It used to be that blogs all had RSS feeds. Somehow there are more blogs than ever before, but some people do not bother with setting up an RSS feed.

The following blogs have nice content, but are annoying to follow without RSS.

Every time I stumble on one of these, it takes me a while to remember a fun workaround. I decided to write this down as a blog post so I have an easier time looking up the details.

Let’s generate an RSS feed

Smarter people than me figured out that one can use CSS selectors to extract rss-like content from webpages. https://feedmaker.fly.dev/ is my favorite.

However, it is a real pain in the ass to write these rules by hand. I do not remember the CSS selector DSL because I almost never use it and reading generated HTML is not my idea of fun.

Detecting a pattern and translating it into another is a perfect application of an LLM.

Here is a template chat: https://chatcraft.org/c/tarasglek/9KnqnBb6jb8g3335_-pzk

The trick is:

  1. Show one of the sufficiently advanced samples from the feedmaker homepage to the LLM

  2. Make it explain to itself how it works. This might be optional with modern thinking LLMs

  3. Paste the HTML from the rss-less blog (or use http://chatcraft.org /import command)

  4. Ask the LLM to generate an rss feed URL