#encoding=utf-8
import requests
from bs4 import BeautifulSoup, BeautifulStoneSoup
import time
header={'User-Agent':'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'}
#爬取酷狗音乐
def get_info(url):
data=requests.get(url,headers=header)
soup=BeautifulSoup(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(),
'singer':title.get_text().split("-")[0],
'song':title.get_text().split("-")[1],
'time':time.get_text().strip()
}
print(data)
if __name__=='__main__':
urls=['http://www.kugou.com/yy/rank/home/{}-8888.html'.format(str(i) for i in range(1,30))]
for url in urls:
get_info(url)
time.sleep(1)
酷狗音乐爬虫
猜你喜欢
转载自blog.csdn.net/qq_27584277/article/details/81347003
今日推荐
周排行