gistfile1.txt

def parsedoc(url):
    page = urlopen(Request(url, headers={'User-Agent': 'Mozilla'}))
    soup = BeautifulSoup(page, features="html.parser")
    for div in soup.find_all("div", {'id': "comments"}):
        div.decompose()
    for footer in soup.find_all("footer", {'id': "footer"}):
        footer.decompose()
    code = len(soup.find_all('code'))
    img = len(soup.find_all('img'))
    clean = soup.find('time')
    clean2 = soup.find('h1')
    headline2 = soup.find_all('h2')
    headlines = len(headline2)
    time = bleach.clean(str(clean), tags=[], strip=True)
    title = bleach.clean(str(clean2), tags=[], strip=True)
    return {"title": title,
            "time": time,
            "headlines": headlines,
            "img": img,
            "code": code}