#获取知乎的网站内容

import requests #数据请求模块 第三方模块 pip install requests

import re #正则表达式

#网页head头

heads = {

    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.99 Safari/537.36'

}

def get_response(html_url):

    response = requests.get(url=html_url, headers=heads)

    return response

url= 'https://zhuanlan.zhihu.com/p/435694901'

response_new = get_response(html_url=url)

print(response_new.text)

#<p data-pid="R1eByHKC">100. 如果你拥有一种超能力，你会用它去做什么</p>

html_data = re.findall('<p data-pid="\w+">(.*?)</p>', response_new.text)

print(html_data)

for url in html_data:

    print(url)