利用正则表达式写的爬取网站数据

import re
import requests
import csv

url = "https://movie.douban.com/top250"
headers = {
   "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36 Edg/125.0.0.0"
}
resp = requests.get(url , headers=headers)
page_content = resp.text

# 解析数据
obj = re.compile(r'<li>.*?<div class="item">.*?<span class="title">(?P<name>.*?)'
                 r'</span>.*?<p class="">*?<br>(?P<year>.*?)&nbsp.*?'
                 r'<span class="rating_num" property="v:average">(?P<score>>*?)'
                 r'</span>.*?<span>(?P<pinjia>)人评介</span>',re.S)

result = obj.finditer(page_content)
f = open("data.csv", mode='w')
csvwriter = csv.writer(f)
for it in result:
    dic = it.groupdict()
    dic['year'] = dic['year'].strip()
    csvwriter.writerow(dic.values())
f.close()
print("over")