唱吧音乐爬取

唱吧音乐爬取

#导入框架
import requests
import re

#确定url
url = 'http://changba.com/u/461549830'
#请求
def changba(url):
	res = requests.get(url)
	if res.status_code == 200:
		res_html = res.text
		# print(res.text)
		
		#匹配歌曲链接
		reg1 = '<a href="(/s/.{22})" style="color:#999;display:block;" target="_blank">' 									
		media = re.findall(reg1, res_html)
		# print(media)
		media_mid = []
		for i in range(len(media)):
			media_mid.append('http://changba.com'+media[i])
		print(media_mid)

		#匹配歌曲名称
		reg2 = '^style="color:#999;display:block;" target="_blank">\n\t*([\u4e00-\u9fa5]{1,20})\t*<div class="userPage-work-detail">$'
		reg2 = '(.*)<div class="userPage-work-detail">'
		name = re.findall(reg2, res_html)
		song_name = []
		for i in range(len(name)):
			song_name.append(name[i].strip())
		print(song_name)

		reg3 = 'http://\w{4,20}.changba.com/\d{10}.mp3'
		for i in range(len(media_mid)):
			result = requests.get(media_mid[i]).text
			MP3_html = re.findall(reg3,result)
			print(MP3_html)
			if(MP3_html):
				MP3 = requests.get(MP3_html[0])
				if MP3.status_code ==200:
					with open(song_name[i]+'.mp3','wb') as f:
						f.write(MP3.content)
				else:
					continue
changba(url)