I'm experimenting with ValueSERP, but I'm having a problem

Hello,
I’m experimenting with ValueSERP, but I’m having a problem with it not being able to remove the HTML and CSS from the scraped data. As a result, I end up with an excessive amount of data, which exceeds ChatGPT’s processing capacity due to the token limit.

Merci

To get helpful responses

  • explain your goal with as m


uch context as possible

  • mention any steps you’ve tried so far

Include screenshots of

Welcome to the Make community!

You can use the built-in function stripHTML.

E.g.:

{{ stripHTML("YOUR_HTML_GOES_HERE") }}

Screenshot_2024-02-06_230233

1 Like

There is also a Text Parser module called HTML to Text that will also extract HTML and links from the HTML. I find it to be a better solution than the stripHTML() function which I think it best used for HTML snippets rather than large blocks of HTML like whole page.

Have a look at the sample output each of these generates in this scenario example.

Here’s a blueprint you can use to try it out…
blueprint (29).json (11.8 KB)

1 Like