bradyjiang

from bs4 import BeautifulSoup

# 20190720, from: https://stackoverflow.com/questions/30565404/remove-all-style-scripts-and-html-tags-from-an-html-pagesoup = BeautifulSoup(str_html)
for s in soup(["head"]):
    s.decompose()
cleaned_html = str(soup)

bradyjiang

from lxml.html.clean import Cleaner

#to prevent Cleaner to replace html with div, leave page_structure alone: http://stackoverflow.com/questions/15556391/lxml-clean-html-replaces-html-tag-with-div
cleaner = Cleaner(page_structure=False)
#according to: http://stackoverflow.com/questions/8554035/remove-all-javascript-tags-and-style-tags-from-html-with-python-and-the-lxml-mod
#Cleaner is a better general solution to the problem than using strip_elements, because in cases like this you want to strip out more than just the <script> tag; you also want to get rid of things like onclick=function() attributes on other tags.
cleaner.javascript=True
cleaner.scripts=True
#turn this on in the future if necessary
#cleaner.style=True