get text from a web page

get_website_text.py

from bs4 import BeautifulSoup
from bs4.element import Comment
import requests


def tag_visible(element):
    if element.parent.name in ['script', 'style', 'head', 'title', 'meta', '[document]']:
        return False
    if isinstance(element, Comment):
        return False
    return True


def get_text(url):
    all_text = []
    page = requests.get(url)
    soup = BeautifulSoup(page.content, "lxml")
    texts = soup.findAll(text=True)
    visible_texts = filter(tag_visible, texts)
    all_text.append(u" ".join(t.strip() for t in visible_texts))
    return " ".join(all_text)

print(get_text("http://doraithodla.com"))