import requests
from lxml import etree
import csv
import time
import random

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(10):
    start = page * 25
    url = f'https://movie.douban.com/top250?start={start}&filter='
    print(f'正在爬取第 {page+1} 页...')

    time.sleep(random.uniform(0.5, 1.5))

    try:
        response = requests.get(url, headers=headers, timeout=10)
        tree = etree.HTML(response.text)
        items = tree.xpath('//div[@class="item"]')

        for item in items:
            rank = item.xpath('.//em/text()')[0]
            title = item.xpath('.//span[@class="title"][1]/text()')[0]
            score = item.xpath('.//span[@class="rating_num"]/text()')[0]
            quote = item.xpath('.//span[@class="inq"]/text()')
            quote = quote[0] if quote else "无"
            info = item.xpath('.//div[@class="bd"]/p[1]/text()')[0].strip()

            movie = {
                "排名": rank,
                "电影名": title,
                "评分": score,
                "引言": quote,
                "主创信息": info
            }
            movie_list.append(movie)

    except Exception as e:
        print(f"第 {page+1} 页爬取失败：{e}")

with open("douban_top250_xpath.csv", "w", encoding="utf-8-sig", newline="") as f:
    writer = csv.DictWriter(f, fieldnames=["排名", "电影名", "评分", "引言", "主创信息"])
    writer.writeheader()
    writer.writerows(movie_list)

print(f"? 爬取完成！共 {len(movie_list)} 条数据，已保存到 douban_top250_xpath.csv")