{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor with lastmod Filter", "description": "Lists the page URLs in a site's sitemaps, with lastmod. Follows sitemap indexes and .xml.gz files. Optional changed-since date filter. Reads robots.txt first and never requests the pages.", "version": "0.1", "x-build-id": "lb5porfDQpBDiRHG0" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/daddyd-prints~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-daddyd-prints-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/daddyd-prints~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-daddyd-prints-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/daddyd-prints~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-daddyd-prints-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "sites": { "title": "Websites", "type": "array", "description": "Domains or site addresses, one per line, for example docs.apify.com. https is assumed when no scheme is given. Any path in an address is ignored: the Actor reads the sitemaps of the whole site, up to the maximum URLs setting. Sitemaps are found from the site's robots.txt Sitemap lines, then from common sitemap paths, but only where robots.txt allows. Exception: an address ending in .xml, .xml.gz or .txt is read as that one sitemap file.", "items": { "type": "string" } }, "sitemapUrls": { "title": "Sitemap URLs (optional)", "type": "array", "description": "Direct links to sitemap files or sitemap indexes, one per line. robots.txt is still read and obeyed for each host before anything is fetched.", "items": { "type": "string" } }, "changedSince": { "title": "Only URLs changed since", "type": "string", "description": "Optional date (YYYY-MM-DD). Only URLs whose sitemap lastmod is on or after this date are saved. A lastmod without a time zone is read as UTC. Leave empty to save every URL." }, "includeUrlsWithoutLastmod": { "title": "Keep URLs that have no lastmod", "type": "boolean", "description": "Used only with the date filter. When on, URLs with no lastmod (or one that cannot be read) are saved too. When off, they are left out and counted in REPORT.", "default": false }, "maxUrls": { "title": "Maximum URLs to save", "minimum": 1, "maximum": 500000, "type": "integer", "description": "The run stops after saving this many URLs. Each saved URL is one billable result, so this caps the cost of a run.", "default": 1000 }, "maxSitemaps": { "title": "Maximum sitemap files to fetch", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Upper limit on sitemap files fetched in one run, counting index files and their children.", "default": 200 }, "maxSitemapDepth": { "title": "Maximum sitemap index depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many levels of sitemap indexes to follow. 0 reads only the top sitemap files, 1 also reads their children, and so on.", "default": 3 }, "tryCommonPaths": { "title": "Try common sitemap paths", "type": "boolean", "description": "When robots.txt lists no sitemap, or none of the sitemaps it lists can be read, try /sitemap.xml, /sitemap_index.xml, /sitemap-index.xml and /sitemap.xml.gz, one at a time, stopping at the first one that is a sitemap. Each path is tried only if robots.txt allows it. Not used for addresses given as sitemap files, or for a site that refused access.", "default": true }, "requestTimeoutSecs": { "title": "Request timeout", "minimum": 5, "maximum": 120, "type": "integer", "description": "Seconds to wait for each response. A file that takes longer than four times this value is abandoned.", "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 } } } } } } } } } }