To remove ".html" from all links within html pages - I wrote this to fix this issue: https://github.com/emckiernan/whyopenresearch/issues/5

html_remover.py

import codecs # to read html
from bs4 import BeautifulSoup # to parse html
import glob # to find all files with a pattern
pages = glob.glob("*.html")

for page in pages:
    # loop through all files
    name = page.split(".")[0]
    print (name)
    html=codecs.open(page, 'r') # read html
    text = html.read()
    soup = BeautifulSoup(text,"html.parser") # parse html
    for link in soup.findAll('a'):
        link['href'] = link['href'].replace(".html", "") # find .html and replace it with null string
    html = soup.prettify() # re-style the output
    
    with open(name+".html", "w") as f:
        f.write(html)