{ "openapi": "3.0.1", "info": { "title": "HTML to Markdown Converter: Webpage to Markdown & JSON", "description": "Turn any webpage URL or raw HTML into clean, LLM-ready Markdown + JSON for RAG pipelines and AI agents. Removes menus, footers and cookie banners; keeps headings, tables and links. No browser, robots.txt respected. $1.50 per 1,000 pages, failed pages free.", "version": "0.1", "x-build-id": "3GpB5VNaNAc9i0S4K" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/grace_hartwell~html-to-markdown-json/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-grace_hartwell-html-to-markdown-json", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/grace_hartwell~html-to-markdown-json/runs": { "post": { "operationId": "runs-sync-grace_hartwell-html-to-markdown-json", "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/grace_hartwell~html-to-markdown-json/run-sync": { "post": { "operationId": "run-sync-grace_hartwell-html-to-markdown-json", "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": "URLs", "type": "array", "description": "Public web pages to convert. Each URL is fetched once (no crawling of further links). robots.txt is respected. If you leave URLs, raw HTML and HTML documents all empty, the Actor converts the demo page https://example.com/.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "rawHtml": { "title": "Raw HTML", "type": "string", "description": "Optional: paste an HTML document to convert it without fetching anything." }, "rawHtmlBaseUrl": { "title": "Base URL for raw HTML", "type": "string", "description": "Optional: used to turn relative links/images in the raw HTML into absolute URLs." }, "htmlDocuments": { "title": "Multiple raw HTML documents (JSON)", "type": "array", "description": "Optional: array of objects like {\"html\": \"...\", \"url\": \"https://optional-base-url\"}." }, "extractMainContent": { "title": "Extract main content only", "type": "boolean", "description": "Remove navigation, headers, footers, cookie banners, sidebars and other boilerplate (Mozilla Readability + cleanup). Turn off to convert the whole .", "default": true }, "keepLinks": { "title": "Keep links in Markdown", "type": "boolean", "description": "Render hyperlinks as [text](url). Off = plain text only.", "default": true }, "keepImages": { "title": "Keep images in Markdown", "type": "boolean", "description": "Render images as ![alt](src).", "default": false }, "keepTables": { "title": "Convert tables", "type": "boolean", "description": "Convert HTML tables to Markdown (GFM) tables. Off = drop tables.", "default": true }, "includeLinks": { "title": "Return links list", "type": "boolean", "description": "Add a structured `links` array (url, text, internal) to each result. mailto:/tel: links are never included.", "default": false }, "redactEmails": { "title": "Redact e-mail addresses", "type": "boolean", "description": "Replace e-mail addresses in the Markdown with [email removed]. Recommended (privacy).", "default": true }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of URLs + HTML documents converted in this run. Also capped by your 'Max total charge' budget.", "default": 100 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Per-page download timeout.", "default": 30 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum parallel downloads.", "default": 5 }, "maxRequestsPerMinute": { "title": "Max requests per minute", "minimum": 1, "maximum": 600, "type": "integer", "description": "Global rate limit. Additionally there is a 1 s delay between requests to the same domain.", "default": 60 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Not needed for most public pages. Proxies are NOT used to bypass logins or paywalls.", "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 } } } } } } } } } }