import requests
import re

headers ={
    'User-Agent': "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chroe/120.0.0.0 Safari/537.36",
}
url = 'https://movie.douban.com/top250'

 

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

pattern = r'<span class> = "title">([^<&]+)</span>'
titles = pattern.findall(html , pattern)
chinese_titles = [t for t in titles if not t.startswith('/')]
top10_titles = chinese_titles[:10]
with open ("movies.txt","w",encoding="utf-8") as f:
    for idx,titles in enumerate(top10_titles,1):
        f.write(f"{idx}. {title}\n")
rating_pattern = r'<span class="rating_num"[^>]*>(\d+\.\d)</span>'
ratings = re.findall(rating_pattern, html)

quote_pattern = r'<span class="inq">([^<]+)</span>'
quotes = re.findall(quote_pattern, html)

print(f'{"排名":<4} {"电影名":<20} {"评分":<6} {"引言"}')
print('-' * 70)
for i in range(min(10, len(chinese_titles))):
    title = chinese_titles[i]
    rating = ratings[i] if i < len(ratings) else '无'
    quote = f'"{quotes[i]}"' if i < len(quotes) else '无'
    print(f'{i+1:<4} {title:<20} {rating:<6} {quote}')