爬取内容目标
分析
1.歌曲名称(在class=“song-title”的span下的a标签内)
2.获取作者(class=“author_list” 的span 的title属性)
代码
import requests
from bs4 import BeautifulSoup
'''
1.目标网址 :http://music.taihe.com/top/dayhot
2.发送请求,获得响应
3.获取BeautifulSoup对象
'''
url="http://music.taihe.com/top/dayhot"
header={
"Accept-Language":"zh-CN,zh;q=0.8",
"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/47.0.2526.108 Safari/537.36 2345Explorer/8.1.0.14126"
}
html=requests.get(url,headers=header)
soup=BeautifulSoup(html.content,'lxml')
####获取歌名
alltitle=soup.select("span.song-title");
titlelist=[] #存放歌名
for t in alltitle:
titlelist.append(t.a.text)
print(len(titlelist)) ##100首歌这里 虽然一个页面显示50 其实他是将另外50个隐藏
##获取歌手名
allsinger=soup.select("span.author_list")
singerlist=[]
for t in allsinger:
singerlist.append(t.get("title"))
print(len(singerlist))
####结果输出
for i in range(0,len(singerlist)):
print(titlelist[i]+'-------'+singerlist[i])
结果