Extract text from an article HTML

gistfile1.txt

from bs4 import BeautifulSoup

def parseContent( content ):
     # parse the html using beautiful soap and store in variable `soup`
    soup = BeautifulSoup(content, 'html.parser')

    # Take out the <div> of name and get its value
    content = soup.find_all(['h1','h2','h3','h4','h5', 'p','a'])

    text = ""
    for tag in content:
        if tag.string is not None:
            text = text + " " + tag.string
    return text