Function used to pull a single letter page for the Epistulae Morales Ad Lucilium extraction.

hello_lucilius_letter.py

# create function to pull letter from webpage (pulls text within <p> elements
def pull_letter(http):

    # get html from webpage given by 'http'
    html = requests.get(http).text
    # parse into a beautiful soup object
    soup = BeautifulSoup(html, "html.parser")

    # build text contents within all p elements
    txt = '\n'.join([x.text for x in soup.find_all('p')])
    # replace extended whitespace with single space
    txt = txt.replace('  ', ' ')
    # replace webpage references ('[1]', '[2]', etc)
    txt = re.sub('\[\d+\]', '', txt)
    # replace all number bullet points that Seneca uses ('1.', '2.', etc)
    txt = re.sub('\d+. ', '', txt)
    # remove double newlines
    txt = txt.replace("\n\n", "\n")
    # and return the result
    return txt