Readability

readability.py

# these modules help us do the script
import html2text
import requests
import sys

# this is the important library that acutally does the work
from textstat.textstat import textstat

# this is an easy way to strip html
h = html2text.HTML2Text()

# we want to not include even link tags
h.ignore_links = True

# function to remove html - could be more robust
def remove_html(in_text):

    return h.handle(in_text)

# grab whatever content was specified in the command line  
url = sys.argv[1]

# we need to strip html tags
test_string = remove_html(requests.get( url ).text)

# show what we grabbed
print( test_string )
print()

# So how readable is it?
print( textstat.flesch_reading_ease(test_string) + " /100" )