{ "openapi": "3.0.1", "info": { "title": "HTML to Markdown Converter — Clean RAG Output", "description": "HTML to Markdown converter and cleaner for LLM/RAG pipelines. Convert static or JavaScript pages, preserve headings, tables, links and images, remove noisy selectors, output clean text, and create overlap-aware chunks with stable IDs, SHA-256 fingerprints, word counts and token estimates.", "version": "0.1", "x-build-id": "Cr8PY2T3U7jLgUO3Z" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/zenomastro~html-to-markdown-cleaner/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-zenomastro-html-to-markdown-cleaner", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/zenomastro~html-to-markdown-cleaner/runs": { "post": { "operationId": "runs-sync-zenomastro-html-to-markdown-cleaner", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/zenomastro~html-to-markdown-cleaner/run-sync": { "post": { "operationId": "run-sync-zenomastro-html-to-markdown-cleaner", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "Page URLs", "minItems": 0, "maxItems": 500, "type": "array", "description": "Public HTTP/HTTPS page URLs to fetch and convert.", "default": [ "https://example.com" ], "items": { "type": "string" } }, "contentSelector": { "title": "Optional CSS content selector", "type": "string", "description": "When provided, only the first matching element is converted.", "default": "" }, "maxMarkdownChars": { "title": "Maximum Markdown characters per page", "minimum": 1000, "maximum": 5000000, "type": "integer", "description": "Maximum Markdown characters retained for each converted page.", "default": 500000 }, "includeCleanHtml": { "title": "Include cleaned HTML", "type": "boolean", "description": "Include cleaned HTML alongside the Markdown result.", "default": false }, "requestTimeoutSecs": { "title": "Request timeout", "minimum": 5, "maximum": 120, "type": "integer", "description": "Maximum seconds allowed for each network request.", "default": 20 }, "userAgent": { "title": "User agent", "type": "string", "description": "HTTP User-Agent header sent to target websites.", "default": "Mozilla/5.0 (compatible; ApifyHtmlMarkdown/1.0)" }, "htmlDocuments": { "title": "Raw HTML documents", "maxItems": 200, "type": "array", "description": "Optional objects with html, baseUrl and id. Convert raw HTML without fetching a URL.", "items": { "type": "object", "properties": { "html": { "type": "string", "title": "HTML", "description": "Raw HTML source to convert.", "editor": "textarea" }, "baseUrl": { "type": "string", "title": "Base URL", "description": "Optional public base URL used to resolve relative links and images.", "editor": "textfield" }, "id": { "type": "string", "title": "Document ID", "description": "Optional caller-supplied identifier copied to the output.", "editor": "textfield" } }, "required": [ "html" ] }, "default": [] }, "removeSelectors": { "title": "Extra selectors to remove", "maxItems": 50, "type": "array", "description": "Optional CSS selectors for ads, menus, widgets or other page noise.", "default": [], "items": { "type": "string" } }, "includeLinks": { "title": "Extract links", "type": "boolean", "description": "Return deduplicated absolute links with anchor text and rel metadata.", "default": true }, "includeImages": { "title": "Extract images", "type": "boolean", "description": "Return image URLs, alt text, title and dimensions.", "default": true }, "includePlainText": { "title": "Include plain text", "type": "boolean", "description": "Add a cleaned plain-text representation alongside Markdown.", "default": true }, "includeChunks": { "title": "Create RAG chunks", "type": "boolean", "description": "Split Markdown into overlapping chunks ready for embeddings or LLM retrieval.", "default": false }, "chunkSizeChars": { "title": "RAG chunk size", "minimum": 500, "maximum": 50000, "type": "integer", "description": "Approximate maximum characters per Markdown chunk.", "default": 6000 }, "chunkOverlapChars": { "title": "Chunk overlap", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Characters overlapped between consecutive chunks.", "default": 500 }, "renderMode": { "title": "Rendering mode", "enum": [ "http", "browser", "auto" ], "type": "string", "description": "HTTP is fastest. Browser renders client-side JavaScript. Auto starts with HTTP and falls back to browser for failures or very thin scripted pages.", "default": "http" }, "minStaticTextChars": { "title": "Auto fallback text threshold", "minimum": 0, "maximum": 20000, "type": "integer", "description": "In auto mode, browser rendering is used when static body text is below this size and scripts are present.", "default": 300 }, "browserWaitUntil": { "title": "Browser wait strategy", "enum": [ "domcontentloaded", "load", "networkidle" ], "type": "string", "description": "Readiness strategy for browser-rendered pages.", "default": "domcontentloaded" }, "browserDelayMs": { "title": "Browser extra delay", "minimum": 0, "maximum": 30000, "type": "integer", "description": "Extra milliseconds after browser navigation before converting HTML.", "default": 500 }, "browserWaitForSelector": { "title": "Browser wait for selector", "type": "string", "description": "Optional CSS selector that must become visible before browser HTML is captured.", "default": "" }, "proxyConfiguration": { "title": "Browser proxy configuration", "type": "object", "description": "Optional Apify/custom proxy for browser rendering. Fast HTTP mode remains direct.", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }