import requests
import re
import json

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>'
quote_pattern = r'<span class="inq">([^<]+)</span>'

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


movies = []
title_index = 0
for i in range(10):
    
    while title_index < len(titles) and titles[title_index].startswith('/'):
        title_index += 1
    
    movie = {
        'rank': i + 1,
        'title': titles[title_index] if title_index < len(titles) else '',
        'en_title': '',
        'rating': ratings[i] if i < len(ratings) else '',
        'quote': quotes[i] if i < len(quotes) else ''
    }
  
    if title_index + 1 < len(titles) and titles[title_index + 1].startswith('/'):
        movie['en_title'] = titles[title_index + 1].replace('/ ', '')
    
    movies.append(movie)
    title_index += 1

with open('movies.json', 'w', encoding='utf-8') as f:
    json.dump(movies, f, ensure_ascii=False, indent=2)

print('已保存到 movies.json')

with open('movies.json', 'r', encoding='utf-8') as f:
    data = json.load(f)
    print(f'共保存 {len(data)} 部电影')
    for m in data[:3]:
        print(f"  {m['rank']}. {m['title']} ({m['en_title']}) - {m['rating']}")