🔬 Convert web pages to clean Markdown with TopAI Web-to-Markdown API
⚡ 0 views · 🔬 Document Extraction & Analysis
Description
Quick overview
This workflow manually converts a specified webpage URL into cleaned, RAG-ready Markdown by calling TopAI Gateway’s Web-to-Markdown API over HTTP.
How it works
- Starts automatically when you trigger the workflow manually, via webhook, or through a recurring scheduled trigger in n8n.
- Sends a high-speed POST request to TopAI Gateway’s Anycast Edge Web-to-Markdown API with the target webpage URL and configuration options.
- Cleans up HTML boilerplate, strips promotional ads, cookie popups, and scripts while preserving markdown tables and document metadata for RAG ingestion.
Setup
- Create a free TopAI Gateway developer account and generate your API key at https://topaigateway.com.
- Replace the ‘Authorization’ header parameter value in the HTTP Request node with your personal token: ‘Bearer <YOUR_TOPAI_API_KEY>’.
- Update the JSON request body with the target website ‘url’ you want to convert and adjust cleanup options like ‘strip_ads_and_scripts’ and ‘preserve_tables’ as needed.
Requirements
- TopAI Gateway API Key (Free tier available at https://topaigateway.com)
Customization
- Set ‘strip_ads_and_scripts’ to true to eliminate noise, or set ‘preserve_tables’ to true to keep HTML tables formatted as markdown tables.
🔗 Nodes Used
HTTP Request
📥 Import
Download workflow.json and import into n8n:
Workflow menu → Import from File