{ "openapi": "3.0.1", "info": { "title": "Sitemap URL Scraper", "description": "Sitemap Scraper SD - Sitemap Scraper is an SEO crawling tool that extracts every URL from a website's sitemaps (robots.txt, sitemap.xml, indexes, gzip, RSS) with lastmod, changefreq, priority, hreflang and news data.", "version": "1.0", "x-build-id": "SoFyHqbI9SLmZcHWu" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/neuro-scraper~sitemap-url-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-neuro-scraper-sitemap-url-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/neuro-scraper~sitemap-url-scraper/runs": { "post": { "operationId": "runs-sync-neuro-scraper-sitemap-url-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/neuro-scraper~sitemap-url-scraper/run-sync": { "post": { "operationId": "run-sync-neuro-scraper-sitemap-url-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Websites or sitemap URLs", "type": "array", "description": "A website (https://crawlee.dev - its sitemaps are found through robots.txt or /sitemap.xml) or a sitemap / sitemap index URL (https://crawlee.dev/sitemap.xml, .xml.gz and .txt work too).", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxItems": { "title": "Max URLs", "minimum": 1, "maximum": 10000000, "type": "integer", "description": "Maximum number of URLs saved (one row per URL).", "default": 1000 }, "maxSitemaps": { "title": "Max sitemap files", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum number of sitemap files (indexes included) read per run.", "default": 200 }, "includeUrlGlobs": { "title": "Include URL globs", "type": "array", "description": "Only save URLs matching one of these globs, e.g. https://crawlee.dev/python/** (** = anything, * = anything except '/').", "items": { "type": "string" } }, "excludeUrlGlobs": { "title": "Exclude URL globs", "type": "array", "description": "Never save URLs matching these globs, e.g. **/tag/**", "items": { "type": "string" } }, "lastmodAfter": { "title": "Only URLs modified after (date)", "type": "string", "description": "YYYY-MM-DD. Keeps only URLs whose sitemap is on or after this date (URLs without lastmod are left out when this is set)." }, "checkUrlStatus": { "title": "Check each URL's HTTP status", "type": "boolean", "description": "Request every saved URL (HEAD, or GET without downloading the body) and add statusCode and finalUrl. One request per URL, spaced by the delay below - slow for large sites.", "default": false }, "tryWellKnownPaths": { "title": "Try well-known sitemap paths", "type": "boolean", "description": "When robots.txt lists no sitemap, try /sitemap.xml, /sitemap_index.xml, /sitemap-index.xml, /wp-sitemap.xml, /sitemap.xml.gz and /sitemap.txt.", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Do not read sitemap files or check URLs that the site's robots.txt disallows.", "default": true }, "requestDelayMs": { "title": "Delay between requests to one site (ms)", "minimum": 0, "maximum": 60000, "type": "integer", "description": "Pause between two requests to the same host.", "default": 1000 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify Proxy (datacenter by default). Choose RESIDENTIAL for sites that block datacenter IPs.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }