网易云音乐python爬虫搜索接口，评论接口，歌词接口
网易云搜索歌曲，歌曲评论抓取，歌词抓取，仅供参考。
网易云音乐接口分析
网易云接口都是同一套加密代码，不同得API对应不同的请求参数，本文以搜索歌曲API为例子详细介绍加密代码，js AES 加密
搜索歌曲接口解析
1.搜索歌曲 《在一起》
2.搜索歌曲接口
2.1 第一步找到搜索歌曲接口
2.2 第二步 通过关键词全局搜索 params 和 encSecKey，找到对应的代码文件
2.3 第三步 通过断点调试定位具体加密代码位置
2.4 分析 代码块
var bVV0x = window.asrsea(JSON.stringify(i3x), bqM3x(["流泪", "强"]), bqM3x(TM7F.md), bqM3x(["爱心", "女孩", "惊恐", "大笑"]));
其中
asrsea( )未知函数
bqM3x( ) 未知函数
TM7F.md 未知参数
i3x：未知参数
2.4.1 向上分析代码 文件 13059行找到 bqM3x函数 以及TM7F
var bqM3x = function(cyu6o) {
var m3x = [];
k3x.bf4j(cyu6o, function(cyt6n) {
m3x.push(TM7F.emj[cyt6n])
});
return m3x.join("")
};
TM7F.md = ["色", "流感", "这边", "弱", "嘴唇", "亲", "开心", "呲牙", "憨笑", "猫", "皱眉", "幽灵", "蛋糕", "发怒", "大哭", "兔子", "星星", "钟情", "牵手", "公鸡", "爱意", "禁止", "狗", "亲亲", "叉", "礼物", "晕", "呆", "生病", "钻石", "拜", "怒", "示爱", "汗", "小鸡", "痛苦", "撇嘴", "惶恐", "口罩", "吐舌", "心碎", "生气", "可爱", "鬼脸", "跳舞", "男孩", "奸笑", "猪", "圈", "便便", "外星", "圣诞"]
TM7F.emj = {
"色": "00e0b",
"流感": "509f6",
"这边": "259df",
"弱": "8642d",
"嘴唇": "bc356",
"亲": "62901",
"开心": "477df",
"呲牙": "22677",
"憨笑": "ec152",
"猫": "b5ff6",
"皱眉": "8ace6",
"幽灵": "15bb7",
"蛋糕": "b7251",
"发怒": "52b3a",
"大哭": "b17a8",
"兔子": "76aea",
"星星": "8a5aa",
"钟情": "76d2e",
"牵手": "41762",
"公鸡": "9ec4e",
"爱意": "e341f",
"禁止": "56135",
"狗": "fccf6",
"亲亲": "95280",
"叉": "104e0",
"礼物": "312ec",
"晕": "bda92",
"呆": "557c9",
"生病": "38701",
"钻石": "14af6",
"拜": "c9d05",
"怒": "c4f7f",
"示爱": "0c368",
"汗": "5b7a4",
"小鸡": "6bee2",
"痛苦": "55932",
"撇嘴": "575cc",
"惶恐": "e10b4",
"口罩": "24d81",
"吐舌": "3cfe4",
"心碎": "875d3",
"生气": "e8204",
"可爱": "7b97d",
"鬼脸": "def52",
"跳舞": "741d5",
"男孩": "46b8e",
"奸笑": "289dc",
"猪": "6935b",
"圈": "3ece0",
"便便": "462db",
"外星": "0a22b",
"圣诞": "8e7",
"流泪": "01000",
"强": "1",
"爱心": "0CoJU",
"女孩": "m6Qyw",
"惊恐": "8W8ju",
"大笑": "d"
};
看都不想看。。。。。。 三个参数都是固定的 在当前环境下 执行语句获得结果
bqM3x([“流泪”, “强”])
**010001**
bqM3x(TM7F.md)
"00e0b509f6259df8642dbc35662901477df22677ec152b5ff68ace615bb7b725152b3ab17a876aea8a5aa76d2e417629ec4ee341f56135fccf695280104e0312ecbda92557c93870114af6c9d05c4f7f0c3685b7a46bee255932575cce10b424d813cfe4875d3e82047b97ddef52741d546b8e289dc6935b3ece0462db0a22b8e7"
bqM3x([“爱心”, “女孩”, “惊恐”, “大笑”])
"0CoJUm6Qyw8W8jud"
2.4.2 分析 i3x参数 和 asrsea函数
其中的 e，f，g参数均已知 （可以搭建后台API直接掉用 其中的CryptoJS 自行倒入）
function a(a) {
var d, e, b = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789", c = "";
for (d = 0; a > d; d += 1)
e = Math.random() * b.length,
e = Math.floor(e),
