python爬取酷狗音乐

url:https://www.kugou.com/yy/html/rank.html

我们随便访问一个歌曲可以看到url有个hash

https://www.kugou.com/song/#hash=AC9D859362CABB2092AEAA39A072606A&album_id=39211957

但是这个hash是可以得到的

import re
import requests
import json

headers = {
    'cookie': 'kg_mid=7a7f50715e7cbc43187cb14650a074d7; ACK_SERVER_10015=%7B%22list%22%3A%5B%5B%22gzlogin-user.kugou.com%22%5D%5D%7D; ACK_SERVER_10016=%7B%22list%22%3A%5B%5B%22gzreg-user.kugou.com%22%5D%5D%7D; ACK_SERVER_10017=%7B%22list%22%3A%5B%5B%22gzverifycode.service.kugou.com%22%5D%5D%7D; kg_dfid=2lP8Vp1RHLHj0wmucn0XlXFL; kg_dfid_collect=d41d8cd98f00b204e9800998ecf8427e; Hm_lvt_aedee6983d4cfc62f509129360d6bb3d=1600062203; kg_mid_temp=7a7f50715e7cbc43187cb14650a074d7; KuGooRandom=66401600062231494; Hm_lpvt_aedee6983d4cfc62f509129360d6bb3d=1600062409',
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36'
}
hash_com = re.compile('"Hash":"(.*?)"',re.I|re.S)
html = requests.get('https://www.kugou.com/yy/html/rank.html',headers=headers)
hash_result = hash_com.findall(html.text)
print(hash_result)

然后我们刷新歌曲这里得网页可以看到都是在这里

发送都是这个url

Request URL: https://wwwapi.kugou.com/yy/index.php?r=play/getdata&callback=jQuery19108001866002482712_1600062977462&hash=AC9D859362CABB2092AEAA39A072606A&album_id=39211957&dfid=2lP8Vp1RHLHj0wmucn0XlXFL&mid=7a7f50715e7cbc43187cb14650a074d7&platid=4&_=1600062977464

然后我敲门只留hash前面看看能不能访问

https://wwwapi.kugou.com/yy/index.php?r=play/getdata&callback=jQuery19108001866002482712_1600062977462&hash=AC9D859362CABB2092AEAA39A072606A

访问是可以的

然后我们再拼接一下

import re
import requests
import json

headers = {
    'cookie': 'kg_mid=7a7f50715e7cbc43187cb14650a074d7; ACK_SERVER_10015=%7B%22list%22%3A%5B%5B%22gzlogin-user.kugou.com%22%5D%5D%7D; ACK_SERVER_10016=%7B%22list%22%3A%5B%5B%22gzreg-user.kugou.com%22%5D%5D%7D; ACK_SERVER_10017=%7B%22list%22%3A%5B%5B%22gzverifycode.service.kugou.com%22%5D%5D%7D; kg_dfid=2lP8Vp1RHLHj0wmucn0XlXFL; kg_dfid_collect=d41d8cd98f00b204e9800998ecf8427e; Hm_lvt_aedee6983d4cfc62f509129360d6bb3d=1600062203; kg_mid_temp=7a7f50715e7cbc43187cb14650a074d7; KuGooRandom=66401600062231494; Hm_lpvt_aedee6983d4cfc62f509129360d6bb3d=1600062409',
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36'
}
hash_com = re.compile('"Hash":"(.*?)"',re.I|re.S)
html = requests.get('https://www.kugou.com/yy/html/rank.html',headers=headers)
hash_result = hash_com.findall(html.text)
# print(hash_result)
base_url = 'https://wwwapi.kugou.com/yy/index.php?r=play/getdata&callback=jQuery19108001866002482712_1600062977462&hash='
for hash in hash_result:
    url = base_url+hash
    # print(url)

然后再获取url

jsondata = requests.get(url,headers=headers)
    print(jsondata.text)

输出为

我们来.json()看看

print(jsondata.json())

但是返回错误了，所以不是一个合法json，来转换一下，通过find来找到合法的json头部和尾部

他的合法开头再这里

结尾就是 .mp3"}}

start = jsondata.text.find('{"status":1')
end = jsondata.text.find('.mp3"}}')+len('.mp3"}}')
print(jsondata.text[start:end])

这里加上len就是因为[]是左闭右合的，返回

全部代码

import re
import requests
import json
import os

headers = {
    'cookie': 'kg_mid=7a7f50715e7cbc43187cb14650a074d7; ACK_SERVER_10015=%7B%22list%22%3A%5B%5B%22gzlogin-user.kugou.com%22%5D%5D%7D; ACK_SERVER_10016=%7B%22list%22%3A%5B%5B%22gzreg-user.kugou.com%22%5D%5D%7D; ACK_SERVER_10017=%7B%22list%22%3A%5B%5B%22gzverifycode.service.kugou.com%22%5D%5D%7D; kg_dfid=2lP8Vp1RHLHj0wmucn0XlXFL; kg_dfid_collect=d41d8cd98f00b204e9800998ecf8427e; Hm_lvt_aedee6983d4cfc62f509129360d6bb3d=1600062203; kg_mid_temp=7a7f50715e7cbc43187cb14650a074d7; KuGooRandom=66401600062231494; Hm_lpvt_aedee6983d4cfc62f509129360d6bb3d=1600062409',
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36'
}
hash_com = re.compile('"Hash":"(.*?)"',re.I|re.S)
html = requests.get('https://www.kugou.com/yy/html/rank.html',headers=headers)
hash_result = hash_com.findall(html.text)
# print(hash_result)
base_url = 'https://wwwapi.kugou.com/yy/index.php?r=play/getdata&callback=jQuery19108001866002482712_1600062977462&hash='
for hash in hash_result:
    url = base_url+hash
    # print(url)
    jsondata = requests.get(url,headers=headers)
    start = jsondata.text.find('{"status":1')
    end = jsondata.text.find('.mp3"}}')+len('.mp3"}}')
    # print(jsondata.text[start:end])
    songurl = json.loads(jsondata.text[start:end])['data']['play_url']
    title = json.loads(jsondata.text[start:end])['data']['audio_name']

    if not os.path.exists('酷狗'):
        os.mkdir('酷狗')

    with open('酷狗/{}.mp3'.format(title),'wb')as f:
        f.write(requests.get(songurl).content)