python 网易云音乐评论爬取1

原文链接：
（1）Python爬取网易云音乐评论
https://www.jianshu.com/p/92950e9605c9
（2）网易云音乐评论爬虫（三）:爬取歌曲的全部评论
https://yq.aliyun.com/articles/672464

#（1）[Python爬取网易云音乐评论](https://www.jianshu.com/p/92950e9605c9)
headers = {
    'User-Agent':'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.87 Safari/537.36'
}

baseUrl = 'https://music.163.com'
def getHtml(url):
    r = requests.get(url, headers=headers)
    html = r.text
    return html

def getUrl():
    #从最新歌单开始
    startUrl = 'https://music.163.com/discover/playlist/?order=new'
    html = getHtml(startUrl)
    pattern =re.compile('
.*?.*?<.*?title="(.*?)".*?href="(.*?)".*?>.*?span class="s-fc4".*?title="(.*?)".*?href="(.*?)".*?
',re.S)
    result = re.findall(pattern,html)
    #获取歌单总页数
    pageNum = re.findall(r'(.*?)',html,re.S)[0]
    info = []
    #对第一页的歌单获取想要的信息
    for i in result:
        data = {}
        data['title'] = i[0]
        url = baseUrl+i[1]
        print url
        data['url'] = url
        data['author'] = i[2]
        data['authorUrl'] = baseUrl+i[3]
        info.append(data)
        #调用获取每个歌单里的歌曲的方法
        getSongSheet(url)
        time.sleep(random.randint(1,10))
        #这里暂时获取第一页的第一个歌单，所以用break
        break
def getSongSheet(url):
    #获取每个歌单里的每首歌的id，作为接下来post获取的关键
    html = getHtml(url)
    result = re.findall(r'
(.*?)
',html,re.S)
    result.pop()
    musicList = []
    for i in result:
        data = {}
        headers1 = {
            'Referer': 'https://music.163.com/song?id={}'.format(i[0]),
            'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.87 Safari/537.36'
        }
        musicUrl = baseUrl+'/song?id='+i[0]
        print musicUrl
        #歌曲url
        data['musicUrl'] = musicUrl
        #歌曲名
        data['title'] = i[1]
        musicList.append(data)
        postUrl = 'https://music.163.com/weapi/v1/resource/comments/R_SO_4_{}?csrf_token='.format(i[0])
        param = {
            'params': get_params(1),
            'encSecKey': get_encSecKey()
        }
        r = requests.post(postUrl,data = param,headers = headers1)
        total = r.json()
        # 总评论数
        total = int(total['total'])
        comment_TatalPage = total/20
        # 基础总页数
        print comment_TatalPage
        #判断评论页数，有余数则为多一页，整除则正好
        if total%20 != 0:
            comment_TatalPage = comment_TatalPage+1
            comment_data,hotComment_data = getMusicComments(comment_TatalPage, postUrl, headers1)
            #存入数据库的时候若出现ID重复，那么注意爬下来的数据是否只有一个
            saveToMongoDB(str(i[1]),comment_data,hotComment_data)
            print 'End!'
        else:
            comment_data, hotComment_data = getMusicComments(comment_TatalPage, postUrl, headers1)
            saveToMongoDB(str(i[1]),comment_data,hotComment_data)
            print 'End!'

        time.sleep(random.randint(1, 10))
        break
def getMusicComments(comment_TatalPage ,postUrl, headers1):
    commentinfo = []
    hotcommentinfo = []
    # 对每一页评论
    for j in range(1, comment_TatalPage + 1):
        # 热评只在第一页可抓取
        if j == 1:
            #获取评论
            r = getPostApi(j , postUrl, headers1)
            comment_info = r.json()['comments']
            for i in comment_info:
                com_info = {}
                com_info['content'] = i['content']
                com_info['author'] = i['user']['nickname']
                com_info['likedCount'] = i['likedCount']
                commentinfo.append(com_info)
            hotcomment_info = r.json()['hotComments']
            for i in hotcomment_info:
                hot_info = {}
                hot_info['content'] = i['content']
                hot_info['author'] = i['user']['nickname']
                hot_info['likedCount'] = i['likedCount']
                hotcommentinfo.append(hot_info)
        else:
            r = getPostApi(j, postUrl, headers1)
            comment_info = r.json()['comments']
            for i in comment_info:
                com_info = {}
                com_info['content'] = i['content']
                com_info['author'] = i['user']['nickname']
                com_info['likedCount'] = i['likedCount']
                commentinfo.append(com_info)
        print u'第'+str(j)+u'页爬取完毕...'
        time.sleep(random.randint(1,10))
    print commentinfo
    print '\n-----------------------------------------------------------\n'
    print hotcommentinfo
    return commentinfo,hotcommentinfo
# offset的取值为:(评论页数-1)*20,total第一页为true，其余页为false
# first_param = '{rid:"", offset:"0", total:"true", limit:"20", csrf_token:""}' # 第一个参数
# 第二个参数
second_param = "010001"
# 第三个参数
third_param = "00e0b509f6259df8642dbc35662901477df22677ec152b5ff68ace615bb7b725152b3ab17a876aea8a5aa76d2e417629ec4ee341f56135fccf695280104e0312ecbda92557c93870114af6c9d05c4f7f0c3685b7a46bee255932575cce10b424d813cfe4875d3e82047b97ddef52741d546b8e289dc6935b3ece0462db0a22b8e7"
# 第四个参数
forth_param = "0CoJUm6Qyw8W8jud"
# 获取参数
def get_params(page): # page为传入页数
    iv = "0102030405060708"
    first_key = forth_param
    second_key = 16 * 'F'
    if(page == 1): # 如果为第一页
        first_param = '{rid:"", offset:"0", total:"true", limit:"20", csrf_token:""}'
        h_encText = AES_encrypt(first_param, first_key, iv)
    else:
        offset = str((page-1)*20)
        first_param = '{rid:"", offset:"%s", total:"%s", limit:"20", csrf_token:""}' %(offset,'false')
        h_encText = AES_encrypt(first_param, first_key, iv)
    h_encText = AES_encrypt(h_encText, second_key, iv)
    return h_encText

