'''''' ''' 一、请求url https://www.wandoujia.com/category/6001 二、请求方式 GET 三、请求头

User-Agent:

Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36

Cookie

''' #爬虫三部曲 #1.发送请求 import requests def get_page(url):     reponse = requests.get(url)     #print(reponse.text)     return reponse # 2.解析数据 ''' (.*?)
    
    
     (.*?) .*?
     (.*?) 
    
    
     
捕鱼大作战
     
    
      13.9万人安装  
      ・ 
      37.31MB
     
     
        捕鱼大作战，经典街机新体验  
     
    
   休闲益智   ''' import re def parse_index(html):     movie_list = re.findall('
.*?.*?(.*?)万人安装  ・ .*?MB',html,re.S)     return movie_list # 3.保存数据 def save_data(movie):     detail_url, app_name, download_num, app_size = movie     data = f'''                游戏名称：{app_name}                 详情页url：{detail_url}                 下载人数：{download_num}万人                 app大小：{app_size}MB                 \n                 \n             '''     print(data)     with open('wandoujia.txt','a',encoding='utf-8') as f:         f.write(data) if __name__ == '__main__':     #拼接所有主页         url=f'https://www.wandoujia.com/category/6001'         #1.往每个主页发送请求         index_res = get_page(url)         #2.解析主页获取电影信息         movie_list = parse_index(index_res.text)         for movie in movie_list:             #3.保存数据             #print(movie_list)             save_data(movie)