Skip to content
Agentic WorkFlow

Get All Text From Link

The Get All Text From Link node is designed to help you gather information from the web quickly. It takes a web address (URL), visits that page in the background, and returns every piece of readable text it finds.

This node is the perfect starting point for building a “Research Assistant” or a news aggregator, as it turns a messy web page into clean, searchable text.

Illustration of text being extracted from a website link

How it works

Section titled “How it works”

When this node runs, it opens the provided link in a hidden browser context. It intelligently ignores background “noise” like programming scripts or styling code, focusing only on the words a human would actually read on the screen.

graph LR
  URL --> Node{Get All Text}
  Node --> Output
  style Node fill:#6d28d9,stroke:#fff,color:#fff

Setup guide

Section titled “Setup guide”
  1. Identify the link: Connect this node to a step that provides a URL, or type a web address directly into the Link URL field.
  2. Choose extraction depth: By default, the node captures everything. You can toggle options to include or exclude specific sections like headers and footers.
  3. Run the node: Once executed, the node will output a text block containing the full content of the page.

Practical example

Section titled “Practical example”

Imagine you have a list of blog post links and you want to summarize them using an AI.

Imagine you have a list of blog post links and you want to summarize them using an AI.

What you configure:

  • Link URL: The web address of the blog post (e.g., https://example.com/blog).
  • Options: Choose whether to include headers or footers, or just the main content.

What you get:

  • Text: A clean block of text containing the article content.
  • Result: “How to Automate Your Workflow. Automation is the key to productivity… In this guide, we will explore…”

Useful tips

Section titled “Useful tips”

Common questions

Section titled “Common questions”
Section titled “Does it work with PDF links?”

This node is optimized for web pages (HTML). For PDF files, we recommend using a specialized document processing node.

Will it capture text inside images?

Section titled “Will it capture text inside images?”

No. This node only reads text that is part of the page code. If a website displays text as an image, this node will not be able to “see” it.