search

dragnet-org / dragnet

Just the facts -- web page content extraction
MIT License
1.26k stars 180 forks source link

how to train it to get author name and headline #72

Open akashmondal1810 opened 6 years ago

pakelley commented 6 years ago

@akashmondal1810 If you have a labelled dataset you can always train a custom model to extract only the author name and headline. Hope that helps!

trifle commented 5 years ago

PS, @akashmondal1810 here is a pointer to get started: https://github.com/dragnet-org/dragnet#training-content-extraction-models Issue https://github.com/dragnet-org/dragnet/issues/27