轉(zhuǎn)載：https://www.cnblogs.com/lsgcoder101/p/8228075.html
from bs4 import BeautifulSoup
import requests
import time
headers={
'User-Agent':'Mozilla/5.0 (Windows NT 6.1;WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3298.4 Safari/537.36'
}
def get_info(url):
wb_data = requests.get(url,headers=headers)
soup = BeautifulSoup(wb_data.text,'lxml')
ranks = soup.select('span.pc_temp_num')
titles = soup.select('div.pc_temp_songlist > ul > li > a')
times = soup.select('span.pc_temp_tips_r > span')
for rank,title,time in zip(ranks,titles,times):
data= {
'rank':rank.get_text().strip(),
'siger':title.get_text().split('-')[0],
'song':title.get_text().split('-')[1],
'time':time.get_text().strip()
}
print(data)
酷狗飆升榜100首
if name == 'main':
urls = ['http://www.kugou.com/yy/rank/home/{}-6666.html?from=rank/'.format(str(i)) for i in
range(1,6)]
for url in urls:
get_info(url)
time.sleep(2)
