Skip to content

Latest commit

 

History

History
20 lines (15 loc) · 1.21 KB

README.md

File metadata and controls

20 lines (15 loc) · 1.21 KB

Article Summary Machine

This program will use a web scraper to extract news articles from various online news sources and output a short and concise summary. It is written in Python 3 and makes use of beautifulsoup4 (web scraper) and spaCy (open-source natural language processessing library). Our target audience are individuals who are tight on time but still want to keep up with current news. This will hopefully reduce the number of people who are misinfirmed because they only read the title of news article, but not the article itself.

Setting Up

beautifulsoup4: Run pip install beautifulsoup4 in the command line.
spaCy: Run pip install -U spacy in the command line.

Usage

Run guidemo.py, paste the link of the news article you wish to summarize, and select the correct scraper.

Authors

  • Aaron Lee
  • Josh Wong
  • Ramon Lin

Sources Used

https://stackoverflow.com/questions/36730372/extract-the-text-from-p-within-div-with-beautifulsoup https://jcharistech.wordpress.com/2018/12/31/text-summarization-using-spacy-and-python/ https://stackoverflow.com/questions/6116978/how-to-replace-multiple-substrings-of-a-string