I've scraped Google News articles in to Sheets - how to update sheets with entire HTML OR PDF

I managed to scrape Google News articles titles and meta data into a google spreadsheet. Now I want to to automatically go to each article URL, pull the full (entire) html, so I can LATER use the data with ChatGPT (custom instructions). Can anyone help with very detailed instructions?


On your case seems like 2 options:

1. Modifying your automation to get the HTMLs

You add the HTML extraction into the existing automation you have

This would require adding “get html from current page” or “get html from urls” (if it’s multiple) into the automation.

2. Getting the links from the spreadsheet, getting the HTML’s and returning them back to the spreadsheet

This is possible and some something you can ask Bardeen’s Magic Box! (Try it next time)

Here’s how I got it.

This topic was automatically closed 2 days after the last reply. New replies are no longer allowed.