c += b.charAt(e);
return c
}
function b(a, b) {
var c = CryptoJS.enc.Utf8.parse(b)
, d = CryptoJS.enc.Utf8.parse("0102030405060708")
, e = CryptoJS.enc.Utf8.parse(a)
, f = CryptoJS.AES.encrypt(e, c, {
iv: d,
mode: CryptoJS.mode.CBC
});
return f.toString()
}
function c(a, b, c) {
var d, e;
return setMaxDigits(131),
d = new RSAKeyPair(b,"",c),
e = encryptedString(d, a)
}
function d(d, e, f, g) {
var h = {}
, i = a(16);
return h.encText = b(d, g),
h.encText = b(h.encText, i),
h.encSecKey = c(i, e, f),
h
}
function e(a, b, d, e) {
var f = {};
return f.encText = c(a + e, b, d),
f
}
2.4.3 python代码复写js （这里开始就是很烦的了 不想搭建后台，直接调用js代码，请求CryptoJS文件会有问题，没办法只能用python代码模拟CryptoJS执行加密）
python 有第三方库 Crypto 可执行AES 加密（有坑）
直接pip install Crypto （会报错 找不到此model）
正确下载
pip install pycryptodome
·使用第三方库 Crypto执行加密操作网上很多坑（自己的见解也很浅）下面的是成功可执行代码（注意js里面加密使用了两次，每次不同的加密参数）具体详细使用见文末github地址
# js代码中b函数的复写
def crypt_js_complex_base(text,key):
BS = AES.block_size
pad = lambda s: s + (BS - len(s) % BS) * chr(BS - len(s) % BS).encode('utf-8')
unpad = lambda s: s[0:-s[-1]]
key = bytes(key,encoding="utf-8")
text = text.encode("utf-8")
IV = b'0102030405060708' # 默认参数
cipher = AES.new(key, mode=AES.MODE_CBC, IV=IV)
# cipher2 = AES.new(key, mode=AES.MODE_CBC, IV=IV) # 加密和解密，cipher对象只能用一次
# print(text)
encrypted = pad(text)
# print(encrypted)
encrypted = cipher.encrypt(encrypted)
# print(encrypted)
encrypted = base64.b64encode(encrypted).decode("utf-8")
# print("第一次加密结果", encrypted)
return encrypted
2.4.4 下面直接贴可执行python代码 我知道大家都懒，
使用方法见文末github地址
# -*- coding:utf-8 -*-
# 享受雷霆感受雨露
# author xyy,time:2020/6/28
from fake_useragent import UserAgent
from Crypto.Cipher import AES
import base64
import requests, pprint,json
class WangYiYun():
def __init__(self):
self.params = ""
self._i = "l6Brr86UeZ6C3Bsw" # 默认使用此字符串
# 使用默认_i 配套的encSecKey
self.encSecKey = "7ca9b5ba8b13044f47ed74c388df912ac84758122acbedc64111f2ac83232b01d3ce16f7195a39c7e064b4c0240b5c1d52624dc13c22ec820d76dfe32db43e496aeacced5be3ca9108c78a85bb389f1edf8d8c9fced02024ba9490401b4ce062cc50764d0a24294e07bb229271391b5a3640e924ee1ed15435dc6e288f1fa873"
self.headers = {
'authority': 'music.163.com',
'user-agent': UserAgent().random,
'content-type': 'application/x-www-form-urlencoded',
'accept': '*/*',
'origin': 'https://music.163.com',
'sec-fetch-site': 'same-origin',
'sec-fetch-mode': 'cors',
'sec-fetch-dest': 'empty',
'referer': 'https://music.163.com/song?id=1426301364',
