{ "openapi": "3.0.1", "info": { "title": "Sitemap Extractor & Website URL Finder (no sitemap needed)", "description": "Get every URL of a website: reads robots.txt, nested sitemap indexes, .xml.gz and text sitemaps, then RSS/Atom feeds, and falls back to a light crawl when there is no sitemap. URL, lastmod, changefreq, priority, source. Filters by URL pattern and date. Failed sites are free.", "version": "0.1", "x-build-id": "iZOtCc7pWAJaBYrlZ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/kilndata~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-kilndata-sitemap-url-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/kilndata~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-kilndata-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/kilndata~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-kilndata-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "One per line. A domain (\"example.com\") or homepage triggers automatic discovery. A direct sitemap or feed URL (\"https://example.com/sitemap.xml\", \".xml.gz\", \"/feed\") is read as is. Duplicates are removed.", "items": { "type": "string" } }, "includeUrlPatterns": { "title": "Only URLs matching", "type": "array", "description": "Optional. Keep only URLs that match at least one pattern. Regular expressions (case-insensitive) or simple wildcards: \"/blog/\", \"/products/.*\", \"https://example.com/docs/*\", \"\\.pdf$\".", "default": [], "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URLs matching", "type": "array", "description": "Optional. Drop URLs that match any of these patterns, e.g. \"/tag/\", \"/page/\\d+\", \"\\?\".", "default": [], "items": { "type": "string" } }, "lastmodAfter": { "title": "Modified after", "type": "string", "description": "Optional. Keep only URLs whose lastmod (or feed date) is on/after this date. An absolute date (\"2025-01-31\") or a relative one (\"30 days\", \"2 weeks\", \"6 months\").", "default": "" }, "lastmodBefore": { "title": "Modified before", "type": "string", "description": "Optional. Keep only URLs whose lastmod is on/before this date. Same formats as above (\"1 year\" = older than one year).", "default": "" }, "includeUrlsWithoutLastmod": { "title": "Keep URLs without a lastmod when filtering by date", "type": "boolean", "description": "Only matters when a date filter is set. Many sitemaps have no lastmod; turn this on to keep those URLs anyway.", "default": false }, "maxUrlsPerSite": { "title": "Max URLs per website", "minimum": 0, "type": "integer", "description": "Stop a website after this many URLs (after filters). 0 = no limit.", "default": 0 }, "limitToStartPath": { "title": "Only URLs under the start path", "type": "boolean", "description": "When a start URL has a path (e.g. \"https://example.com/blog/\"), return only URLs under that path. Domains and homepages always return the whole website.", "default": true }, "feeds": { "title": "Use RSS/Atom feeds", "enum": [ "fallback", "always", "never" ], "type": "string", "description": "\"fallback\" reads feeds only when no sitemap URL was found. \"always\" also adds feed URLs (useful for the freshest posts). \"never\" skips feeds.", "default": "fallback" }, "crawlFallback": { "title": "Crawl when there is no sitemap or feed", "type": "boolean", "description": "If a website has no usable sitemap and no feed, follow its internal links (same domain, robots.txt respected) to list its URLs.", "default": true }, "maxCrawlPages": { "title": "Max pages to crawl (fallback)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "How many HTML pages the crawl fallback downloads per website. Every internal link found on those pages is returned, so 50 pages usually yield hundreds of URLs.", "default": 50 }, "includeExtras": { "title": "Include images and hreflang alternates", "type": "boolean", "description": "Add \"images\" (image:image locations) and \"alternates\" (xhtml:link hreflang versions) from the sitemap to each URL.", "default": false }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Probing common sitemap locations and the crawl fallback skip paths disallowed by robots.txt. Sitemaps listed in robots.txt are always read.", "default": true }, "maxConcurrency": { "title": "Websites in parallel", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many websites are processed at the same time.", "default": 10 }, "sitemapConcurrency": { "title": "Parallel requests per website", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many sitemap files of the same website are downloaded at the same time. Keep it low to be polite.", "default": 5 }, "maxSitemapDepth": { "title": "Max sitemap index depth", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many levels of nested sitemap indexes to follow (index → index → sitemap). Loops are detected automatically.", "default": 5 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 300, "type": "integer", "description": "Time allowed to download one file (large sitemaps can take a while).", "default": 60 }, "siteTimeoutSecs": { "title": "Time limit per website (seconds)", "minimum": 30, "maximum": 86400, "type": "integer", "description": "When reached, the website stops and keeps the URLs collected so far, so one huge site never blocks the run.", "default": 900 }, "maxRetries": { "title": "Max retries per file", "minimum": 0, "maximum": 5, "type": "integer", "description": "Retries for network errors, 429 and 5xx. Each retry changes strategy (HTTP/2 → HTTP/1.1 → different client).", "default": 2 }, "ignoreSslErrors": { "title": "Ignore SSL certificate errors", "type": "boolean", "description": "Read public sitemaps even from websites with expired or misconfigured certificates.", "default": true }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Sitemaps are public and almost never need a proxy. Use one only if a website blocks the requests.", "default": { "useApifyProxy": 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 } } } } } } } } } }