“Ekstrak semua teks dari situs web menggunakan Beautifulsoup dan Python” Kode Jawaban

Ekstrak semua teks dari situs web menggunakan Beautifulsoup dan Python

from bs4 import BeautifulSoup
from bs4.element import Comment
import urllib.request


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


def text_from_html(body):
    soup = BeautifulSoup(body, 'html.parser')
    texts = soup.findAll(text=True)
    visible_texts = filter(tag_visible, texts)  
    return u" ".join(t.strip() for t in visible_texts)

html = urllib.request.urlopen('http://www.nytimes.com/2009/12/21/us/21storm.html').read()
print(text_from_html(html))