爬取音乐排行榜，需要自补请求头

import time,json
import requests
from bs4 import BeautifulSoup

class Kugou(object):  #  定义一个类(Class)，类就是一个模板，模板里可以包含多个函数。
 def __init__(self):   self.header = { }   #  初始化函数，用来定义创建新文件的状态
 def getInfo(self, url):
   html = requests.get(url, headers=self.header)
   soup = BeautifulSoup(html.text, 'html.parser')
   ranks = soup.select('.pc_temp_num')
   titles = soup.select('.pc_temp_songlist > ul > li > a')  # 层层标签查找
   times = soup.select('.pc_temp_time')
   for rank, title, songTime in zip(ranks, titles, times):
     data = {# rank 全打印就是带HTML标签的
                'rank': rank.get_text().strip(),
                'title': title.get_text().split('-')[1].strip(),
                'singer': title.get_text().split('-')[0].strip(),
                'songTime': songTime.get_text().strip()  }
     s = str(data)
     print('rank:%2s\t' % data['rank'], 'title:%2s\t' % data['title'],
           'singer:%2s\t' %data['singer'], 'songTime:%2s\t' % data['songTime'])
     with open('歌曲排行版.txt', 'a', encoding='utf8') as f:
            f.writelines(s + '\n')   #每写一条，换行
            
if __name__ == '__main__':  #当模块被直接运行时，以下代码块将被运行。
  urls = [ 'http://www.kugou.com/yy/rank/home/{}-8888.html'.format(str(i)) for i in range(10) ]
  kugou = Kugou()
  for url in urls:
       kugou.getInfo(url)
       time.sleep(1)  #函数推迟调用1秒运行，目的是让执行的过程能看清楚