New Features: lm.get_URL(), lm_get_MD(), lm_get_PDF, lm_getTXT, etc...

[Gustavo-Livemix]

It will be wonderfull if there were Helper functions for external retrieval like:

• lm.get_URL(path) for using an URL
• lm_get_MD(path) for using Markdown document
• lm_get_PDF(path) for using PDF documents
• lm_getTXT(path) for using txt documents
• lm_get_DOC(path) for using MS Word documents
• lm_get_JSON(path) for using JSON documents
• etc
  Like there is for lm.get_wiki (), lm.get_weather(), lm.getdate()
  Thanks a lot and keep the great work! It's amazing!

[jncraton]

Thanks for the kind words! I'm glad that you are finding this package useful.

I can certainly see the value of simplifying retrieval from different types of documents. I'm not planning to implement this right now, but I'll consider ways to better integrate this in the future.

As you are probably aware, there are already packages such as textract that specialize in solving the problem of going from all sorts of documents to plain text. Using something like that would hopefully address your immediate needs.