{ "openapi": "3.0.1", "info": { "title": "Website to Markdown Crawler for RAG – Hard Spend Cap", "description": "Crawl a website sitemap-first and get clean Markdown or plain text for every page, for RAG, LLM knowledge bases and content audits. You set a hard page and spend cap before the run, so a crawl never costs more than planned. Static HTML only.", "version": "1.0", "x-build-id": "B2XVS5OF9b2FWblDU" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/appetizing_horsefly~capped-content-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-appetizing_horsefly-capped-content-crawler", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/appetizing_horsefly~capped-content-crawler/runs": { "post": { "operationId": "runs-sync-appetizing_horsefly-capped-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/appetizing_horsefly~capped-content-crawler/run-sync": { "post": { "operationId": "run-sync-appetizing_horsefly-capped-content-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "type": "array", "description": "Sites or sections to crawl. Only pages under the same host and path prefix are crawled.", "default": [ "https://docs.apify.com/academy" ], "items": { "type": "string" } }, "maxPages": { "title": "Max pages (hard cap)", "minimum": 1, "maximum": 100000, "type": "integer", "description": "The run stops after this many pages are saved. You are never billed for more.", "default": 20 }, "maxSpendUsd": { "title": "Max spend (USD, hard cap)", "minimum": 0, "type": "number", "description": "Hard budget. Converted to a page cap at the per-page price; the lower of the two caps wins. 0 = use maxPages only.", "default": 0 }, "maxRunMinutes": { "title": "Max run time (minutes)", "minimum": 1, "maximum": 1440, "type": "integer", "description": "The crawl stops cleanly after this time and keeps everything saved so far.", "default": 30 }, "useSitemaps": { "title": "Sitemap first", "type": "boolean", "description": "Discover pages from robots.txt Sitemap: entries and /sitemap.xml before following links.", "default": true }, "followLinks": { "title": "Follow links", "type": "boolean", "description": "Also follow in-scope links found on pages (needed when a site has no sitemap).", "default": true }, "maxDepth": { "title": "Max link depth", "minimum": 0, "maximum": 50, "type": "integer", "description": "Link-following depth from start URLs.", "default": 5 }, "includeUrlPatterns": { "title": "Include URL regexes", "type": "array", "description": "Only save pages whose URL matches one of these regexes. Empty = all in scope.", "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URL regexes", "type": "array", "description": "Skip URLs matching any of these regexes.", "default": [ "\\.(pdf|zip|png|jpe?g|gif|svg|mp4)$", "/(tag|tags|author|page)/" ], "items": { "type": "string" } }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip URLs disallowed by robots.txt.", "default": true }, "outputFormat": { "title": "Content format", "enum": [ "markdown", "text" ], "type": "string", "description": "Format of the main content.", "default": "markdown" }, "concurrency": { "title": "Parallel requests", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many HTTP requests to run in parallel. Lower it for small or slow sites.", "default": 10 }, "requestTimeoutSecs": { "title": "Request timeout (s)", "minimum": 3, "maximum": 120, "type": "integer", "description": "Seconds to wait for each page request before skipping it.", "default": 20 }, "minWords": { "title": "Min words", "minimum": 0, "type": "integer", "description": "Pages with less main text than this are skipped (not charged).", "default": 30 } } }, "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 } } } } } } } } } }