Extracting text did not work—still gives me HTML

Hi, I’ve added an Extract Data node asking for just the text within the HTML source provided by the scraper node (which I thought was supposed to perform this operation of selecting only the content of an element—please see other post).

However, despite specifying “Extract only the text content found within the HTML element with id=‘main-content’” I am still getting HTML.

Please see:
https://www.gumloop.com/pipeline?workbook_id=aFcqA9m5SygZmmu7m6MFDL&tab=1

Hey @AangelHD! If you’re reporting an issue with a flow or an error in a run, please include the run link and make sure it’s shareable so we can take a look.

  1. Find your run link on the history page. Format: https://www.gumloop.com/pipeline?run_id={{your_run_id}}&workbook_id={{workbook_id}}

  2. Make it shareable by clicking “Share” → ‘Anyone with the link can view’ in the top-left corner of the flow screen.
    GIF guide

  3. Provide details about the issue—more context helps us troubleshoot faster.

You can find your run history here: https://www.gumloop.com/history

Hey @AangelHD – This is very likely the AI model not sticking to the instructions. You can explicitly specify that you’re looking for text content only in the description field as well. It worked for me here: https://www.gumloop.com/pipeline?workbook_id=shtJstWWXFRzwX9u1Hy1qU&tab=1&run_id=9we53xFhrnPU5JfZm2RGU5

Alternatively you can play around with different AI models as well which can ingest large data like Gemini 2.5 Pro.

Yes, I did manage to get around it with a similar solution. Thank you.

1 Like

This topic was automatically closed 5 days after the last reply. New replies are no longer allowed.