Python爬虫：5_爬取豆瓣Top250电影

代码

import requests
import re
import csv

#　拿取页面源代码
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/94.0.4606.81 Safari/537.36'
}
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.*?<span '
                 r'class="rating_num" property="v:average">(?P<score>.*?)</span>.*?'
                 r'<span>(?P<num>.*?)人评价</span>', re.S)

ret = obj.finditer(page_content)

f = open('data.csv', mode='w')
csvwriter = cs