import requests
import re
import os
from time import sleep

base_url = 'https://movie.douban.com/top250?start={}&filter='
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
}

p = re.compile(
    r'<div class="item">.*?'
    r'<span class="title">(.*?)</span>.*?'
    r'<span class="rating_num" property="v:average">(.*?)</span>.*?'
    r'<span>(.*?人评价)</span>.*?'
    r'<span class="inq">(.*?)</span>',
    re.S
)

m = []
for page in range(10):
    u = base_url.format(page*25)
    try:
        r = requests.get(u, headers=headers, timeout=10)
        r.encoding = 'utf-8'
        items = p.findall(r.text)
        for i in items:
            t = i[0].split('/')[0].strip()
            m.append([t, i[1], i[2], i[3]])
    except:
        pass
    sleep(1)

dp = os.path.join(os.path.expanduser("~"), "Desktop")
fp = os.path.join(dp, "top250.txt")

with open(fp, 'w', encoding='utf-8') as f:
    for i, v in enumerate(m, 1):
        f.write(f'{i}. {v[0]}\n')
        f.write(f'{v[1]}\n')
        f.write(f'{v[2]}\n')
        f.write(f'{v[3]}\n\n')