下面先给大家介绍下python获取酷狗音乐top500的下载地址 mp3格式，具体代码如下所示：
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
|
# -*- coding: utf-8 -*-
# @time : 2018/4/16
# @file : kugou_top500.py
# @software: pycharm
# @pyver : python 2.7
import requests,json
headers={
'useragent' : 'mozilla/5.0 (iphone; cpu iphone os 5_0 like mac os x) applewebkit/534.46 (khtml, like gecko) version/5.1 mobile/9a334 safari/7534.48.3',
'referer' : 'http://m.kugou.com/rank/info/8888',
'cookie' : 'um_distinctid=161d629254c6fd-0b48b34076df63-6b1b1279-1fa400-161d629255b64c; kg_mid=cb9402e79b3c2b7d4fc13cbc85423190; hm_lvt_aedee6983d4cfc62f509129360d6bb3d=1523818922; hm_lpvt_aedee6983d4cfc62f509129360d6bb3d=1523819865; hm_lvt_c0eb0e71efad9184bda4158ff5385e91=1523819798; hm_lpvt_c0eb0e71efad9184bda4158ff5385e91=1523820047; musicwo17=kugou'
}
def get_songs(url):
res=requests.get(url,headers=headers)
return res.text
def get_song_download_url(url):
res=requests.get(url,headers=headers)
res_tmp_list = json.loads(res.text)
return res_tmp_list['data']['play_url']
def get_song_page_data(url):
song_json = json.loads(get_songs(url))
song_list_json = song_json['data']['info']
total = []
for i in range(len(song_list_json)):
song_download_url = "http://www.kugou.com/yy/index.php?r=play/getdata&hash=%s&album_id=%s&_=1523819864065" % (song_list_json[i]['hash'], song_list_json[i]['album_id'])
song_data_dict = {'downloadurl':get_song_download_url(song_download_url),'filename':song_list_json[i]['filename']}
total.append(song_data_dict)
return total
for i in range(1,18):
url='http://mobilecdngz.kugou.com/api/v3/rank/song?rankid=8888&ranktype=2&page=%s&pagesize=30&volid=&plat=2&version=8955&area_code=1' % i
page_list_data = get_song_page_data(url)
for j in range(len(page_list_data)):
print "%s %s" % (page_list_data[j]['filename'],page_list_data[j]['downloadurl'])
|
效果
下面看下python--爬取酷狗top500的数据
你是不是也遇到不能完整爬取top500的数据，因为规律只在前几页有用，后面有小改动，所以中间跳转了，不是完整的top500。我换了个方向，爬取飙升榜100首（上面代码）。
希望酷狗给大家个机会哈，毕竟才100首影响不了多大。
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
|
from bs4 import beautifulsoup
import requests
import time
headers={
'user-agent':'mozilla/5.0 (windows nt 6.1;wow64) applewebkit/537.36 (khtml, like gecko) chrome/65.0.3298.4 safari/537.36'
}
def get_info(url):
wb_data = requests.get(url,headers=headers)
soup = beautifulsoup(wb_data.text,'lxml')
ranks = soup.select('span.pc_temp_num')
titles = soup.select('div.pc_temp_songlist > ul > li > a')
times = soup.select('span.pc_temp_tips_r > span')
for rank,title,time in zip(ranks,titles,times):
data= {
'rank':rank.get_text().strip(),
'siger':title.get_text().split('-')[0],
'song':title.get_text().split('-')[1],
'time':time.get_text().strip()
}
print(data)
#酷狗飙升榜100首
if __name__ == '__main__':
urls = ['http://www.kugou.com/yy/rank/home/{}-6666.html?from=rank/'.format(str(i)) for i in
range(1,6)]
for url in urls:
get_info(url)
time.sleep(2)
|
总结
以上所述是小编给大家介绍的python获取酷狗音乐top500的下载地址 mp3格，希望对大家有所帮助，如果大家有任何疑问请给我留言，小编会及时回复大家的。在此也非常感谢大家对服务器之家网站的支持！
原文链接：https://blog.csdn.net/meinaozi/article/details/79955652