New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Feat] Improve extract only main content #748

Open

tomkosm opened this issue Oct 8, 2024 · 3 comments

Collaborator

tomkosm commented Oct 8, 2024

Its broken on some site, ie: https://www.jto.org/article/S1556-0864(20)30292-6/fulltext

We should also evaluate potentially using:
https://github.com/mozilla/readability

Member

nickscamara commented Oct 8, 2024

We could fallback to readability. It is not that great for links and we would need to do significant regex parsing to fix multi-line links etc.

Member

nickscamara commented Oct 8, 2024 •

edited

Loading

Another feature request is to clean a lot further, excluding links and images

Contributor

calebpeffer commented Oct 10, 2024

found another site this is broken on:

https://machinelearningguider.blogspot.com/2024/09/langchain-code-journey-from-basics-part_2.html?m=1

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment