βž•Add data to a document

As you could have already noticed, NeuralText is able to extract a lot of data from pages ranking on Google.

Sometimes you might want to add these data to the document.

This article will explain what are the available options to include data in the document.

Import from URL

You can import content from external URLs in this way:

  1. Click on the β€œImport from URL” icon in editor toolbar

  2. Insert the URL in the field

  3. Click on β€œProcess URL”

  4. After a few seconds, you will see a preview of the extracted article

  5. Click on β€œConfirm” button to insert in the editor

Why NeuralText is unable to pull data from some URLs?

Although are doing our best to extract the text content from competitor pages as possible, sometimes we cannot get the data we need.

Below are a few reasons why this might be the case:

  • Several pages lack enough text content. We use heading tags to evaluate if a page has enough text content to be considered useful to the user. Our extraction algorithms tend to consider the main content of a page, removing all the boilerplate (navbar, sidebar and footer links etc.).

  • Blocked Page - Some websites block third parties from programmatically accessing the contents of their site.

  • Unstructured Content - There are many parts of a website that aren't part of the main content. For instance, a navigation bar, footer, sidebar, or any advertisements. Whenever we extract content from a page we try to get rid of these unimportant elements. When the page structure looks confusing to our system, it can mean we are unable to identify the content, and therefore can't extract the text from a page.

We are continuously improving our extraction engine. If you need some help, don’t hesitate to contact our friendly support.

Last updated