AI Sitemap Content Extractor
Pricing
from $4.00 / 1,000 processed pages
Go to Apify Store
AI Sitemap Content Extractor
Transform website sitemaps into clean, AI-ready content with Markdown, semantic chunks, and optional AI summaries.
AI Sitemap Content Extractor
Pricing
from $4.00 / 1,000 processed pages
Transform website sitemaps into clean, AI-ready content with Markdown, semantic chunks, and optional AI summaries.
You can access the AI Sitemap Content Extractor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "1.1", "x-build-id": "8IeusLr5qPWG2CsE8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/enosgb~ai-sitemap-content-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-enosgb-ai-sitemap-content-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/enosgb~ai-sitemap-content-extractor/runs": { "post": { "operationId": "runs-sync-enosgb-ai-sitemap-content-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/enosgb~ai-sitemap-content-extractor/run-sync": { "post": { "operationId": "run-sync-enosgb-ai-sitemap-content-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": "Website URL or Sitemap URL", "type": "array", "description": "Enter the website's main URL (e.g., https://example.com) or a direct sitemap URL (e.g., https://example.com/sitemap.xml). The Actor will automatically find and parse the sitemap.", "default": [ { "url": "https://example.com" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Maximum Pages to Process", "minimum": 0, "maximum": 50000, "type": "integer", "description": "Maximum number of pages to fetch and process. Set to 0 for unlimited (not recommended for large sites).", "default": 1000 }, "maxDepth": { "title": "Maximum URL Depth", "minimum": 0, "maximum": 20, "type": "integer", "description": "Maximum URL path depth to process. Pages deeper than this will be skipped. Set to 0 for no limit.", "default": 0 }, "maxConcurrency": { "title": "Concurrency", "minimum": 1, "maximum": 100, "type": "integer", "description": "Number of pages to fetch in parallel. Higher = faster but uses more memory. Recommended: 10-50.", "default": 20 }, "excludePatterns": { "title": "Exclude URL Patterns", "type": "array", "description": "Additional URL patterns to exclude (one per line, supports regex). Built-in exclusions: login, privacy, terms, admin, feeds, media files.", "default": [], "items": { "type": "string" } }, "includePatterns": { "title": "Include Only URL Patterns", "type": "array", "description": "If set, only URLs matching these patterns will be processed (one per line, supports regex). Leave empty to process all non-excluded URLs.", "default": [], "items": { "type": "string" } }, "minContentQuality": { "title": "Minimum Content Quality Score", "minimum": 0, "maximum": 100, "type": "integer", "description": "Minimum quality score (0-100) for a page to be included. Pages below this threshold will be skipped. Set to 0 to include all pages.", "default": 30 }, "chunkSize": { "title": "Chunk Size (tokens)", "minimum": 0, "maximum": 8000, "type": "integer", "description": "Target number of tokens per chunk for LLM-ready content splitting. Set to 0 to disable chunking.", "default": 1000 }, "chunkOverlap": { "title": "Chunk Overlap (tokens)", "minimum": 0, "maximum": 500, "type": "integer", "description": "Number of overlapping tokens between consecutive chunks for context continuity.", "default": 100 }, "enableAiSummary": { "title": "Enable AI Summarization", "type": "boolean", "description": "Generate a 2-4 sentence summary for each page using Groq AI.", "default": true }, "enableAiClassification": { "title": "Enable AI Content Classification", "type": "boolean", "description": "Classify each page as blog_post, documentation, landing_page, etc. using Groq AI.", "default": true }, "useProxy": { "title": "Use Proxy", "type": "boolean", "description": "Enable proxy rotation for sites with anti-bot protection. Requires Apify proxy plan.", "default": 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 } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for AI Sitemap Content Extractor from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: