python爬虫获取豆瓣电影top250的名字

最近面试了一个爬虫实习岗位,不知道能不能过,先学习一下爬虫练练手.

import re
import urllib.request
import urllib.error


def get_douban_pages():
    index = 1  # 电影排名
    # 伪装成浏览器
    header = {
        'User-Agent':
        'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:84.0) Gecko/20100101 Firefox/84.0'
    }
    for i in range(0, 10):  # 0~19
        num = i * 25
        url = 'https://movie.douban.com/top250?start=%d&filter=' % num
        req = urllib.request.Request(url, headers=header)

        try:
            response = urllib.request.urlopen(req, timeout=1.5)
            # 过滤出所有影片名(各地的影片名)
            reg = r'<span class="title">.*?</span>'
            reg_ques = re.compile(reg)
            name_list = reg_ques.findall(response.read().decode('utf-8'))

            # 过滤出需要的(大陆的影片名)影片名
            name_list2 = []
            reg2 = r'^(?!.*&nbsp;)'  # 不含&nbsp;的字符串,其他地方的影片名前面都是有&nbsp;的
            reg_ques = re.compile(reg2)
            for name in name_list:
                if reg_ques.match(name):
                    name_list2.append(name)
            for name_html in name_list2:
                name = name_html[20:][0:-7]
                print('NO.', index, ' ', name)
                index += 1
        except urllib.error.URLError as e:
            if hasattr(e, 'reason'):
                print(e.reason)


if __name__ == "__main__":
    get_douban_pages()