{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor - All Pages from Any Website, $0.20/1K", "description": "Get every page URL of any website from its sitemaps: auto-finds robots.txt and CMS sitemaps, follows indexes and .gz, adds lastmod, images, video, news and hreflang. Date and pattern filters, optional status check. $0.20 per 1,000 URLs.", "version": "0.1", "x-build-id": "3MSYFamdTX00LYTE7" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/plotpointtech~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-plotpointtech-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/plotpointtech~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-plotpointtech-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/plotpointtech~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-plotpointtech-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", "properties": { "startUrls": { "title": "Websites or sitemap URLs", "type": "array", "description": "Domains (example.com), home pages, or direct sitemap / RSS feed URLs. For a domain, the tool finds sitemaps in robots.txt and at common locations (/sitemap.xml, /sitemap_index.xml, /wp-sitemap.xml and more).", "default": [ "https://wordpress.org/news/" ], "items": { "type": "string" } }, "maxUrlsPerSite": { "title": "Maximum URLs per website", "minimum": 1, "maximum": 10000000, "type": "integer", "description": "Stop after this many URLs from each website (after filters and de-duplication). This also caps your cost.", "default": 1000 }, "stayInStartPath": { "title": "Stay in the start URL's folder", "type": "boolean", "description": "If you enter a section such as https://example.com/blog/, keep only URLs under /blog/. Turn off to get every URL of the whole website. Has no effect for domains, home pages or direct sitemap URLs.", "default": true }, "includePatterns": { "title": "Only URLs matching", "type": "array", "description": "Keep only URLs that contain a match for at least one of these regular expressions or * wildcards, e.g. /blog/ or *product*.", "default": [], "items": { "type": "string" } }, "excludePatterns": { "title": "Skip URLs matching", "type": "array", "description": "Drop URLs that match any of these regular expressions or * wildcards, e.g. /tag/ or \\?page=.", "default": [], "items": { "type": "string" } }, "lastmodAfter": { "title": "Only URLs modified after", "type": "string", "description": "Keep only URLs whose lastmod (or news / RSS publication date) is on or after this date. Use YYYY-MM-DD or a relative period such as '7 days', '3 months'. Child sitemaps older than this date are skipped, which makes runs on big sites much faster." }, "keepUrlsWithoutLastmod": { "title": "Keep URLs without lastmod when filtering by date", "type": "boolean", "description": "When 'Only URLs modified after' is set, also keep URLs that have no date in the sitemap.", "default": false }, "dedupe": { "title": "Remove duplicate URLs", "type": "boolean", "description": "Output each URL once even if it appears in several sitemaps or for several input sites.", "default": true }, "includeExtras": { "title": "Include images, videos, news and hreflang", "type": "boolean", "description": "Add image, video and news sitemap data and hreflang alternate-language URLs to each record.", "default": true }, "checkStatus": { "title": "Check HTTP status of every URL (extra charge)", "type": "boolean", "description": "Send a light HEAD request (GET if HEAD is refused) to every URL and add statusCode, finalUrl and redirectChain. Charged as a separate 'URL status checked' event. Slower: about 10 URLs per second per site.", "default": false }, "crawlIfNoSitemap": { "title": "Crawl internal links if no sitemap is found", "type": "boolean", "description": "If a website has no sitemap or RSS/Atom feed, follow links from the home page instead. Those records have source = 'crawled'.", "default": true }, "maxCrawlPages": { "title": "Maximum pages to crawl (fallback)", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Page limit for the fallback crawl of sites without a sitemap.", "default": 100 }, "sameDomainOnly": { "title": "Only URLs on the input domain", "type": "boolean", "description": "Drop sitemap URLs that point to other domains (subdomains and www are treated as the same site only when the host matches exactly apart from www).", "default": false }, "statusCheckConcurrency": { "title": "Parallel status checks", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many status checks run at the same time (1-10). Requests to one server are also spaced at least 0.1 s apart.", "default": 5 }, "timeoutSecs": { "title": "Request timeout (seconds)", "minimum": 3, "maximum": 120, "type": "integer", "description": "Timeout for each status check request.", "default": 20 } } }, "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 } } } } } } } } } }