{ "openapi": "3.0.1", "info": { "title": "Website to Markdown — LLM-Ready Content Crawler for RAG", "description": "Crawl any website and get clean, LLM-ready Markdown for every page: main content only (no menus, footers or cookie banners), absolute links, tables, title, description, author and publish date. For RAG, vector databases, AI agents and training data. Flat $1 per 1,000 pages.", "version": "0.1", "x-build-id": "vkdRCUSkA8jpLff3r" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/actor-forge~website-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-actor-forge-website-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/actor-forge~website-to-markdown/runs": { "post": { "operationId": "runs-sync-actor-forge-website-to-markdown", "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/actor-forge~website-to-markdown/run-sync": { "post": { "operationId": "run-sync-actor-forge-website-to-markdown", "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": "Where to start crawling. The crawl stays on the same site and under each URL's path: https://docs.example.com/guides crawls only the guides; a bare domain crawls the whole site. Use include globs to widen or narrow it.", "items": { "type": "string" } }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after converting this many pages (across all start URLs). To convert only the start URLs themselves, set Max link depth to 0.", "default": 100 }, "maxDepth": { "title": "Max link depth", "minimum": 0, "maximum": 100, "type": "integer", "description": "How many links away from a start URL to follow. 0 = only the start URLs themselves (no crawling, no sitemaps).", "default": 10 }, "includeSubdomains": { "title": "Include subdomains", "type": "boolean", "description": "Also crawl subdomains of the start site (e.g. blog.example.com when starting at example.com). Pages on another host are only reached when you also set include globs that cover them, e.g. https://*.example.com/**.", "default": false }, "includeGlobs": { "title": "Include URL globs", "type": "array", "description": "Only crawl URLs matching one of these, e.g. https://example.com/blog/** (** = anything, * = anything except /). Replaces the default 'stay under the start path' rule.", "default": [], "items": { "type": "string" } }, "excludeGlobs": { "title": "Exclude URL globs", "type": "array", "description": "Never crawl URLs matching these, e.g. **/tag/** or **/login*.", "default": [], "items": { "type": "string" } }, "useSitemap": { "title": "Use sitemaps", "type": "boolean", "description": "Also discover pages from the site's sitemap.xml (and sitemaps listed in robots.txt). Finds pages that links miss.", "default": true }, "onlyMainContent": { "title": "Main content only", "type": "boolean", "description": "Keep just the article or main content (Firefox Reader View's algorithm), dropping menus, sidebars, footers and banners. Turn off to keep the whole page body (navigation is still removed).", "default": true }, "removeSelectors": { "title": "Remove CSS selectors", "type": "array", "description": "Extra elements to strip before conversion, e.g. .newsletter-signup or #comments.", "default": [], "items": { "type": "string" } }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Which content fields to return for each page. Same price whatever you pick.", "items": { "type": "string", "enum": [ "markdown", "text", "html" ], "enumTitles": [ "Markdown", "Plain text", "Cleaned HTML" ] }, "default": [ "markdown" ] }, "includeLinks": { "title": "Include page links", "type": "boolean", "description": "Add the list of absolute links found on each page.", "default": false }, "minWords": { "title": "Minimum words", "minimum": 0, "type": "integer", "description": "Skip thin pages (tag lists, empty archives) with fewer words than this. Skipped pages are not charged.", "default": 0 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip pages that the site's robots.txt disallows for crawlers.", "default": 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 }, "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 } } } } } } } } } }