This project aims to build a tool to Data Extraction and NLP i.e. analyse given web aricles in form of list of urls and to genarate Sentiment Analysis . The objective of this project is to extract textual data articles from the given URL and perform text analysis to compute variables like

• Positive Score
• Negative Score
• Polarity Score
• Subjectivity Score
• Average Sentence Lenght
• Percent of Complex Words
• Fog Index
• Average Nember of Words Per Sentence
• COMPLEX WORD COUNT
• WORD COUNT
• SYLLABLE PER WORD
• PERSONAL PRONOUNS
• AVG WORD LENGTH

Labraries and dependancies Used

• BeautifulSoup - from bs4 import BeautifulSoup
• Natural Language Tool Kit nltk
• Numpy
• Pandas
• os

List of URLS and there source can be provided using Input.xlsx file in a list format

My Approch is to make funtions for each variable we want to find

Text file is genarated with title and article with file name same as given in the source inpute file for each source in same Directory / Folder

Output_File is genarated in same Directory / Folder