{ "openapi": "3.0.1", "info": { "title": "Sitemap Scraper", "description": "Sitemap Scraper extracts URLs, page metadata, update dates, images, and structured sitemap data from XML sitemaps. Ideal for SEO audits, website analysis, content discovery, indexing validation, competitor research, and large-scale web data collection.", "version": "2.0", "x-build-id": "VTlmxgWZ924DxObJV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapevanta~sitemap-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapevanta-sitemap-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapevanta~sitemap-scraper/runs": { "post": { "operationId": "runs-sync-scrapevanta-sitemap-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapevanta~sitemap-scraper/run-sync": { "post": { "operationId": "run-sync-scrapevanta-sitemap-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Start URLs", "minItems": 1, "type": "array", "description": "Where the crawl begins. Usually one homepage. The scheme is added automatically if you omit it, and the first URL's domain defines the crawl scope.", "items": { "type": "string" } }, "maxPages": { "title": "Max pages to crawl", "minimum": 1, "maximum": 20000, "type": "integer", "description": "Hard cap on pages visited. The crawl stops here even if more URLs are queued.", "default": 200 }, "maxCrawlDepth": { "title": "Max crawl depth", "minimum": 0, "maximum": 15, "type": "integer", "description": "How many link hops from a start URL to follow. 0 crawls only the start URLs themselves.", "default": 3 }, "includeSubdomains": { "title": "Include subdomains", "type": "boolean", "description": "Follow links to subdomains of the start domain. Off by default, so blog.example.com is skipped when crawling example.com.", "default": false }, "includeUrlPatterns": { "title": "Only crawl URLs matching", "type": "array", "description": "Regular expressions. When set, only matching URLs are queued.", "items": { "type": "string" }, "default": [] }, "excludeUrlPatterns": { "title": "Skip URLs matching", "type": "array", "description": "Regular expressions for URLs to skip, such as /tag/ or a paging query parameter.", "items": { "type": "string" }, "default": [] }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Read the site's robots.txt and skip disallowed paths. Disallowed pages are also marked non-indexable.", "default": true }, "generateSitemapFile": { "title": "Generate sitemap.xml", "type": "boolean", "description": "Write a valid sitemap document to the run's key-value store as 'generated-sitemap.xml'.", "default": true }, "sitemapIndexableOnly": { "title": "Sitemap includes indexable pages only", "type": "boolean", "description": "Exclude redirects, error pages, noindex pages and non-canonical duplicates from the generated sitemap. Recommended.", "default": true }, "concurrentRequests": { "title": "Concurrent requests", "minimum": 1, "maximum": 30, "type": "integer", "description": "Pages fetched at once.", "default": 5 }, "requestDelayMs": { "title": "Delay after each request", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Pause after each page, to stay polite on small servers.", "default": 0 }, "maxAttempts": { "title": "Max attempts per page", "minimum": 1, "maximum": 5, "type": "integer", "description": "Tries per page. Only transient failures are retried.", "default": 2 }, "requestTimeoutSec": { "title": "Request timeout", "minimum": 5, "maximum": 120, "type": "integer", "description": "Per-request timeout in seconds.", "default": 30 }, "emitRunSummary": { "title": "Append run summary row", "type": "boolean", "description": "Add one final record with the site audit: indexability issues, status codes, depth spread and duplicate titles.", "default": true }, "proxyConfig": { "title": "Proxy configuration", "type": "object", "description": "Optional Apify Proxy settings, useful for sites that rate limit by IP.", "default": { "useApifyProxy": 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 } } } } } } } } } }