Any implementation of Pytorch library "newsletter3k"?

Hi everyone,

Do you know if there is any implementation of newsletter3k library? It seems very straightforward to be a node :slight_smile:


Hi there,

Interesting lib, didn’t know it so far.

The Palladian Web Page Content Extractor seems to cover partly the same goal, so maybe you want to give it a try? It’s based on the “Readability” algorithm, which afair is quite similar to/the foundation to what Instapaper used (which in turn is used in the mentioned newsletter3k).

More information about the node here:


– Philipp

1 Like

Thank you Philipp. I’ve used Palladian before with mixed results depending on the type of website. What I find interesting from newsletter3k is the other all-in-one features: url identification, keyword extraction, summary, author, google trending terms, …

  • Diego

That’s indeed quite interesting, and currently not supported out of the box. Thanks for sharing your feedback! :slight_smile: