{ "openapi": "3.0.1", "info": { "title": "llms.txt Generator: crawl a site, write llms.txt and full text", "description": "Crawls each site up to a page limit, respecting robots.txt, and writes an llms.txt file in the format of the llms.txt proposal, with an optional llms-full.txt holding the main text of every page as Markdown.", "version": "0.1", "x-build-id": "FQ0VDX9KnPL1S56i1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/examsens.ai~llms-txt-generator/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-examsens.ai-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/examsens.ai~llms-txt-generator/runs": { "post": { "operationId": "runs-sync-examsens.ai-llms-txt-generator", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/examsens.ai~llms-txt-generator/run-sync": { "post": { "operationId": "run-sync-examsens.ai-llms-txt-generator", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "startUrls" ], "properties": { "startUrls": { "title": "Sites", "type": "array", "description": "The home page (or the section start page) of each site. Each one gets its own llms.txt. The crawl stays on the start URL's host.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Maximum pages per site", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Most pages listed in each llms.txt. Each page included is one billable event.", "default": 50 }, "useSitemap": { "title": "Use the sitemap", "type": "boolean", "description": "Take pages from the site's XML sitemaps (named in robots.txt, or /sitemap.xml) before following links.", "default": true }, "includeFullText": { "title": "Also write llms-full.txt", "type": "boolean", "description": "Write a second file with the main text of every listed page converted to Markdown.", "default": false }, "includePatterns": { "title": "Only include URLs matching", "type": "array", "description": "Regular expressions. When set, only pages whose URL matches one of them are listed, such as /docs/.", "items": { "type": "string" } }, "excludePatterns": { "title": "Exclude URLs matching", "type": "array", "description": "Regular expressions. Pages whose URL matches one of them are left out, such as /tag/ or \\?page=.", "items": { "type": "string" } }, "optionalPatterns": { "title": "Put in the Optional section", "type": "array", "description": "Regular expressions. Pages whose URL matches go under the Optional heading, which the llms.txt proposal reserves for links an agent can skip, such as /blog/ or /changelog/.", "items": { "type": "string" } }, "siteName": { "title": "Site name", "type": "string", "description": "The H1 of the file. Leave empty to take it from the home page." }, "siteSummary": { "title": "Summary", "type": "string", "description": "The blockquote under the H1. Leave empty to use the home page's meta description." }, "timeoutSecs": { "title": "Timeout per request (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Give up on one page after this many seconds.", "default": 20 } } }, "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 } } } } } } } } } }