'accept-language': 'zh-CN,zh;q=0.9',
'cookie': '_iuqxldmzr_=32; _ntes_nnid=5f8ee04e745645d13d3f711c76769afe,1593048942478; _ntes_nuid=5f8ee04e745645d13d3f711c76769afe; WM_TID=XqvK2%2FtWaSBEUBRBEEN7XejGE%2FL0h6Vq; WM_NI=iN6dugAs39cIm2K2R9ox28GszTm5oRjcvJCcyIuaI1dccEVSjaHEwhc8FuERfkh3s%2FFP0zniMA5P4vqS4H3TJKdQofPqezDPP4IR5ApTjuqeNIJNZkCvHMSY6TtEkCZUS3k%3D; WM_NIKE=9ca17ae2e6ffcda170e2e6eeb2e57dbababf88b879a8b08fa2d84f869f9fbaaa50a3f599a5d650939b8dadd52af0fea7c3b92aab92fa85f86d83adfddae243afee85d3d133ada8fed9c679ba8ca3d6ee5aaabdbaabc269bb97bb82cc3ba8bdada6d559aabf88a6f664a1e88a96c85aa6b5a8d4f2258690009bed638f9ffbb1b77eb38dfca9b2608a95acb2ee6e94afab9bc75c94ec87b3b84bb48ca696f46f8e9786afd96181aa88aed253f68cbca6ea499a8b9dd4ea37e2a3; JSESSIONID-WYYY=tI8MIKMCRBuyCYnUJMCyUTlp%2Fufv5xIfCquvp7PJ4%2BuXod%5CXH%5CB0icDZw8TNlwHUHOW%2B2t%2BCuXyC4VZ%5C19OrzaDE%5Ck0F0dAZQh7KcVxUoHKpqUdiVzPu8NxCK9cJRG%5C%5CPTvtqxjFerd1%2BBa4%2F%5C8PESa4pvvRaQF6jljjsibX%5CrcPsH0I%3A1593347447142',
}
# 搜索歌曲接口
API_Serch_Songs = 'https://music.163.com/weapi/cloudsearch/get/web?csrf_token='
# 歌曲评论
API_Comments_Song = 'https://music.163.com/weapi/v1/resource/comments/R_SO_4_{}?csrf_token=' # 音乐ID可替换
# 歌曲歌词
API_Lyric_Songs = 'https://music.163.com/weapi/song/lyric?csrf_token='
# crypt_js_complex python 复写cryptjs
def crypt_js_complex(self,text):
BS = AES.block_size
pad = lambda s: s + (BS - len(s) % BS) * chr(BS - len(s) % BS).encode('utf-8')
unpad = lambda s: s[0:-s[-1]]
key = bytes(self._i, encoding="utf-8")
text = text.encode("utf-8")
IV = b'0102030405060708'
cipher = AES.new(key, mode=AES.MODE_CBC, IV=IV)
# cipher2 = AES.new(key, mode=AES.MODE_CBC, IV=IV) # 加密和解密，cipher对象只能用一次
# print(text)
encrypted = pad(text)
# print(encrypted)
encrypted = cipher.encrypt(encrypted)
# print(encrypted)
encrypted = base64.b64encode(encrypted).decode("utf-8")
# print("第二次加密结果", encrypted)
return encrypted
# crypt_js_complex 的基础
def crypt_js_complex_base(self,text):
BS = AES.block_size
pad = lambda s: s + (BS - len(s) % BS) * chr(BS - len(s) % BS).encode('utf-8')
unpad = lambda s: s[0:-s[-1]]
key = b'0CoJUm6Qyw8W8jud'
text = text.encode("utf-8")
IV = b'0102030405060708'
cipher = AES.new(key, mode=AES.MODE_CBC, IV=IV)
# cipher2 = AES.new(key, mode=AES.MODE_CBC, IV=IV) # 加密和解密，cipher对象只能用一次
# print(text)
encrypted = pad(text)
# print(encrypted)
encrypted = cipher.encrypt(encrypted)
# print(encrypted)
encrypted = base64.b64encode(encrypted).decode("utf-8")
