{ "openapi": "3.0.1", "info": { "title": "Sitemap Analyzer — Recursive Parse, Health Check, AI Tags", "description": "Parse any sitemap.xml recursively, extract all URLs with metadata, check HTTP health status, and optionally cluster URLs by topic using Claude AI. Perfect for SEO audits and site migration.", "version": "0.0", "x-build-id": "DmTIISfClLmwH6K4J" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/elder_contrabasson~sitemap-analyzer/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-elder_contrabasson-sitemap-analyzer", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/elder_contrabasson~sitemap-analyzer/runs": { "post": { "operationId": "runs-sync-elder_contrabasson-sitemap-analyzer", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/elder_contrabasson~sitemap-analyzer/run-sync": { "post": { "operationId": "run-sync-elder_contrabasson-sitemap-analyzer", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "siteUrl" ], "properties": { "siteUrl": { "title": "Site URL, subfolder URL, or direct sitemap URL", "type": "string", "description": "Accepts three kinds of input: (a) a root domain - robots.txt and common paths are tried automatically; (b) a subfolder URL like example.com/blog - the subfolder sitemap is resolved, filtering robots.txt directives by the subpath; (c) a direct sitemap URL (.xml, .xml.gz, or sitemap-index).", "default": "https://www.apify.com" }, "sitemapUrl": { "title": "Explicit sitemap URL (optional, overrides auto-detection)", "type": "string", "description": "If set, this exact sitemap URL is used and all auto-detection is skipped. Most reliable when you already know the sitemap address. Accepts .xml, .xml.gz, and sitemap-index files." }, "maxUrls": { "title": "Max URLs to process", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Hard cap on URLs extracted (URL mode). Crawl stops when reached. Set to 0 for unlimited.", "default": 1000 }, "maxSitemaps": { "title": "Max child sitemaps to process", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Hard cap on the number of child sitemaps walked (both modes). Keeps runs predictable on huge sitemap-indexes. 0 = unlimited.", "default": 0 }, "maxDepth": { "title": "Max sitemap-index nesting depth", "minimum": 1, "maximum": 12, "type": "integer", "description": "How deep to follow nested sitemap-index files. Depth 0 = the entry sitemap itself.", "default": 6 }, "requestDelayMs": { "title": "Delay between sitemap requests (ms)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Pause between consecutive sitemap fetches. Higher values reduce anti-bot soft-bans on strict sites (800-1500ms recommended for sites with anti-bot protection). 0 = no delay (fastest).", "default": 300 }, "enableHealthCheck": { "title": "Check HTTP status of each URL", "type": "boolean", "description": "Send HEAD request to each URL to verify it returns 200. Adds ~1 sec per URL.", "default": false }, "healthCheckConcurrency": { "title": "Concurrent health check requests", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many URLs to check in parallel. Higher = faster but more aggressive on target site.", "default": 10 }, "enableAiClustering": { "title": "Cluster URLs by topic using AI (optional)", "type": "boolean", "description": "Group URLs into topic clusters using Claude (e.g. product pages, blog posts, support docs). Requires Anthropic API key.", "default": false }, "anthropicApiKey": { "title": "Anthropic API key (only if AI clustering enabled)", "type": "string", "description": "Your Anthropic API key (sk-ant-...). BYOK - we don't store it. Get one at console.anthropic.com" }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Check robots.txt before scraping and skip URLs that are disallowed.", "default": true }, "sitemapTreeMode": { "title": "Sitemap tree mode (analyze child sitemaps instead of URLs)", "type": "boolean", "description": "Instead of extracting URLs, list every child sitemap inside the index: its URL, how many URLs it contains, depth, and parent. Useful for competitor scale analysis.", "default": false }, "sampleUrlsPerSitemap": { "title": "Sample URLs per child sitemap (tree mode only)", "minimum": 0, "maximum": 100, "type": "integer", "description": "In tree mode, also pull this many sample URLs from each child sitemap (0 = none, just counts).", "default": 0 }, "useProxy": { "title": "Use Apify Proxy (datacenter)", "type": "boolean", "description": "Route requests through Apify datacenter proxy + rotate User-Agent. Helps against rate-limiting and IP bans. Does NOT bypass Cloudflare/DataDome JS-challenges.", "default": false }, "proxyType": { "title": "Proxy type (only if proxy enabled)", "enum": [ "datacenter", "residential" ], "type": "string", "description": "Datacenter — fast and cheap, good vs rate-limits. Residential — slower and more expensive, but bypasses many anti-bot systems. Residential requires the RESIDENTIAL proxy group to be available in your Apify account.", "default": "datacenter" } } }, "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 } } }, "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 } } } } } } } } } }