news_scanner.py

import requests
from bs4 import BeautifulSoup

# def scan_news2():
#     url = "https://www.reuters.com/world/" 
#     r = requests.get(url)
#     soup = BeautifulSoup(r.text, "html.parser")

#     # headlines = [h.get_text().strip() for h in soup.select("h3.story-title, h2")]


#     heading_element = soup.find("span", {"data-testid": "TitleHeading"})

#     if heading_element:
#         heading_text = heading_element.get_text(strip=True)
#         print("Heading:", heading_text)
#     else:
#         print("Heading not found")

    
    
#     print('SE SUPONE QUE ES EL TITULAR,')
#     print(headlines[:2])
#     return headlines[:5]  # top5 titulares


def scan_news():
    headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/85.0.4183.121 Safari/537.36'}

    url = "https://www.abc.net.au/news"#"https://www.news.com.au/"#"https://www.nytimes.com/"
    r = requests.get(url, headers=headers)
    r_html = r.text
    # print(r_html)
    # print('----------------------------')
    soup = BeautifulSoup(r_html, "html.parser")
    scripts = soup.find_all('a')
    headlines = [h.get_text().strip() for h in scripts if len(h.get_text().split(' '))>=5]
    return headlines[:1]