{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor – All Pages for RAG & SEO", "description": "Get every URL a website publishes: XML sitemaps, sitemap indexes, gzip and news sitemaps, RSS/Atom feeds, plus a shallow crawl when there's no sitemap. lastmod, source and robots.txt status per URL. Feed it to your RAG pipeline, crawler or SEO audit. $0.40 per 1,000 URLs.", "version": "0.1", "x-build-id": "APHeJQYG1TsercjU4" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/oldjard~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-oldjard-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/oldjard~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-oldjard-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/oldjard~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-oldjard-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", "type": "array", "description": "Websites, one per line or comma-separated. example.com lists the whole site. A URL with a path (https://docs.example.com/guide) lists only that section; turn off limitToStartPath to change this. A sitemap or feed URL (https://example.com/sitemap_news.xml) is read directly. Duplicates and blank lines are removed; an entry that isn't a web address gets a free error row.", "items": { "type": "string" } }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 0, "type": "integer", "description": "Stop a site after this many URLs (after filters and dedupe). 0 means no limit. Each URL output is one url-found charge, so this also caps the cost per site.", "default": 10000 }, "includePatterns": { "title": "Only URLs matching", "type": "array", "description": "Keep only URLs matching at least one pattern. Globs with * match the path and query, e.g. /blog/*, *.pdf, /docs/*/api/*. A glob starting with https:// matches the whole URL. Wrap a pattern in slashes for a regular expression on the whole URL, e.g. /\\/v[0-9]+\\//i. Empty = keep everything.", "items": { "type": "string" } }, "excludePatterns": { "title": "Skip URLs matching", "type": "array", "description": "Drop URLs matching any of these patterns (same syntax as above), e.g. /tag/*, /author/*, *?page=*.", "items": { "type": "string" } }, "modifiedSince": { "title": "Modified since", "type": "string", "description": "Only URLs whose sitemap or feed date (lastmod, publication date) is on or after this date, for refreshing a RAG index with just what changed. Accepts a date (2026-09-01) or a period (7 days, 2 weeks). URLs without any date are skipped when this is set." }, "includeFeeds": { "title": "Also read RSS/Atom feeds", "type": "boolean", "description": "Read the RSS or Atom feeds the site links from its start page. Feeds often list the newest posts before the sitemap does, and give a title and publication date.", "default": true }, "crawlMode": { "title": "Crawl links", "enum": [ "fallback", "always", "off" ], "type": "string", "description": "Only when there's no sitemap or feed (default): follow the site's own links a few levels deep. Always: also crawl sites that have a sitemap, to catch pages missing from it. Never: sitemaps and feeds only. The crawl stays on the site, honours robots.txt and fetches only HTML pages.", "default": "fallback" }, "maxCrawlPages": { "title": "Max pages to crawl per site", "minimum": 0, "maximum": 5000, "type": "integer", "description": "How many pages the link crawl may open per site. Every link on those pages is reported, so 50 pages usually find hundreds of URLs.", "default": 50 }, "maxCrawlDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many clicks away from the start page the crawl goes. 1 = only links on the start page.", "default": 2 }, "sameDomainOnly": { "title": "Only the site's own domain", "type": "boolean", "description": "Drop URLs on other domains that a sitemap or feed lists (subdomains like blog.example.com are kept).", "default": true }, "limitToStartPath": { "title": "Only the start URL's section", "type": "boolean", "description": "For a start URL with a path (like https://example.com/docs), keep only URLs under that path.", "default": true }, "maxSitemapsPerSite": { "title": "Max sitemaps per site", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Safety cap on how many sitemap and feed files to read per site. Very large sites (news, marketplaces) can have thousands.", "default": 1000 }, "maxConcurrency": { "title": "Sites in parallel", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many sites to work on at the same time. Each site is visited politely: at most 3 requests at once, honouring any robots.txt Crawl-delay.", "default": 5 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Give up on a request whose server hasn't started answering within this time.", "default": 30 } } }, "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 } } } } } } } } } }