import requests
import re
import csv
import json
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
}
movie_list = []
for page in range(0, 250, 25):
    url = f"https://movie.douban.com/top250?start={page}&filter="
    response = requests.get(url, headers=headers)
    html = response.text
    pattern = re.compile(
        r'<em class="">(\d+)</em>.*?<span class="title">([^<]+)</span>.*?<span class="other">.*?/ (.*?)</span>.*?<span class="rating_num" property="v:average">(\d+\.\d+)</span>.*?<span>(\d+)人评价</span>',
        re.S
    )
    results = pattern.findall(html)
    for res in results:
        rank = res[0]  
        title = res[1]  
        en_title = res[2].strip()
        rating = res[3]  
        vote = res[4]  
        movie_dict = {
            "排名": rank,
            "电影名": title,
            "英文名": en_title,
            "评分": rating,
            "评价人数": vote
        }
        movie_list.append(movie_dict)
with open("movies.txt", "w", encoding="utf-8") as f:
    for movie in movie_list:
        f.write(f"{movie['排名']}. {movie['电影名']} 评分：{movie['评分']} 评价人数：{movie['评价人数']}\n")
print("✅ movies.txt 保存成功（仅电影名+评分+评价人数）")
with open("movies.csv", "w", encoding="utf-8-sig", newline="") as f:
    writer = csv.DictWriter(f, fieldnames=["排名", "电影名", "英文名", "评分", "评价人数"])
    writer.writeheader() 
    writer.writerows(movie_list)  
print("✅ movies.csv 保存成功（完整信息）")
with open("movies.json", "w", encoding="utf-8") as f:
    json.dump(movie_list, f, ensure_ascii=False, indent=2)
print("✅ movies.json 保存成功（完整信息）")
high_rating_movies = [m for m in movie_list if float(m["评分"]) > 9.5]
print("\n🎯 评分高于9.5的电影：")
for m in high_rating_movies:
    print(f"{m['排名']}. {m['电影名']} 评分：{m['评分']} 评价人数：{m['评价人数']}")
with open("high_rating_movies.csv", "w", encoding="utf-8-sig", newline="") as f:
    writer = csv.DictWriter(f, fieldnames=["排名", "电影名", "英文名", "评分", "评价人数"])
    writer.writeheader()
    writer.writerows(high_rating_movies)
print("\n✅ high_rating_movies.csv 保存成功（评分>9.5的电影）")