爬虫简单程序（豆瓣top）

import requests as r
import re

header = {
    # 伪装为ie浏览器
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36 Edg/95.0.1020.44'
}

url="https://movie.douban.com/top250"

response=r.get(url=url,headers=header)

# 排除杂项数据，仅提取名称
obj=re.compile(r'<span class="title">(?P<name>.*?)</span>.*?class="">',re.S)

result=obj.finditer(response.text)

for i in result:
    print(i.group("name"))