Python百度音乐小爬虫

 1 #!/usr/bin/env python
 2 # _*_ coding:utf-8 _*_
 3 import requests
 4 import re
 5 data = {
 6     \'key\':\'朋友\'#搜索的歌曲关键词
 7 }
 8 #百度音乐搜索url
 9 search_url = \'http://music.baidu.com/search\'
10 #发送http请求
11 search_response= requests.get(search_url, params=data)
12 #设置显示编码格式<head><meta encoding=""/>
13 search_response.encoding = \'utf-8\'
14 search_response_html = search_response.text
15 #获取歌曲id保存为字典格式，正则表达式
16 song_ids = re.findall(r\'&quot;sid&quot;:(\d+),\',search_response_html)
17 #print(song_ids)
18 song_api = \'http://play.baidu.com/data/music/songlink\'
19 data = {#传参数用字典
20     \'songIds\':\',\'.join(song_ids),#把列表里面的元素用逗号拼接起来
21     \'hq\':0,
22     \'type\':\'mp3\',
23     \'pt\':0,
24     \'flag\':1,
25     \'s2p\':650,
26     \'prerate\':128,
27     \'bwt\':266,
28     \'dur\':231000,
29     \'bat\':266,
30     \'bp\':100,
31     \'pos\':65833,
32     \'auto\':0
33 }
34 #根据sid获取下载地址
35 song_response = requests.post(song_api,data=data)
36 print(song_response)
37 song_info = song_response.json()#将返回的歌曲转成字典
38 print(song_info)
39 song_info = song_info[\'data\'][\'songList\']
40 print(song_info)
41 for song in song_info:#遍历下载
42     song_name = song[\'songName\']
43     with open(\'d:/T/%s.mp3\' % song_name, \'wb\') as f:
44         print(song[\'songLink\'])
45         response = requests.get(song[\'songLink\'])
46         f.write(response.content)
47 #print(song_ids)