{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor – All URLs & Lastmod Filter", "description": "Get every URL from a website's sitemap.xml, including indexes, gzip and robots.txt. Filter by lastmod and pay only for the URLs you keep: $1 per 1,000 URLs.", "version": "0.1", "x-build-id": "HK7PVDJxpMUbLN3m8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/martinvarelaa~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-martinvarelaa-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/martinvarelaa~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-martinvarelaa-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/martinvarelaa~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-martinvarelaa-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 URLs", "type": "array", "description": "Domains (https://example.com), specific sitemap URLs (https://example.com/sitemap.xml) or robots.txt URLs. For domains the Actor discovers sitemaps automatically.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxUrls": { "title": "Maximum URLs", "minimum": 1, "maximum": 10000000, "type": "integer", "description": "Stop after this many unique URLs across all inputs. You pay per URL returned.", "default": 1000 }, "discoverViaRobotsTxt": { "title": "Discover sitemaps from robots.txt", "type": "boolean", "description": "Read Sitemap: lines from robots.txt before trying common paths.", "default": true }, "tryCommonPaths": { "title": "Try common sitemap paths", "type": "boolean", "description": "Also check /sitemap.xml, /sitemap_index.xml, /wp-sitemap.xml and similar when robots.txt has no Sitemap line.", "default": true }, "includeUrlPatterns": { "title": "Include only URLs matching (regex)", "type": "array", "description": "Keep only URLs matching at least one pattern, e.g. \"/blog/\".", "default": [], "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URLs matching (regex)", "type": "array", "description": "Drop URLs matching any of these patterns.", "default": [], "items": { "type": "string" } }, "includeImages": { "title": "Include image URLs (image sitemap extension)", "type": "boolean", "description": "Add an images array when the sitemap lists images for a URL.", "default": false }, "includeAlternates": { "title": "Include hreflang alternates", "type": "boolean", "description": "Add an alternates array with hreflang links when the sitemap has them.", "default": false }, "lastmodSince": { "title": "Only URLs modified since (YYYY-MM-DD)", "type": "string", "description": "URLs older than this date are not returned and are not charged. URLs without lastmod are kept unless 'Drop URLs without lastmod' is checked." }, "dropUrlsWithoutLastmod": { "title": "Drop URLs without lastmod when filtering by date", "type": "boolean", "description": "Use together with the date filter. Undated URLs are omitted and not charged.", "default": false }, "maxSitemapDepth": { "title": "Maximum sitemap index depth", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many levels of sitemap index to follow. 1 reads the root sitemap only.", "default": 5 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Not needed for most sites. Residential proxies are not used.", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }