I am really new at this and I am not quite sure what I am doing. I wanted to take a webpage from an RSS feed and have chatgpt make a summary. Then I wanted to be able to post that onto various social media channels.
If you’re fetching the article’s URL, you’ll probably need to do some kind of HTML sanitisation, or convert from HTML to text, or both, before you can pass it to OpenAI.
There is no right way of doing it. You can even use a web scraping module to simplify the job.
For web scraping, some apps you can use are ScrapingBee and ScrapeNinja to get content from the page.
I’ve used ScrapeNinja, and you can use jQuery-like selectors there in the extractor function.
ScrapeNinja also can run the page in a web-browser so it closely emulates what users see, as opposed to just the raw page HTML fetched from the HTTP module.
If you want an example, take a look at Grab data from page and url - #5 by samliew
samliew – request private consultation
Join the Make unofficial Discord server!
1 Like
Thank you for your reply. I do not see a module called “get page” under the HTTP modules. When I search that term in the modules I do not see anything relevant. I am on the “core” plan. Do the subscription level have anything to do with the module not available?
See below – it’s “Make a request”.
1 Like