一个简单的Python案例,爬取酷狗TOP500歌曲,仅供学习参考
import requests
from bs4 import BeautifulSoup
import time
# 爬取酷狗TOP500歌曲
# 作者:本文博主
# 创建时间:2019-08-03
# 最后更新时间:2019-08-03
headers={"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"}
def get_info(url):
wb_data=requests.get(url,headers=headers)
soup=BeautifulSoup(wb_data.text,'lxml')
# ranks=soup.select('#rankWrap > div.pc_temp_songlist > ul > li > span.pc_temp_num > strong')
titles=soup.select('#rankWrap > div.pc_temp_songlist > ul > li > a')
times=soup.select('#rankWrap > div.pc_temp_songlist > ul > li > span.pc_temp_tips_r > span')
for title,time in zip(titles,times):
data={
'title':title.get_text().split('-&#