{ "openapi": "3.0.1", "info": { "title": "llms.txt Generator (Website to llms.txt & llms-full.txt)", "description": "Turn any website or docs site into an llms.txt (sectioned links with one-line descriptions) and llms-full.txt (every page as clean Markdown) for AI assistants, RAG and AI search. Plain HTTP, sitemap-aware, robots.txt-friendly.", "version": "0.0", "x-build-id": "XNVzCLuBjpdoyr8EP" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/webdatatools~llms-txt-generator/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-webdatatools-llms-txt-generator", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/webdatatools~llms-txt-generator/runs": { "post": { "operationId": "runs-sync-webdatatools-llms-txt-generator", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/webdatatools~llms-txt-generator/run-sync": { "post": { "operationId": "run-sync-webdatatools-llms-txt-generator", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "Start URLs", "type": "array", "description": "Enter the website(s) to turn into llms.txt, e.g. https://docs.apify.com. Each different domain gets its own llms.txt and llms-full.txt.", "default": [ { "url": "https://crawlee.dev/js/docs/quick-start" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Max pages per website", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Enter the maximum number of pages to read per website, e.g. 100. This is the billed unit (one dataset row per page).", "default": 100 }, "maxDepth": { "title": "Max link depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "Enter how many links deep to follow from a start URL, e.g. 3. Set 0 to crawl only the start URL(s).", "default": 3 }, "includePathPrefixes": { "title": "Include path prefixes", "type": "array", "description": "Optional. Only read pages whose path starts with one of these prefixes, e.g. /docs. Leave empty to stay inside the folder of each start URL (https://example.com/docs/intro → /docs), or the whole site for a home-page start URL.", "default": [], "items": { "type": "string" } }, "excludePathPatterns": { "title": "Exclude URL patterns", "type": "array", "description": "Optional. Regular expressions tested against the full URL; a match is skipped, e.g. \\.(png|jpe?g)$ to skip images. Defaults cover binary files and login/signup pages.", "default": [ "\\.(png|jpe?g|gif|svg|webp|pdf|zip|mp4|css|js)$", "/login", "/signup", "\\?replytocom=" ], "items": { "type": "string" } }, "useSitemap": { "title": "Seed from sitemap.xml", "type": "boolean", "description": "Turn this on to also read /sitemap.xml on each start URL's domain and add its URLs (filtered by the settings above) to the crawl queue, up to Max pages.", "default": true }, "includeMarkdown": { "title": "Markdown in the dataset", "type": "boolean", "description": "Turn this off to keep only title, description and token count per page in the dataset (llms-full.txt still has every page's Markdown).", "default": true }, "removeSelectors": { "title": "Extra CSS selectors to remove", "type": "array", "description": "Optional. Extra CSS selectors to strip before extracting content, e.g. .cookie-banner or #newsletter-signup, on top of the built-in nav/header/footer/aside removal.", "default": [], "items": { "type": "string" } }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Enter the maximum number of pages fetched in parallel, e.g. 10. Lower it if the target site rate-limits you.", "default": 10 }, "respectRobots": { "title": "Respect robots.txt", "type": "boolean", "description": "Turn this on to skip URLs disallowed by the site's robots.txt file (recommended and on by default).", "default": true }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. Select a proxy configuration, e.g. Apify Proxy with the datacenter group, if the target site blocks requests from shared IPs.", "default": { "useApifyProxy": false } }, "inputDatasetId": { "title": "Input dataset ID (optional)", "type": "string", "description": "Take the URLs from another Actor run's dataset, e.g. \"aBcD1234\". Combined with the list above." }, "inputField": { "title": "Field to read from that dataset", "type": "string", "description": "Column holding the value, e.g. \"url\" (the default) or \"website\". Array columns are flattened." } } }, "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 } } } } } } } } } }