import re
import csv
import json
import requests
headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/130.0.0.0 Safari/537.36"
}
movie_list = []
for start in range(0, 250, 25):
    url = f"https://movie.douban.com/top250?start={start}"
    print(f"正在爬取：{url}")
    
    try:
        response = requests.get(url, headers=headers, timeout=10)
        response.raise_for_status()  
        html = response.text
        pattern = re.compile(
            r'<div class="item">.*?'
            r'<span class="title">(.*?)</span>.*?'  
            r'<span class="rating_num" property="v:average">(.*?)</span>.*?'  # 评分
            r'<span>(.*?)人评价</span>.*?'  
            r'<span class="inq">(.*?)</span>',  
            re.S
        )
        movies = pattern.findall(html)
        
        for movie in movies:
            name = movie[0].strip()  
            score = movie[1].strip()  
            comment_num = movie[2].strip()  
            comment = movie[3].strip()  

            movie_dict = {
                "电影名称": name,
                "评分": score,
                "评价人数": comment_num,
                "短评": comment
            }
            movie_list.append(movie_dict)

    except Exception as e:
        print(f"爬取失败：{e}")

with open("douban_top250.csv", "w", encoding="utf-8-sig", newline="") as f:
    fieldnames = ["电影名称", "评分", "评价人数", "短评"]
    writer = csv.DictWriter(f, fieldnames=fieldnames)
    writer.writeheader()  
    writer.writerows(movie_list) 

print("✅ CSV 文件已保存：douban_top250.csv")

with open("douban_top250.json", "w", encoding="utf-8") as f:
    json.dump(movie_list, f, ensure_ascii=False, indent=4)

print("✅ JSON 文件已保存：douban_top250.json")
print(f"\n🎉 爬取完成！共获取 {len(movie_list)} 部电影数据")