt text, schema, hreflang) with fix hints.",
"version": "0.2",
"x-build-id": "mYmUP2mS2bTbCrIm1"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/madrasco~sitemap-health-check/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-madrasco-sitemap-health-check",
"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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/madrasco~sitemap-health-check/runs": {
"post": {
"operationId": "runs-sync-madrasco-sitemap-health-check",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/madrasco~sitemap-health-check/run-sync": {
"post": {
"operationId": "run-sync-madrasco-sitemap-health-check",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"mode": {
"title": "What to check",
"enum": [
"sitemap",
"urlList",
"pageLinks"
],
"type": "string",
"description": "sitemap: find the sitemaps of the site(s) in 'url' and check every URL listed. urlList: check exactly the URLs given (any site, one per line). pageLinks: read the pages given (a sitemap URL is expanded into its pages) and check every link and image on them once: broken, redirected, refused, unreachable, with the page and anchor text each sits on. On-page rules run on every HTML page read in all modes.",
"default": "sitemap"
},
"url": {
"title": "Sitemap, website or page URLs",
"type": "string",
"description": "sitemap mode: a sitemap (https://example.com/sitemap.xml, .xml.gz, index files welcome) or a website (then sitemaps come from robots.txt Sitemap lines, else /sitemap.xml or /sitemap_index.xml). urlList mode: the URLs to check. pageLinks mode: the pages whose links to check, or a sitemap of them. Separate several with spaces or new lines."
},
"sitemapUrls": {
"title": "More URLs",
"type": "array",
"description": "Optional: more URLs as a list (up to 20 sitemaps/sites, 100 pages in pageLinks mode, 50,000 URLs in urlList mode). Also accepted as 'urls' or 'startUrls'.",
"items": {
"type": "string"
}
},
"maxUrls": {
"title": "Maximum URLs or pages to check",
"minimum": 1,
"maximum": 50000,
"type": "integer",
"description": "Stop after this many unique URLs (sitemap and urlList modes) or pages read (pageLinks mode). The summary says when the cap was reached.",
"default": 5000
},
"maxSitemaps": {
"title": "Maximum sitemap files to read",
"minimum": 1,
"maximum": 1000,
"type": "integer",
"description": "Limit on sitemap files, counting index files and their children.",
"default": 100
},
"onlyProblems": {
"title": "Only list URLs with problems",
"type": "boolean",
"description": "Leave healthy URLs out of the dataset (they are still counted in the summary).",
"default": false
},
"checkPageTags": {
"title": "Check meta robots and canonical tags",
"type": "boolean",
"description": "Download the page HTML (first 1 MB) to read and . Off: status, redirects and headers only (HEAD requests, faster).",
"default": true
},
"respectRobotsTxt": {
"title": "Respect robots.txt",
"type": "boolean",
"description": "Don't request URLs the site's robots.txt disallows for our crawler; they are reported as blocked (a real sitemap problem). Turn off only for sites you own.",
"default": true
},
"sameHostOnly": {
"title": "Only check URLs on the sitemap's own site",
"type": "boolean",
"description": "URLs on other hosts are reported but not requested (the www and non-www variants count as the same site).",
"default": true
},
"delaySecs": {
"title": "Delay between requests to a host (s)",
"minimum": 0,
"maximum": 30,
"type": "integer",
"description": "Minimum spacing between request starts to one host; a larger robots.txt Crawl-delay (up to 10 s) wins.",
"default": 1
},
"maxConcurrencyPerHost": {
"title": "Requests at once per host",
"minimum": 1,
"maximum": 2,
"type": "integer",
"description": "1 or 2. Never more than 2, to stay gentle on the site.",
"default": 2
},
"timeoutSecs": {
"title": "Request timeout (s)",
"minimum": 3,
"maximum": 60,
"type": "integer",
"description": "Per request.",
"default": 20
},
"maxLinks": {
"title": "Maximum links to check (pageLinks)",
"minimum": 1,
"maximum": 50000,
"type": "integer",
"description": "pageLinks mode: stop after this many unique links. Each link is checked once however many pages it is on.",
"default": 2000
},
"checkExternalLinks": {
"title": "Check links to other sites (pageLinks)",
"type": "boolean",
"description": "Off: only links to the page's own site are checked. Each other site's robots.txt is read and obeyed too.",
"default": true
},
"checkImages": {
"title": "Check images (pageLinks)",
"type": "boolean",
"description": "Also check ![]()
addresses.",
"default": true
},
"checkOnPage": {
"title": "On-page rules",
"type": "boolean",
"description": "Title, meta description, H1, canonical, html lang, viewport, image alt, structured data (JSON-LD, microdata, RDFa) and hreflang checks on every HTML page read. Needs 'Check meta robots and canonical tags' on (the page must be downloaded).",
"default": true
}
}
},
"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
}
}
}
}
}
}
}
}
}
}