import requests
from bs4 import BeautifulSoup
import time
import json  # 补上json库

# 请求头，模拟浏览器，防止被拦截
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"
}

# 存储所有电影数据
movie_list = []
# 只爬前两页，每页25条，合计50条
for page in range(0, 50, 25):
    url = f"https://movie.douban.com/top250?start={page}"
    res = requests.get(url, headers=headers)
    res.encoding = "utf-8"
    soup = BeautifulSoup(res.text, "html.parser")
    items = soup.find_all("div", class_="item")

    for item in items:
        # 电影名称
        title = item.find("span", class_="title").get_text(strip=True)

        # 主演信息
        info_text = item.find("div", class_="bd").p.get_text(strip=True)
        # 截取导演演员部分
        actor_info = info_text.split("\n")[0]

        # 短评，部分电影无短评做容错
        quote_tag = item.find("span", class_="inq")
        short_comment = quote_tag.get_text(strip=True) if quote_tag else "无短评"

        data = {
            "电影名": title,
            "主创主演": actor_info,
            "经典短评": short_comment
        }
        movie_list.append(data)
        print(data)
    # 每页延时1秒，降低访问频率，避免封IP
    time.sleep(1)

# 打印总数量
print(f"\n一共抓取{len(movie_list)}部电影")

with open("movies.json","w",encoding="utf-8") as f:
    json.dump(movie_list, f, ensure_ascii=False, indent=2)
print("数据已保存到 movies.json 文件！")