pip install newspaper3k
pip install git+https://github.com/codelucas/newspaper.git
python
import newspaper
user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'
config = newspaper.Config()
config.browser_user_agent = user_agent
article = newspaper.Article(url, config=config)
python
import newspaper
from selenium import webdriver
driver = webdriver.Chrome()
driver.get(url)
html = driver.page_source
article = newspaper.Article(url)
article.set_html(html)
article.parse()
python
import newspaper
article = newspaper.Article(url)
article.download()
article.set_html(article.html.decode('utf-8', 'ignore'))
article.parse()
python
import newspaper
from bs4 import BeautifulSoup
article = newspaper.Article(url)
article.download()
article.parse()
soup = BeautifulSoup(article.html, 'html.parser')
images = soup.find_all('img')
for image in images:
image_url = image['src']
