python爬虫之：抓取网易云音乐某首歌曲的热门评论
首先，以这首歌为例：
python 代码如下：
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
33
34
35
36
37
38
| import requests
import json
# import BeautifulSoup from bs4
def get_hotComments(res):
comments_json = json.loads(res.text)
hot_comments = comments_json['hotComments']
with open('/Users/yao/www/python/evol-love.txt', 'w', encoding='utf-8') as file:
for each in hot_comments:
file.write(each['user']['nickname'] + ': \n\n')
file.write(each['content'] + '\n')
# file.write(each['likedCount'] + '\n')
# file.write(each['time'] + '\n')
file.write('--❤-----------❤--\n')
def get_comments(url):
song_id = url.split('=')[1]
headers = {
'user-agent': 'curl https://bootstrap.pypa.io/get-pip.py | python3',
'referer': 'https://music.163.com/song?id=1381290746'}
params = '15S1vG2hDWPcsAeXpjYIcwuRpK7nwElk3Cdy6c/3aJdbH5aBub7nWrYPxZQaMzKrhFSUo1n4nGHkCbaZAl77WSFPMYjjv6sU5Qipnqnn4QjXRH6eN1w/PcauCCUo4NDgaw/Uudad5J/zpgDY2005gC3UF+s2s/ND5tjXTU0SeDkiBg47A6b6VqhK/7E/hS9++nlvAC7QkkzCbsXZMp/jyBl5+KroeMcGAfFumxZ5pME='
encSecKey = '3f5dbdd0ec1f0a1501b88f6e04ce30ecf88192b4e3a92bd2dc1216f2ccc90898211e6347a2ab36d07f93793352ff6559fb927b7cbd337f5887d2af7b442e2dfb0b4abd83e85c6c3bb20fe2beef050db4c169531411f4e23caaa201f62609fcda4de694c8e9e759443fea2f7febf044bd9c4bcb2697519ca96dca676730059156'
data = {
'params': params,
'encSecKey': encSecKey
}
target_url = 'https://music.163.com/weapi/v1/resource/comments/R_SO_4_{}?csrf_token=55a6b8514346a9f676c8485978093b9f'.format(song_id)
res = requests.post(target_url, headers=headers, data=data)
# rawHTML = ''
# soup = BeautifulSoup(rawHTML)
# file_name_obj = soup.select_one('.f-ff2')
# file_name = file_name_obj.text
return res
def main():
url = input('please input song url:')
res = get_comments(url)
# title = get_title(url)
get_hotComments(res)
if __name__ == "__main__":
main()
|
得到的txt文件如下（如有需要可进一步分析）：
