Newsletter3K is a good python Library for News content extraction. It works mostly well .I want to extract names after first "by" word in visible text. This is my code, it did not work well, somebody out there please help:
import re
from newspaper import Config
from newspaper import Article
from newspaper import ArticleException
from bs4 import BeautifulSoup
from bs4.element import Comment
import urllib.request
USER_AGENT = 'Mozilla/5.0 (Macintosh;Intel Mac OS X 10.15; rv:78.0)Gecko/20100101 Firefox/78.0'
config = Config()
config.browser_user_agent = USER_AGENT
config.request_timeout = 10
html1='https://saugeentimes.com/new-perspectives-a-senior-moment-food-glorious-food-part-2/'
article = Article(html1.strip(), config=config)
article.download()
article.parse()
soup = BeautifulSoup(article)
## I want to take only visible text
[s.extract() for s in soup(['style', 'script', '[document]', 'head', 'title'])]
visible_text = soup.getText()
for line in visible_text:
# Capture one-or-more words after first (By or by) the initial match
match = re.search(r'By (\S+)', line)
# Did we find a match?
if match:
# Yes, process it to print
By = match.group(1)
print('By {}'.format(By))`