Những vấn đề thường gặp với newspaper3k và cách khắc phục

import newspaper
from newspaper import Config

config = Config()
config.memoize_articles = False
config.fetch_images = False
config.language = 'en'

article = newspaper.Article('https://example.com/article-url', config=config)
article.download()
article.parse()
print(article.title)
 

from bs4 import BeautifulSoup
import requests

url = 'https://example.com/article-url'
response = requests.get(url)
soup = BeautifulSoup(response.content, 'html.parser')
title = soup.find('h1').text
print(title)

from selenium import webdriver
from newspaper import Article

url = 'https://www.wsj.com/livecoverage/trump-biden-rnc-election-2024?mod=hp_lead_pos7'
driver = webdriver.Chrome()
driver.get(url)
html = driver.page_source
driver.quit()

article = Article(url)
article.set_html(html)
article.parse()
print(article.text)

import newspaper
from concurrent.futures import ThreadPoolExecutor

def fetch_article(url):
    article = newspaper.Article(url)
    article.download()
    article.parse()
    return article

urls = ['https://abcnews.go.com/US/trump-assassination-attempt-investigation-continues-new-details/story?id=112020474', 'https://abcnews.go.com/US/rust-armorer-hannah-gutierrez-seeks-new-trial-after/story?id=112012187']
with ThreadPoolExecutor(max_workers=10) as executor:
    articles = list(executor.map(fetch_article, urls))

for article in articles:
    print(article.title)
 

import newspaper
from newspaper import Config

config = Config()
config.language = 'fr'
article = newspaper.Article('https://www.goodmorningamerica.com/news/story/former-nfl-star-terrell-davis-speaks-wrongful-handcuffing-112021507', config=config)
article.download()
article.parse()
print(article.text)