# print("第一次加密结果", encrypted)
return encrypted
# 获得parms参数值
def get_params(self,text):
return self.crypt_js_complex(
self.crypt_js_complex_base(text),)
# 搜索歌曲接口
def serch_songs(self,name,offset=0):
"""
:param name:str
:param offset:int 偏移量 默认第一页 例如 0 30 60 90
:return 接口数据
"""
text = '{"hlpretag":"","hlposttag":"","#/discover":"","s":"%s","type":"1","offset":"%s","total":"false","limit":"30","csrf_token":""}'%(name,offset*30)
# payload = 'params={params}&encSecKey={encSecKey}'.format(params=self.get_params(text),encSecKey=self.encSecKey)
params = (
('csrf_token', ''),
)
data = {
'params': self.get_params(text),
'encSecKey': self.encSecKey
}
response = requests.post(self.API_Serch_Songs, headers=self.headers, params=params,
data=data)
self._dispose(json.loads(response.text))
# 歌曲评论抓取
def comment_song(self,songid:str,offset:int=0):
""""
:param str 歌曲ID
:param int 翻页 默认第一页 0 20 40
:return 接口数据
"""
text = '{"rid":"R_SO_4_%s","offset":"%s","total":"true","limit":"20","csrf_token":""}'%(songid,offset*20)
params = (
('csrf_token', ''),
)
data = {
'params': self.get_params(text),
'encSecKey': self.encSecKey
}
response = requests.post(self.API_Comments_Song.format(songid), headers=self.headers,
params=params, data=data)
self._dispose(json.loads(response.text))
# 歌词爬取
def lyric_song(self,songid:str):
"""
:param songid str 歌曲ID
:return 接口数据
"""
# 歌词接口加密参数原型
text = '{"id":"%s","lv":-1,"tv":-1,"csrf_token":""}'%(songid)
params = (
('csrf_token', ''),
)
data = {
'params': self.get_params(text),
'encSecKey': self.encSecKey
}
response = requests.post(self.API_Lyric_Songs, headers=self.headers, params=params, data=data)
self._dispose(json.loads(response.text))
# 处理爬虫获取到的数据，这里我就输出值
def _dispose(self, data):
pprint.pprint(data)
return data
# 主函数 测试
def wangyi_main(self):
# 搜索接口
# self.serch_songs("旧账",0)
#歌曲评论接口
self.comment_song("25639331",0)
# 歌词接口
# self.lyric_song("1351615757") # 旧账
pass
if __name__ == '__main__':
wangyi = WangYiYun()
wangyi.wangyi_main()
歌曲评论接口解析
歌曲评论接口同上
参数：
'{"rid":"R_SO_4_25639331","offset":"0","total":"true","limit":"20","csrf_token":""}'
API：
'https://music.163.com/weapi/v1/resource/comments/R_SO_4_{}?csrf_token=' # 音乐ID可替换
歌词接口解析
歌词接口接口同上
参数：
'{"id":"25639331","lv":-1,"tv":-1,"csrf_token":"”}'
API：
"/weapi/song/lyric”
网易云爬虫github地址
补充
关于 No module named ‘Crypto’ 解决方案
pip3 uninstall pycryptodome
pip3 uninstall crypto
Pip3 install pycrypto