{ "openapi": "3.0.1", "info": { "title": "Sitemap Content Extractor — Website to Clean Markdown", "description": "Turn any website's sitemap into clean, LLM-ready Markdown. Auto-discovers sitemaps via robots.txt, extracts article text, tables, headings, links and images while stripping navigation, ads and cookie banners. Filter pages by lastmod date.", "version": "0.5", "x-build-id": "jNEtsvcEWVI03ej5w" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/celebrated-quadraphonic~sitemap-content-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-celebrated-quadraphonic-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/celebrated-quadraphonic~sitemap-content-extractor/runs": { "post": { "operationId": "runs-sync-celebrated-quadraphonic-sitemap-content-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/celebrated-quadraphonic~sitemap-content-extractor/run-sync": { "post": { "operationId": "run-sync-celebrated-quadraphonic-sitemap-content-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "includeMetadata": { "title": "Include metadata", "type": "boolean", "description": "Include title, meta description, language, headings, outbound links and image counts.", "default": true }, "limitToStartDomain": { "title": "Limit to start domain", "type": "boolean", "description": "Only fetch URLs on the same domain as the start URL.", "default": true }, "maxContentChars": { "title": "Max content chars", "minimum": 0, "type": "integer", "description": "Truncate extracted content per page to this many characters. 0 = no truncation.", "default": 0 }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Maximum number of pages to fetch and extract.", "default": 100 }, "maxSitemapDepth": { "title": "Max sitemap depth", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many nested sitemap-index levels to expand.", "default": 3 }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "text", "html" ], "type": "string", "description": "Content format: clean Markdown (best for LLMs), plain text, or cleaned HTML.", "default": "markdown" }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Sitemaps and pages are fetched over plain HTTP; proxies are not needed for typical runs.", "default": { "useApifyProxy": false } }, "requestConcurrency": { "title": "Request concurrency", "minimum": 1, "maximum": 30, "type": "integer", "description": "How many pages to fetch in parallel.", "default": 10 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Honor robots.txt Disallow rules when fetching page content.", "default": true }, "startUrls": { "title": "Start URLs / domains", "type": "array", "description": "Domains or sitemap URLs, one per line. Examples: apify.com, https://example.com/sitemap.xml", "items": { "type": "string" } }, "urlPatternInclude": { "title": "URL include patterns", "type": "array", "description": "Only keep URLs matching at least one of these regular expressions, one per line. Example: /docs/", "items": { "type": "string" } }, "urlPatternExclude": { "title": "URL exclude patterns", "type": "array", "description": "Skip URLs matching any of these regular expressions, one per line. Example: /blog/draft", "items": { "type": "string" } }, "minLastmod": { "title": "Min lastmod date", "type": "string", "description": "Only keep URLs whose sitemap lastmod is on/after this date (YYYY-MM-DD). URLs without lastmod are kept.", "default": "" }, "maxLastmod": { "title": "Max lastmod date", "type": "string", "description": "Only keep URLs whose sitemap lastmod is on/before this date (YYYY-MM-DD). URLs without lastmod are kept.", "default": "" } } }, "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 } } } } } } } } } }