{ "openapi": "3.0.1", "info": { "title": "Website Content to Markdown & llms.txt Crawler - AI & RAG Ready", "description": "High-performance, lightweight asynchronous crawler converting web pages into clean Markdown, computing token estimates, and generating standard /llms.txt manifests for AI and RAG ingestion.", "version": "1.0", "x-build-id": "GL16NJmqDxctJNo6v" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/abi4~website-content-llmstxt-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-abi4-website-content-llmstxt-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/abi4~website-content-llmstxt-crawler/runs": { "post": { "operationId": "runs-sync-abi4-website-content-llmstxt-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/abi4~website-content-llmstxt-crawler/run-sync": { "post": { "operationId": "run-sync-abi4-website-content-llmstxt-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "List of URLs from which the crawl begins. Enter one or more URLs.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Max Pages", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of pages to crawl before completing the run.", "default": 20 }, "maxDepth": { "title": "Max Crawl Depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "Maximum distance in clicks from start URLs (0 = start URLs only, 1 = 1 click away, etc.).", "default": 3 }, "includeLlmsTxtGeneration": { "title": "Generate /llms.txt Manifest", "type": "boolean", "description": "Automatically synthesize standard /llms.txt and /llms-full.txt files and save them in the Key-Value Store.", "default": true }, "removeElementsCssSelector": { "title": "Remove Elements (CSS Selector)", "type": "string", "description": "CSS selectors of elements to strip from the HTML DOM before converting to Markdown.", "default": "nav, footer, script, style, noscript, .cookie-banner, .advertisement, [role=navigation], [role=banner], [role=contentinfo]" }, "enableMcpMode": { "title": "Enable MCP Server Mode", "type": "boolean", "description": "When enabled, executes the Actor as a Model Context Protocol (MCP) server for direct integration with Cursor, Claude Desktop, and Windsurf.", "default": false }, "mcpTransport": { "title": "MCP Transport Protocol", "enum": [ "stdio", "sse" ], "type": "string", "description": "Transport protocol for MCP tool execution. Use stdio for local CLI/IDE execution and sse for Apify Standby web integration.", "default": "stdio" }, "renderJs": { "title": "Render Dynamic JavaScript", "type": "boolean", "description": "Enable Playwright headless browser rendering for client-rendered SPAs (React, Vue, Angular). Note: If enabled, ensure your Actor run memory is set to at least 1,024 MB.", "default": false }, "waitForSelector": { "title": "Wait for CSS Selector", "type": "string", "description": "Optional CSS selector to wait for when renderJs is enabled before extracting content (e.g. 'article, .docs-content').", "default": "" }, "contentSelector": { "title": "Target Content CSS Selector", "type": "string", "description": "Scope Markdown extraction exclusively to matching element(s) (e.g. 'main, article, .markdown-body') before pruning boilerplate.", "default": "" }, "customExtractionSelectors": { "title": "Custom Field Selectors", "type": "object", "description": "Optional JSON map of field names to CSS selectors to extract specific elements into structured output (e.g. {\"author\": \".author-name\", \"published\": \"time\"}).", "default": {} }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings for the crawler. Select Apify Proxy to bypass geo-restrictions and rate limits.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }