{ "openapi": "3.0.1", "info": { "title": "Sitemap Extractor: All URLs from XML Sitemaps", "description": "Get every URL from a site's XML sitemaps and indexes, with lastmod, changefreq and priority. robots.txt discovery, .gz, filters. $0.40 per 1,000 URLs.", "version": "0.1", "x-build-id": "vMZTkPkIxa4RooZMy" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ataism~sitemap-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ataism-sitemap-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/ataism~sitemap-extractor/runs": { "post": { "operationId": "runs-sync-ataism-sitemap-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/ataism~sitemap-extractor/run-sync": { "post": { "operationId": "run-sync-ataism-sitemap-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": "Site or sitemap URLs", "type": "array", "description": "One per line, up to 100. A site URL (https://crawlee.dev/) is looked up in robots.txt (Sitemap: lines), then at /sitemap.xml and /sitemap_index.xml. A sitemap URL (path ending in .xml, .xml.gz or .txt, or containing \"sitemap\") is read directly. Social-media and Google hosts are refused.", "items": { "type": "string" } }, "maxUrls": { "title": "Max URLs", "minimum": 1, "maximum": 200000, "type": "integer", "description": "Upper limit of URL rows for the whole run (each row is charged). Default 50,000, hard cap 200,000 (100,000 when the run has less than 512 MB of memory). The run stops cleanly when it is reached.", "default": 50000 }, "includePattern": { "title": "Only URLs containing", "type": "string", "description": "Optional. Keep only URLs that contain this text, case-insensitive. Use * for \"anything\": /blog/ keeps blog URLs, /products/*/reviews keeps product review pages. Plain text and * only (no regular expressions). Filtered URLs are not charged." }, "excludePattern": { "title": "Skip URLs containing", "type": "string", "description": "Optional. Drop URLs that contain this text (same rules as above), for example /tag/ or ?page=. Wins over the include pattern." }, "lastmodAfter": { "title": "Modified on or after", "type": "string", "description": "Optional date (YYYY-MM-DD, or a full date-time with zone). Keeps only URLs whose is on or after it; URLs without a lastmod are dropped while this is set. Child sitemaps whose index lastmod is older are not downloaded." }, "maxDepth": { "title": "Max index depth", "minimum": 0, "maximum": 5, "type": "integer", "description": "How many levels of sitemap indexes are followed. 0 reads only the sitemaps you give or that robots.txt lists; the default 3 covers almost every site; maximum 5. Deeper child sitemaps are reported in one free depth-cap row.", "default": 3 }, "dedupe": { "title": "Remove duplicates", "type": "boolean", "description": "On (default): a URL listed in several sitemaps is output and charged once (the first sitemap wins). Off: one row per listing.", "default": true }, "mode": { "title": "Mode", "type": "string", "description": "Internal: \"selfTest\" runs the maintainer health check and saves no items.", "default": "run" } } }, "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 } } } } } } } } } }