import requests
import re

# 准备保存的文件
f = open("豆瓣电影top250.csv", "w", encoding="utf-8")
suffix = True
suffixs = ""
while suffix:

    url = 'https://movie.douban.com/top250'+suffixs
    header = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36 Edg/108.0.1462.42"
    }
    request = requests.get(url, headers=header)
    PageSuros = request.text

    comple = re.compile(r'<div class="item">.*?<span class="title">(?P<name>.*?)</span>.*?<p class="">.*?导演:(?P<author>.*?);&nbsp',re.S)
    suffixstr = re.compile(r'<span class="next">.*?<link rel="next" href="(?P<suffix>.*?)"/>', re.S)
    # re.S 可以用正则里面的 ”.“ 匹配到换行符

    # if(request.status_code):
    date = comple.finditer(PageSuros)
    suffixstr = suffixstr.findall(PageSuros)

    # string 函数 strip() 作用： 去除字符串左右两边的空格
    for item in date:
        name = item.group("name")
        author = item.group("author")
        f.write(f"{name},{author}\n")
    if suffixstr[0]:
        suffixs = suffixstr[0]
        print("OK")
    else:
        suffix = False
        print("完成")