Remove all style, scripts, and html tags from an html page

Question

Here is what I have so far:

from bs4 import BeautifulSoup

def cleanme(html):
    soup = BeautifulSoup(html) # create a new bs4 object from the html data loa         


        

Answer 1

Using lxml instead:

# Requirements: pip install lxml

import lxml.html.clean


def cleanme(content):
    cleaner = lxml.html.clean.Cleaner(
        allow_tags=[''],
        remove_unknown_tags=False,
        style=True,
    )
    html = lxml.html.document_fromstring(content)
    html_clean = cleaner.clean_html(html)
    return html_clean.text_content().strip()

testhtml = "\n\nI need this text captured
And this
"
cleaned = cleanme(testhtml)
print (cleaned)