HTML Cleaner

htmlclean.py

import requests
from lxml.html.clean import Cleaner

url = "http://en.wikipedia.org/wiki/Zipf%27s_law"
html = requests.get(url).text
cleaner = Cleaner(allow_tags=[''], remove_unknown_tags=False, remove_tags=['<div>','</div>'])
cleaner.scripts = True
cleaner.page_structure = True
cleaner.javascript = True 
cleaner.style = True
cleaner.comments = True
cleaned_text = cleaner.clean_html(html).replace("\t"," ").replace("<div>",'').replace("</div>","")