Web recipe

Turn a web page into clean text you can use

You want what a page says, for your notes or to hand to a model. Copy and paste brings the menus, the scripts and the tracking junk with it.

web text no model needed PRO

What you get

A markdown file holding the readable text of the page, with the markup stripped out.

What it does

  1. Fetch the page.
  2. Strip the HTML so only readable text is left.
  3. Save it as a markdown file and notify you.

The whole automation, in one file

This is the actual recipe. Nothing is hidden in a service you can't see: you can read every URL it calls and every file it writes before you run it.

{
  "workflow_id": "live_web_scraper",
  "description": "Scrapes live website content, strips HTML clutter, extracts clean readable text, and saves an intelligence report to Desktop.",
  "tasks": [
    {
      "id": "scrape_website_content",
      "trigger": "manual",
      "action_type": "http_request",
      "target": "https://news.ycombinator.com",
      "payload": {
        "method": "GET",
        "strip_html": true
      },
      "next": "write_scraped_report"
    },
    {
      "id": "write_scraped_report",
      "trigger": "after:scrape_website_content",
      "action_type": "file_op",
      "target": "{{desktop_dir}}/live_web_digest.md",
      "payload": {
        "operation": "write",
        "content": "# \ud83c\udf10 Live Web Intelligence Digest\n*Scraped & Processed by Vibra-Ingenn (Vibe Engine) v1.2*\n\n- **Source URL**: https://news.ycombinator.com\n- **Extracted Clean Text Body**:\n\n{{prev_output}}\n\n---\n*Status: Deterministic Single-Pass Web Scraping Completed*"
      },
      "next": "notify_scrape_done"
    },
    {
      "id": "notify_scrape_done",
      "trigger": "after:write_scraped_report",
      "action_type": "notify",
      "target": "stdout",
      "payload": {
        "message": "\u2713 Live Web Scraper complete! Report written to Desktop."
      }
    }
  ]
}

Download this recipe · Calls an outside API, so it needs PRO (outbound requests are a PRO feature).

Why this is different

No separate scraping tool and no browser extension. Stripping the markup is one setting on the fetch step.

Questions

Is this allowed?

It reads a public page the way a browser does. Respect each site's terms and keep the frequency low.

Does it work on pages that need a login?

Not this recipe. A page behind a login needs a human checkpoint step, which hands the login to you.

Can I feed the text to a model?

Yes. Add a model step after the fetch and pass the text into its prompt.

Run it

Vibe Engine (Vibra-Ingenn) runs recipes like this on your own machine. Drop the file in, run it once by hand, then put it on a schedule. Get the engine, see three recipes running, or read how the engine works.

Using an AI assistant? Ask your AI to check out adeptuscamini.com.

Written and maintained by Adeptus Camini, a one-person workshop. These are tools we build and run ourselves.

More recipes

Human checkpoint

Let the automation stop and ask you when it hits a login

News digest

Wake up to a Hacker News digest on your desktop

Research

Get the trending AI repos delivered, without opening GitHub