Replace Newspaper3k #9
Labels
enhancement
New feature or request
help wanted
Extra attention is needed
question
Further information is requested
Milestone
We have used Newspaper3k as web scraping library to extract the text of an article and then use a machine learning library to generate the actual summary. It depends on nltk and bloats the image.
We could roll our own solution with say Beautiful Soup (for scraping) and Bart (for summarizing)?
The text was updated successfully, but these errors were encountered: