pip install newspaper3k
python
from newspaper import Article
article = Article(url)
article.download()
article.parse()
title = article.title
author = article.authors
publish_date = article.publish_date
python
from newspaper import Article
def is_junk_news(url):
article = Article(url)
article.download()
article.parse()
article.nlp()
keywords = article.keywords
for keyword in keywords:
if keyword in junk_keywords:
return True
return False
python
from newspaper import Article
def categorize_article(url):
article = Article(url)
article.download()
article.parse()
article.nlp()
keywords = article.keywords
categories = {
}
for category, keywords_list in categories.items():
for keyword in keywords:
if keyword in keywords_list:
return category
