{ "openapi": "3.0.1", "info": { "title": "Sitemap Extractor & URL Discovery", "description": "Find the page URLs a website lists in robots.txt and XML sitemaps (sitemap indexes, gzip, text sitemaps, hreflang, lastmod), with a polite shallow-crawl fallback. Clean JSON for crawlers, SEO audits, RAG and AI agents.", "version": "0.1", "x-build-id": "oe5IO3sRh4WjMBvGf" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/madpai~sitemap-url-discovery/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-madpai-sitemap-url-discovery", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/madpai~sitemap-url-discovery/runs": { "post": { "operationId": "runs-sync-madpai-sitemap-url-discovery", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/madpai~sitemap-url-discovery/run-sync": { "post": { "operationId": "run-sync-madpai-sitemap-url-discovery", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "Websites or sitemap URLs", "type": "array", "description": "Domains (example.com), homepage URLs, or direct sitemap URLs. Sitemaps are found via robots.txt, then common paths like /sitemap.xml.", "items": { "type": "string" } }, "maxUrls": { "title": "Max URLs", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Total cap on URLs saved across all inputs. You pay per URL saved, so this also caps cost.", "default": 1000 }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 0, "type": "integer", "description": "Cap per input so one big site can't use the whole budget. 0 = no per-site cap.", "default": 0 }, "includeRegex": { "title": "Include URLs matching (regex)", "type": "string", "description": "Keep only URLs matching this case-insensitive regular expression, e.g. /blog/." }, "excludeRegex": { "title": "Exclude URLs matching (regex)", "type": "string", "description": "Drop URLs matching this case-insensitive regular expression, e.g. /tag/|/page/\\d+." }, "lastmodAfter": { "title": "Only URLs modified after", "type": "string", "description": "Keep only URLs whose sitemap lastmod is on or after this date (YYYY-MM-DD). Useful for change monitoring. URLs without lastmod are dropped when set." }, "fallbackCrawl": { "title": "Crawl links if no sitemap", "type": "boolean", "description": "If a site has no usable sitemap, follow same-site links from the homepage (HTTP only, shallow).", "default": true }, "maxCrawlPages": { "title": "Max pages to crawl (fallback)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Pages fetched per site during the fallback crawl. Each page can reveal many URLs.", "default": 30 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Don't fetch sitemaps or pages disallowed by robots.txt. Can only be turned off together with \"I own these sites\".", "default": true }, "checkRobotsForUrls": { "title": "Flag URLs blocked by robots.txt", "type": "boolean", "description": "Add allowedByRobots to each URL, checked against the robots.txt of the URL's own host (one extra robots.txt request per other host, max 10; otherwise null with a robotsNote).", "default": true }, "maxSitemapsPerDomain": { "title": "Max sitemap files per site", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Safety cap on sitemap files fetched per site, including nested indexes.", "default": 300 }, "requestDelayMs": { "title": "Delay between requests to a site (ms)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Per-site delay between requests (about 1 request per second by default). robots.txt Crawl-delay is honoured if longer. Values under 1000 ms only apply with \"I own these sites\" checked.", "default": 1000 }, "maxConcurrency": { "title": "Sites in parallel", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many sites to process at once.", "default": 5 }, "ownSiteConfirmed": { "title": "I own or am authorised to crawl these sites", "type": "boolean", "description": "Only check this for your own sites. It allows turning off robots.txt and using delays under 1 second.", "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 } } } } } } } } } }