extract_meta.py

from bs4 import BeautifulSoup

def extract_meta(data):
    """
    This function takes raw html data as input
    and gives title, description, keywords as output
    """
    soup = BeautifulSoup(data, 'html.parser')
    meta = ""
    title = soup.title.string
    title = title
    meta = soup.findAll('meta')
    data ={}
    data["title"] = title
    for tag in meta:
        name = tag.get('name')
        if name in ["title",'description','keywords']:
            desc = tag.get('content')
            data[name] = data.get(name," ")+desc
            data[name].strip()
    return data