import time import requests from bs4 import BeautifulSoup headers={ 'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36' } def get_info(url): req=requests.get(url=url,headers=headers) soup=BeautifulSoup(req.text,'lxml') ranks=soup.select('.pc_temp_num') titles=soup.select('.pc_temp_songlist > ul > li > a') times=soup.select('.pc_temp_time') for rank,title,time in zip(ranks,titles,times): data={ 'rank':rank.get_text().strip(), 'title':title.get_text().split('-')[1].strip(), 'signer': title.get_text().split('-')[0].strip(), '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(1,36)] for url in urls: get_info(url) time.sleep(1)
文章来源: Python爬取酷狗TOP100