A program which scrapes news articles from 2 websites, saves them, and performs NLP on the article texts.
- This program scrapes www.prnewswire.com and www.marketwatch.com and writes the titles, URLs, and article texts to a JSON file.
- The article texts are then analyzed using NLP by performing NER using spaCy; as well as NER and Sentiment Analysis using IBM Watson.
- Everything listed above can be run and updated using the master.py file