BrianRuizy / web-scraping-NLP

Machine Learning - Personal Python project demonstrating a data analytic technique known as Web Scraping + Natural Language Processing performed on a real webpage.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Lumen
Web Scraping

Personal portfolio project demonstrating a data analytic technique known as web scraping, on this particular project the analysis will be performed onto Barnes & Noble data.

About

Web scraping is a technique used to extract certain elements from web pages to develop quantitative resolutions from data. With the use of Sentiment Analysis, a useful method for detecting expression in text, web scraping can become a valuable application for many companies or brands who desire a deeper insight into their clients/ customers.

For this particular project, I extracted data from a Barnes & Noble webpage depicting a particular used-book seller feedback. I managed to gather the sites .html through Chrome's Developer Tools.

Dependencies

  • textblob
  • bs4 (BeautifulSoup)
  • termcolor

Result

The output of some of the "reviews" with the respective polarity preceeding.

screen shot 2019-03-01 at 2 43 09 am

The output of the count of both positive and negative reviews.

screen shot 2019-03-01 at 2 36 48 am


About

Machine Learning - Personal Python project demonstrating a data analytic technique known as Web Scraping + Natural Language Processing performed on a real webpage.


Languages

Language:HTML 87.2%Language:Python 12.8%