#Created by 七老狮
# filename :Google_News.py.py
import bs4
import lxml #xml parser
import ssl
from bs4 import BeautifulSoup as soup
from urllib.request import urlopen

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)

Google_News.py

  • 代码
    161 引用 • 44 回帖
  • python

    Python (发音:[ paiθ(ə)n; (US) paiθɔn ]n. 蟒蛇,巨蛇 ),是一种面向对象的解释性的计算机程序设计语言,也是一种功能强大而完善的通用型语言,已经具有十多年的发…

    7952 引用 • 22 回帖 • 2 关注
  • 简易小工具
感谢    赞同    分享    收藏    关注    反对    举报    ...