代码拉取完成,页面将自动刷新
import ssl
from urllib.request import urlopen
from bs4 import BeautifulSoup as soup
def news(xml_news_url):
'''Print select details from a html response containing xml
@param xml_news_url: url to parse
'''
context = ssl._create_unverified_context()
Client = urlopen(xml_news_url, context=context)
xml_page = Client.read()
Client.close()
soup_page = soup(xml_page, "xml")
news_list = soup_page.findAll("item")
for news in news_list:
print(f'news title: {news.title.text}')
print(f'news link: {news.link.text}')
print(f'news pubDate: {news.pubDate.text}')
print("+-" * 20, "\n\n")
# you can add google news 'xml' URL here for any country/category
news_url = "https://news.google.com/news/rss/?ned=us&gl=US&hl=en"
sports_url = "https://news.google.com/news/rss/headlines/section/topic/SPORTS.en_in/Sports?ned=in&hl=en-IN&gl=IN"
# now call news function with any of these url or BOTH
news(news_url)
news(sports_url)
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。