{ "openapi": "3.0.1", "info": { "title": "Website Crawl Preflight Auditor", "description": "Check robots.txt, sitemaps, static extraction quality, crawl risk, and estimated Apify costs before running a crawler or RAG ingestion job.", "version": "0.1", "x-build-id": "nDtUfkJW20YTjFBde" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sebastian-actors~website-crawl-preflight-auditor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sebastian-actors-website-crawl-preflight-auditor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sebastian-actors~website-crawl-preflight-auditor/runs": { "post": { "operationId": "runs-sync-sebastian-actors-website-crawl-preflight-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sebastian-actors~website-crawl-preflight-auditor/run-sync": { "post": { "operationId": "run-sync-sebastian-actors-website-crawl-preflight-auditor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrl": { "title": "Start URL", "type": "string", "description": "Website URL to audit, such as https://example.com. Used to discover robots.txt and common sitemap locations." }, "sitemapUrl": { "title": "Sitemap URL", "type": "string", "description": "Optional XML sitemap or sitemap index URL to inspect." }, "urls": { "title": "Sample URLs", "maxItems": 500, "type": "array", "description": "Optional list of public URLs to sample directly.", "items": { "type": "string" }, "default": [] }, "maxOrigins": { "title": "Maximum origins", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum number of distinct website origins audited in one run. Limits apply independently to each origin.", "default": 10 }, "samplePages": { "title": "Sample pages", "minimum": 1, "maximum": 250, "type": "integer", "description": "Maximum number of pages to sample for static extraction diagnostics.", "default": 25 }, "maxSitemapUrls": { "title": "Max sitemap URLs", "minimum": 1, "maximum": 500000, "type": "integer", "description": "Maximum number of sitemap URLs to inspect/count before stopping.", "default": 100000 }, "maxSitemapDepth": { "title": "Max sitemap depth", "minimum": 0, "maximum": 3, "type": "integer", "description": "Maximum depth for sitemap index recursion.", "default": 2 }, "sameDomainOnly": { "title": "Same domain only", "type": "boolean", "description": "Only include sitemap records and redirects on the exact audited origin (scheme, hostname, and port). Explicit input origins are still audited separately.", "default": true }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Use robots.txt rules when evaluating sample URLs and recommendations.", "default": true }, "checkSitemaps": { "title": "Check sitemaps", "type": "boolean", "description": "Discover and parse sitemaps when possible.", "default": true }, "checkSamplePages": { "title": "Check sample pages", "type": "boolean", "description": "Fetch sample pages to estimate static crawl quality and extraction difficulty.", "default": true }, "estimateApifyCosts": { "title": "Estimate Apify costs", "type": "boolean", "description": "Estimate approximate static-fetch compute cost range based on discovered pages and sample diagnostics.", "default": true }, "includeRecommendedSettings": { "title": "Include recommended settings", "type": "boolean", "description": "Output recommended settings for downstream crawl, SEO audit, or RAG Actors.", "default": true }, "includeDisallowedPaths": { "title": "Include disallowed paths", "type": "boolean", "description": "Include summarized robots.txt disallow path patterns in the output.", "default": true }, "includeSampleRows": { "title": "Include sample rows", "type": "boolean", "description": "Also write one dataset row per sampled page.", "default": true }, "userAgent": { "title": "User agent", "type": "string", "description": "User agent used for robots.txt checks and HTTP requests.", "default": "WebsiteCrawlPreflightBot/1.0 (+https://apify.com)" }, "urlAllowlistPatterns": { "title": "URL allowlist patterns", "type": "array", "description": "Optional regex patterns. If provided, only matching URLs are included in sampling and recommendations.", "items": { "type": "string" }, "default": [] }, "urlBlocklistPatterns": { "title": "URL blocklist patterns", "type": "array", "description": "Optional regex patterns. Matching URLs are excluded from sampling and recommendations.", "items": { "type": "string" }, "default": [] }, "requestTimeoutSecs": { "title": "Request timeout seconds", "minimum": 5, "maximum": 60, "type": "integer", "description": "Timeout for robots, sitemap, and sample page requests.", "default": 20 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum number of sample page requests in parallel.", "default": 5 }, "costModel": { "title": "Cost model", "type": "object", "description": "Optional static-fetch cost model overrides." } } }, "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 } } } } } } } } } }