import re
import requests

# 爬蟲三部曲：
# 1.获取请求
def get_data(url, headers):
  response = requests.get(url, headers=headers)
  # 如果爬取的是html文本就是用.text方法获取文本数据，如果爬取的是音视频就用.content方法获取二进制流数据
  # print(response.text)  # 获取相应文本，比如html代码
  return response.text

# 2.解析数据
def parser_data(text):
  # re.findall("正则表达式", "过滤的文本", re.S) # 匹配模式：re.S 全局模式
  data = re.findall(
    '<div class="item">.*"(.*" rel="external nofollow" >.*"title">(.*"rating_num" property="v:average">(.*"豆瓣TOP250.txt", "a", encoding="utf-8") as f:
    for i in res_list_iter:
      move_page, move_title, move_score, move_evaluation = i
      # print(move_page, move_title, move_score, move_evaluation)
      str1 = f"电影名字：《{move_title}》  电影评分：{move_score}  电影评价：{move_evaluation}  电影详情页：{move_page}\n"
      f.write(str1)

# 使用请求头请求数据
headers = {
  'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102   Safari/537.36'
}
n = 0
# 获取10个链接
for i in range(10):
  url = f"https://movie.douban.com/top250"
  n += 25
  text = get_data(url, headers)
  res_list_iter = parser_data(text)
  save_data(res_list_iter)