1.作业一
# ● 目标网站：https://www.kugou.com/yy/html/rank.html
# ● 爬取要求：
# ○ 1、获取到榜单页面的源码
# ○ 2、用正则解析数据，获取到该页面所有歌曲的名字(包括歌手)和页面链接
# ○ 3、把数据保存到csv
import re
import requests
url = ‘https://www.kugou.com/yy/html/rank.html‘
headers = {
‘user-agent’: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36’,
‘cookie’: ‘kg_mid=6207dac002e7ae6a40352a75196d5836; kg_dfid=4FIvTh2Rj5qU01t3TD3WjAZS; kg_dfid_collect=d41d8cd98f00b204e9800998ecf8427e; ACK_SERVER_10015=%7B%22list%22%3A%5B%5B%22bjlogin-user.kugou.com%22%5D%5D%7D; ACK_SERVER_10016=%7B%22list%22%3A%5B%5B%22bjreg-user.kugou.com%22%5D%5D%7D; ACK_SERVER_10017=%7B%22list%22%3A%5B%5B%22bjverifycode.service.kugou.com%22%5D%5D%7D; Hm_lvt_aedee6983d4cfc62f509129360d6bb3d=1645530652; Hm_lpvt_aedee6983d4cfc62f509129360d6bb3d=1645530652’,

}
response = requests.get(url,headers=headers)
response2 = response.content.decode(‘utf-8’)
response3 = response2.encode(‘utf-8’).decode(“unicode_escape”)
# print(response3)
a = response3.split(‘global.features’)[1]
print(a)
# 做到这里不会了。。。