filecleaner.py

#!/usr/bin/python3
import requests
from bs4 import BeautifulSoup

def clean(url):
  r = requests.get(url)
  html = r.text

  soup = BeautifulSoup(html, "lxml")
  for script in soup(["script", "style"]):
    script.extract()    # rip it out

  sOut = soup.text

  sOut = sOut.replace("\r", "\n")
  while sOut.find("\n\n") > -1:
  	sOut = sOut.replace("\n\n", "\n")
  return sOut.strip()

if __name__ == '__main__':
  url = 'http://webcache.googleusercontent.com/search?q=cache:JqL5UFr1tGoJ:ru.fallout.wikia.com/wiki/%25D0%259F%25D0%25BB%25D0%25B0%25D1%2581%25D1%2582%25D0%25B8%25D0%25BA%25D0%25BE%25D0%25B2%25D0%25B0%25D1%258F_%25D0%25B2%25D0%25B7%25D1%2580%25D1%258B%25D0%25B2%25D1%2587%25D0%25B0%25D1%2582%25D0%25BA%25D0%25B0+&cd=9&hl=en&ct=clnk&gl=ru&client=ubuntu'
  print (clean(url))