Python 早报

• 来源于 365资讯简报

demo

'''
早报
早报地址：https://www.163.com/dy/media/T1603594732083.html
'''
import requests
from lxml import etree

def main():
    url="https://www.163.com/dy/media/T1603594732083.html"
    rsp=requests.get(url)
    html=etree.HTML(rsp.text)
    today_url=html.xpath("//h2[@class='media_article_title']/a/@href")[0]
    rsp=requests.get(today_url)
    html=etree.HTML(rsp.text)
    news_list=html.xpath("//div[@class='post_body']/p[2]//text()")
    news_list=news_list[1:]
    for news in news_list:
        print(news)
if __name__ == "__main__":
    main()