import requests
import re
import csv

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

title_pattern = r'<span class="title">([^<&]+)</span>'
rating_pattern = r'<span class="rating_num"[^>]*>(\d+\.?\d*)</span>'

titles = re.findall(title_pattern, html)
ratings = re.findall(rating_pattern, html)

movies = []
for i in range(min(10, len(titles))):
    # 每两个title为一组（中文 + 可能有的英文）
    title = titles[i] if not titles[i].startswith('/') else ''
    en_title = titles[i+1] if i+1 < len(titles) and titles[i+1].startswith('/') else ''
    en_title = en_title.replace('/ ', '') if en_title else ''
    
    movie = {
        'rank': i + 1,
        'title': title,
        'en_title': en_title,
        'rating': ratings[i] if i < len(ratings) else ''
    }
    movies.append(movie)

with open('movies.csv', 'w', encoding='utf-8', newline='') as f:
    writer = csv.DictWriter(f, fieldnames=['rank', 'title', 'en_title', 'rating'])
    writer.writeheader()
    writer.writerows(movies)

print('已保存到 movies.csv')


with open('movies.csv', 'r', encoding='utf-8') as f:
    for line in f:
        print(line.strip())