import requests
import re

# 1. ȡҳ
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
}
url = 'https://movie.douban.com/top250'

response = requests.get(url, headers=headers)
html = response.text

# 2. ʽȡӰ
# Ӱ <span class="title"> 
pattern = r'<span class="title">([^<&]+)</span>'
titles = re.findall(pattern, html)

# 3. ˵Ӣֻ
chinese_titles = [t for t in titles if not t.startswith('/')]

# ȡǰ10
top10 = chinese_titles[:10]

# 4. 浽ıļ
with open('movies.txt', 'w', encoding='utf-8') as f:
    for i, title in enumerate(top10, 1):
        f.write(f'{i}. {title}\n')

print('ѱǰ10Ӱ movies.txt')

# ʾ֤
with open('movies.txt', 'r', encoding='utf-8') as f:
    print(f.read())