{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Extractor", "description": "Get every page URL a website lists in its sitemaps. Finds sitemaps via robots.txt and common paths, follows nested indexes, reads .gz, text, news and RSS sitemaps, and filters by date or pattern.", "version": "1.0", "x-build-id": "4xEwPMMRoT68neOFd" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/pipwort~sitemap-url-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-pipwort-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/pipwort~sitemap-url-extractor/runs": { "post": { "operationId": "runs-sync-pipwort-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/pipwort~sitemap-url-extractor/run-sync": { "post": { "operationId": "run-sync-pipwort-sitemap-url-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "A website home page (for example https://example.com) or a direct sitemap URL. For a home page, the Actor looks in robots.txt first, then at common sitemap locations.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "discoverFromRobots": { "title": "Read robots.txt for sitemap locations", "type": "boolean", "description": "Use the Sitemap: lines in robots.txt.", "default": true }, "tryCommonPaths": { "title": "Try common sitemap paths", "type": "boolean", "description": "If robots.txt lists nothing, try /sitemap.xml, /sitemap_index.xml, /wp-sitemap.xml and similar.", "default": true }, "maxUrlsPerSite": { "title": "Max URLs per site", "minimum": 0, "type": "integer", "description": "0 means no limit.", "default": 0 }, "maxUrlsTotal": { "title": "Max URLs in total", "minimum": 0, "type": "integer", "description": "0 means no limit. You can also cap spending with the run's maximum cost setting.", "default": 0 }, "lastmodAfter": { "title": "Only URLs modified after", "type": "string", "description": "Keep URLs whose lastmod is on or after this date (YYYY-MM-DD)." }, "lastmodBefore": { "title": "Only URLs modified before", "type": "string", "description": "Keep URLs whose lastmod is on or before this date (YYYY-MM-DD)." }, "keepUrlsWithoutLastmod": { "title": "Keep URLs with no lastmod when filtering by date", "type": "boolean", "description": "Many sitemaps omit lastmod. Turn off to drop those URLs when a date filter is set.", "default": true }, "includePatterns": { "title": "Include patterns (regex)", "type": "array", "description": "Keep only URLs matching at least one pattern, for example /blog/ or \\.html$", "items": { "type": "string" } }, "excludePatterns": { "title": "Exclude patterns (regex)", "type": "array", "description": "Drop URLs matching any of these patterns.", "items": { "type": "string" } }, "sameDomainOnly": { "title": "Same domain only", "type": "boolean", "description": "Drop URLs on other domains (subdomains are kept).", "default": true }, "includeImages": { "title": "Include image URLs", "type": "boolean", "description": "Add image:image locations listed for each page.", "default": false }, "includeAlternates": { "title": "Include hreflang alternates", "type": "boolean", "description": "Add xhtml:link language alternates for each page.", "default": false }, "maxDepth": { "title": "Max sitemap index depth", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many levels of nested sitemap indexes to follow.", "default": 5 }, "maxConcurrency": { "title": "Max parallel requests", "minimum": 1, "maximum": 20, "type": "integer", "description": "Keep this low to be polite to the website.", "default": 5 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 180, "type": "integer", "description": "Per request.", "default": 30 }, "maxRetries": { "title": "Retries per request", "minimum": 0, "maximum": 6, "type": "integer", "description": "Retries on timeouts, 429 and 5xx responses, with backoff.", "default": 3 }, "userAgent": { "title": "User-Agent", "type": "string", "description": "Optional custom User-Agent header." } } }, "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 } } } } } } } } } }