An n8n workflow fetches a submitted URL, strips it to readable content, has OpenAI summarise it into structured fields, and saves a Notion note.
An n8n workflow fetches a submitted URL, strips it to readable content, has OpenAI summarise it into structured fields, and saves a Notion note.
A webhook receives a URL, an HTTP Request node fetches the page, and a Code node removes scripts, styles and tags, then truncates the text to 8,000 characters. OpenAI, in JSON output mode, returns title, summary, key insights and tags. The Notion node maps these to six properties with no parsing step.
Stripping the HTML first cut the payload from about 60K tokens to under 4K. Summaries improved and cost dropped significantly. JavaScript-heavy single-page apps return empty shell HTML, and some sites block requests.
Share the Notion database with your n8n integration first, or the write fails silently. Adding a Mozilla/5.0 User-Agent header clears most 403 errors.
Build an n8n workflow that starts from a webhook or form where I submit a [URL]. It should fetch the page, strip it down to readable text, ask an AI model to produce a title, a 3-sentence summary, key points and 3 tags, then create a new note in my Notion database [database name] with those fields. You're done when a test URL I submit produces a correctly filled Notion note; show me the draft workflow before you activate it.
Score every demo request against your ICP, update HubSpot and ping the right rep in Slack within a minute of the form submit.
Every new Zendesk ticket gets a category, priority and sentiment tag plus a draft reply in an internal note before an agent opens it.
Each month, find posts whose search clicks dropped, research what changed with Perplexity, and get a Claude-written refresh brief for each one.