爬取网易云评论--涉及加密问题、程序断点问题

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# Author:woshinidaye

#抓取网易云歌曲的热评，为了简单，不要登录了
#1、找到未加密的参数
#2、想办法把参数进行加密，加密逻辑与网易一致，params,encSecKey
#3、请求，拿去数据
#加密
# var
# bUM2x = window.asrsea(JSON.stringify(i6c), bsG7z(["流泪", "强"]), bsG7z(WW3x.md), bsG7z(["爱心", "女孩", "惊恐", "大笑"]));
# e6c.data = j6d.cs6m({
#     params: bUM2x.encText,
#     encSecKey: bUM2x.encSecKey
# })

import requests,re,json,base64
from lxml import html
from Crypto.Cipher import AES           #pip install pycryptodome
etree = html.etree

url = "https://music.163.com/weapi/comment/resource/comments/get?csrf_token="
#请求方式
e = '010001'
f = '00e0b509f6259df8642dbc35662901477df22677ec152b5ff68ace615bb7b725152b3ab17a876aea8a5aa76d2e417629ec4ee341f56135fccf695280104e0312ecbda92557c93870114af6c9d05c4f7f0c3685b7a46bee255932575cce10b424d813cfe4875d3e82047b97ddef52741d546b8e289dc6935b3ece0462db0a22b8e7'
g = "0CoJUm6Qyw8W8jud"
i = 'hjbiwTejTo17235R'
def get_encSecKey():
    return '6c11f64c829ec94df8ce7d711932c15c4c6e46daf00674f0f22dc1170ba68e809047ee5a7e12c3e07d8c1c3f66b76e4518201b1d4679bd1659a747856f16ac17c32286fba6a82034fa2597004dcca90ca9bfce49bd1a85d09fac162d7b40b390fe8d4c4be15bcc65788d0002fdbd91fb529a71d4d42aa702170fd8e92f1ed87e'
def to_16 (data):
    pad = 16 -len(data)%16
    data = data + chr(pad)*pad
    return data
def enc_params(data,key):
    iv = '0102030405060708'
    data = to_16(data)
    aes = AES.new(key=key.encode('utf-8'),IV=iv.encode('utf-8'),mode=AES.MODE_CBC)
    bs = aes.encrypt(data.encode('utf-8'))
    return str(base64.b64encode(bs),'utf-8')       #返回params
def get_params(data):       #默认data是字符串
    first = enc_params(data,g)
    second = enc_params(first,i)
    return second


# "c6aaef7d7fe54edc416de03808f94c8de2590f943d4f334d8bc485e53f00b95acdfbe704330a01d81bfe666c00b5d681321ab4b04147d0ba1683877e4350b1310e3ad67465ffa1dc9ea57b9d682f1efffbe14ad734a9454faf8e28464491542226109de2fdce6751b63426bd3b18543108c5076ef2b8eab03358ea7a88ce90e9"
data = {
    'csrf_token': "",
    'cursor': '-1',
    'offset': '0',
    'orderType': '1',
    'pageNo': '1',
    'pageSize': '20',
    'rid': "R_SO_4_1881521546",
    'threadId': "R_SO_4_1881521546"
}
#加密方式
'''
    function a(a) {             #随机产生16位字符串
        var d, e, b = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789", c = "";
        for (d = 0; a > d; d += 1)      #循环16次
            e = Math.random() * b.length,       #随机数
            e = Math.floor(e),              #取整
            c += b.charAt(e);                   #取字符串中的xxxx位置
        return c
    }
    function b(a, b) {          #a是要加密的数据
        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,              #偏移量
            mode: CryptoJS.mode.CBC         #模式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) {        #d:data   e:010001    f:bsG7z(WW3x.md)  g:bsG7z(["爱心", "女孩", "惊恐", "大笑"])
        var h = {}
          , i = a(16);          #i就是16位随机字符
        return h.encText = b(d, g), 
        h.encText = b(h.encText, i),           #得到params,       做了两次加密，第一次 data+g
        h.encSecKey = c(i, e, f),              #得到encSecKey  
        h
    }
'''
# var bUM2x = window.asrsea(JSON.stringify(i6c), bsG7z(["流泪", "强"]), bsG7z(WW3x.md), bsG7z(["爱心", "女孩", "惊恐", "大笑"]));
'''
  u6o.be6Y = function(Y6S, e6c) {
        var i6c = {}
          , e6c = NEJ.X({}, e6c)
          , mo0x = Y6S.indexOf("?");
        if (window.GEnc && /(^|\.com)\/api/.test(Y6S) && !(e6c.headers && e6c.headers[eu7n.AI4M] == eu7n.FD6x) && !e6c.noEnc) {
            if (mo0x != -1) {
                i6c = j6d.gW8O(Y6S.substring(mo0x + 1));
                Y6S = Y6S.substring(0, mo0x)
            }
            if (e6c.query) {
                i6c = NEJ.X(i6c, j6d.fT8L(e6c.query) ? j6d.gW8O(e6c.query) : e6c.query)
            }
            if (e6c.data) {
                i6c = NEJ.X(i6c, j6d.fT8L(e6c.data) ? j6d.gW8O(e6c.data) : e6c.data)
            }
            i6c["csrf_token"] = u6o.gQ8I("__csrf");
            Y6S = Y6S.replace("api", "weapi");
            e6c.method = "post";
            delete e6c.query;
            var bUM2x = window.asrsea(JSON.stringify(i6c), bsG7z(["流泪", "强"]), bsG7z(WW3x.md), bsG7z(["爱心", "女孩", "惊恐", "大笑"]));
            e6c.data = j6d.cs6m({
                params: bUM2x.encText,
                encSecKey: bUM2x.encSecKey
            })
        }
        var cdnHost = "y.music.163.com";
        var apiHost = "interface.music.163.com";
        if (location.host === cdnHost) {
            Y6S = Y6S.replace(cdnHost, apiHost);
            if (Y6S.match(/^\/(we)?api/)) {
                Y6S = "//" + apiHost + Y6S
            }
            e6c.cookie = true
        }
        cxg5l(Y6S, e6c)
'''

resp = requests.post(url,data={
    'params': get_params(json.dumps(data)),
    "encSecKey":get_encSecKey()
})
print(resp.text)


#上面是获取某一首歌的评论，变量主要在data里面，更换歌曲ID，可以通过页面查找获取
'''
url = 'https://music.163.com/playlist?id=6920064959'
resp = requests.get(url=url,headers=headers)
resp.encoding = 'utf-8'
# print(resp.text)
# 用RE
# obj = re.compile(r'<li><a href="/(?P<song_id>.*?)">(?P<song_title>.*?)</a></li>',re.S)
# songs = obj.finditer(resp.text)
# for my_list in songs:
#     aa = my_list.group('song_id').split('=')[-1]
#     print(aa,'\t',my_list.group('song_title'))

#用Xpath
# etree = html.etree
# # print(resp.text)
# html = etree.HTML(resp.text)
# test = html.xpath('//html/body/div[3]/div[1]/div/div/div[2]/div[2]//a/@href')
# #这个地方试了好久，写全的话取不出来，感觉是跟页面有嵌套有关系
# print(test)

#用bs4
# from bs4 import BeautifulSoup
# html = BeautifulSoup(resp.text,'html.parser')
# test = html.find('ul',class_='f-hide').find_all('a')
# print(test)
'''