Arjuna is a NLP Project to generate poets and poems based on Bahasa language. This repository is sources that used at PyCon ID 2021 talks created by @miqdude and @veronicaads.
This repository consist two main folder: scraper and model.
This folder contains python script that used to do web scraping to https://www.kompas.id/kategori/sastra/ as dataset for the model.
You need to register to https://www.kompas.id first before use this scraper to fill the email and password parameter.
Please install all the requirements library at requirements folder : pip install -r requirements.txt
python kompas_sastra_scraper.py --user_email [email protected] --password xxxxxxxxxx --depth 5