{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor: All Site URLs, Lastmod & News", "description": "Get every page URL a website lists in its XML sitemaps, with lastmod, changefreq, priority and image, news and video details. Finds sitemaps from robots.txt and the usual locations, follows sitemap indexes, reads gzip, text sitemaps and RSS/Atom feeds. Pay per URL.", "version": "1.0", "x-build-id": "YNv6dHnhzaECHU4O9" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/private_image_hg9~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-private_image_hg9-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/private_image_hg9~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-private_image_hg9-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/private_image_hg9~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-private_image_hg9-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 addresses", "type": "array", "description": "One per line. A domain like example.com (its sitemaps are found from robots.txt, then /sitemap.xml, /sitemap_index.xml, /sitemap-index.xml and /wp-sitemap.xml), or the address of one sitemap or feed to read directly, like https://example.com/sitemap_news.xml. Repeats are read once.", "items": { "type": "string" } }, "maxUrlsPerSite": { "title": "Max URLs per website", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Reading stops once this many URLs of one website were saved (after filters). Each saved URL is one charged row.", "default": 10000 }, "includeFilter": { "title": "Only URLs containing", "type": "array", "description": "Keep only URLs that contain at least one of these (case-insensitive), e.g. /blog/. Start an entry with re: to use a regular expression, e.g. re:/20(25|26)/. Leave empty to keep all.", "items": { "type": "string" } }, "excludeFilter": { "title": "Leave out URLs containing", "type": "array", "description": "Drop URLs that contain any of these (case-insensitive), e.g. /tag/ or ?page=. re: works here too. Dropped URLs are not charged.", "items": { "type": "string" } }, "lastmodAfter": { "title": "Changed on or after", "type": "string", "description": "Keep only URLs whose lastmod (or feed date) is on or after this date, like 2026-01-31, or a relative time like 30 days. URLs without a date are left out when this is set, and child sitemaps the index says last changed before it are skipped without being downloaded." }, "maxSitemapsPerSite": { "title": "Max sitemap files per website", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Most sitemap files (indexes included) downloaded for one website. Big news sites can have thousands.", "default": 200 }, "maxConcurrency": { "title": "Websites at once", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many websites are read in parallel. Each website still gets at most one request per second.", "default": 5 } } }, "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 } } } } } } } } } }