from bs4 import BeautifulSoup
import requests
import re
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 Safari/537.36'
}
url='https://songsearch.kugou.com/song_search_v2?&page=1&pagesize=30&userid=-1&clientver=&platform=WebFilter&tag=em&filter=2&iscorrection=1&privilege_filter=0&_=1555124510574'
#想要爬取別的網頁直接修改這個json數據地址就行
r=requests.get(url,headers=headers)
soup=BeautifulSoup(r.text,'lxml')
title_list=soup.select('.pc_temp_songlist ul li')
hash=re.findall(r',"FileHash":"(.*?)"',r.text)
hash1=re.findall(r',"FileName":"(.*?)"',r.text)
#直接用正則匹配隱藏的數據
print(hash)
print(hash1)
q=0
for url in hash:
url_a=f'https://wwwapi.kugou.com/yy/index.php?r=play/getdata&callback=jQuery1910212680783679835_1555073815772&hash={url}&album_id=18784389'
#這個URL不用修改的
c=requests.get(url_a,headers=headers)
a=c.text[40:-3]
b=re.findall('"play_url":"(.*)","authors":',a)[0]
b1=re.sub(r"\\",'',b)
f = requests.get(b1)
with open(hash1[q]+'.mp3','wb')as d:
d.write(f.content)
print(hash1[q])
q+=1