Python爬取酷狗飙升榜前十首（100）首，写入CSV文件

 1 import requests
 2 from bs4 import BeautifulSoup
 3 import time
 4 
 5 # 请求头
 6 headers = {
 7     'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
 8 }
 9 
10 def requests_list(url):
11     wb_data = requests.get(url,headers=headers)
12     soup = BeautifulSoup(wb_data.text,'lxml')
13     nums = soup.select('span.pc_temp_num')#排名
14     titles = soup.select('div.pc_temp_songlist > ul > li > a')#标题
15     times = soup.select('span.pc_temp_tips_r > span')#歌曲时间
16     # 定义一个n方便判断是否是只取飙升榜的前十首歌
17     n=0
18     # 将每次循环爬取出的数据放入空字典中
19     data=[]
20     data.append(['num','singer','song','time'])
21     for num,title,time in zip(nums,titles,times):
22         data.append([
23             num.get_text().strip(),
24             title.get_text().split('-')[0],#用"-"分割歌手和歌名
25             title.get_text().split('-')[1],
26             time.get_text().strip()
27         ])
28         n=n+1
29         if n>=10:
30             break
31     print(data)
32     return data
33 
34 def save_to_csv(data):
35     # 打开kugou.csv文件，将爬取的数据写入进去
36     fr=open("kugou.csv","w")
37     for s in data:
38         fr.write(",".join(s)+"
")
39     
40 if __name__ == '__main__':
41     urls = "https://www.kugou.com/yy/rank/home/1-6666.html?from=rank"
42     save_to_csv(requests_list(urls))