Featured Template

Get URL Contents

A simple admin-approved workflow that opens a URL and pulls back the main readable page content. It works well for summarization, research pipelines, content cleanup, and feeding downstream AI steps.

Import template Create account to import

Overview

What this template does

Get URL Contents is a lightweight building block workflow. It takes a single URL variable, navigates the browser to that page, waits for the page to settle, and extracts the primary content block as readable text.

Category

General purpose

Inputs

1 required variable: URL

Step count

2 workflow steps

Workflow Steps

How the template runs

1. Navigate

Opens the supplied {{URL}} in the current tab and waits 2000ms so the page has time to render before extraction begins.

Important settings

  • command: navigate
  • url: {{URL}}
  • wait_ms: 2000

2. Get Content

Extracts the first major readable content block from the page as text-only content without image references.

Important settings

  • command: get_content
  • mode: nth
  • n: 1
  • include_images: false

Variables

What you need to supply

URL

The page URL you want to open and extract content from.

{
  "URL": "https://example.com/article"
}

Best For

Where this template fits well

Research and summarization

Use it when you need a clean text version of an article or page before sending that content into an LLM summarizer.

Pipeline building blocks

Use it as a reusable first step inside larger workflows that need browser-based extraction before classification, tagging, or storage.

Limitations

What to keep in mind

  • It currently extracts only the first content block because it uses n: 1.
  • It does not include images in the result.
  • Highly dynamic pages may need a longer wait than 2000ms.