A number $n$ of headlines from the BBC world news portal will be downloaded through web-scrapping. This information will be stored in a .csv file autogenerated by the program; This files contains the date of the news and the headline. With this data, new headlines will be generated using Markov chains. Finally, graphs will be displayed that show an analysis of the information collected.
-
Install requeriments
pip install -r requirements.txt
-
Change credentials.
Go to the .env file, and add your data (username, website, email).
-
Run the main file
You can find all the original date in data/exp_1 and all the generated title in data/exp_2