# 获取 encSecKey
def get_encSecKey():
    encSecKey = "257348aecb5e556c066de214e531faadd1c55d814f9be95fd06d6bff9f4c7a41f831f6394d5a3fd2e3881736d94a02ca919d952872e7d0a50ebfa1769a7a62d512f5f1ca21aec60bc3819a9c3ffca5eca9a0dba6d6f7249b06f5965ecfff3695b54e1c28f3f624750ed39e7de08fc8493242e26dbc4484a01c76f739e135637c"
    return encSecKey

# 加密过程
def AES_encrypt(text, key, iv):
    pad = 16 - len(text) % 16
    text = text + pad * chr(pad)
    encryptor = AES.new(key, AES.MODE_CBC, iv)
    encrypt_text = encryptor.encrypt(text)
    encrypt_text = base64.b64encode(encrypt_text)
    return encrypt_text

#获取post得到的Json
def getPostApi(j ,postUrl, headers1):
    param = {
        # 获取对应页数的params
        'params': get_params(j),
        'encSecKey': get_encSecKey()
    }
    r = requests.post(postUrl, data=param, headers=headers1)
    return r
def saveToMongoDB(musicName,comment_data,hotComment_data):
    client = pymongo.MongoClient(host='localhost',port=27017)
    db = client['Music163']
    test = db[musicName]
    test.insert(hotComment_data)
    test.insert(comment_data)
    print musicName+u'已存入数据库...'

if __name__ == '__main__':
    getUrl()

#（2）[网易云音乐评论爬虫（三）:爬取歌曲的全部评论](https://yq.aliyun.com/articles/672464)
#GitHub(https://github.com/zyingzhou/wangyiyun_music/blob/master/get_comments.py)
#! /usr/bin/env python
# coding='utf-8'
'''
获取网易云音乐歌曲全部评论
Author: zhouzying
URL: https://www.zhouzying.cn
Date: 2018-09-14
Update: 2018-09-27         Add data argument.
Update: 2018-10-04         Get replied comments and add users name who shared comments.
'''
import requests
import math
import random
# pycrypto
from Crypto.Cipher import AES
import codecs
import base64

# 构造函数获取歌手信息
def get_comments_json(url, data):
    headers={'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
             'Accept-Encoding': 'gzip, deflate',
             'Accept-Language': 'zh-CN,zh;q=0.9',
             'Connection': 'keep-alive',
             'Cookie': 'WM_TID=36fj4OhQ7NdU9DhsEbdKFbVmy9tNk1KM; _iuqxldmzr_=32; _ntes_nnid=26fc3120577a92f179a3743269d8d0d9,1536048184013; _ntes_nuid=26fc3120577a92f179a3743269d8d0d9; __utmc=94650624; __utmz=94650624.1536199016.26.8.utmcsr=google|utmccn=(organic)|utmcmd=organic|utmctr=(not%20provided); WM_NI=2Uy%2FbtqzhAuF6WR544z5u96yPa%2BfNHlrtTBCGhkg7oAHeZje7SJiXAoA5YNCbyP6gcJ5NYTs5IAJHQBjiFt561sfsS5Xg%2BvZx1OW9mPzJ49pU7Voono9gXq9H0RpP5HTclE%3D; WM_NIKE=9ca17ae2e6ffcda170e2e6eed5cb8085b2ab83ee7b87ac8c87cb60f78da2dac5439b9ca4b1d621f3e900b4b82af0fea7c3b92af28bb7d0e180b3a6a8a2f84ef6899ed6b740baebbbdab57394bfe587cd44b0aebcb5c14985b8a588b6658398abbbe96ff58d868adb4bad9ffbbacd49a2a7a0d7e6698aeb82bad779f7978fabcb5b82b6a7a7f73ff6efbd87f259f788a9ccf552bcef81b8bc6794a686d5bc7c97e99a90ee66ade7a9b9f4338cf09e91d33f8c8cad8dc837e2a3; JSESSIONID-WYYY=G%5CSvabx1X1F0JTg8HK5Z%2BIATVQdgwh77oo%2BDOXuG2CpwvoKPnNTKOGH91AkCHVdm0t6XKQEEnAFP%2BQ35cF49Y%2BAviwQKVN04%2B6ZbeKc2tNOeeC5vfTZ4Cme%2BwZVk7zGkwHJbfjgp1J9Y30o1fMKHOE5rxyhwQw%2B%5CDH6Md%5CpJZAAh2xkZ%3A1536204296617; __utma=94650624.1052021654.1536048185.1536199016.1536203113.27; __utmb=94650624.12.10.1536203113',
             'Host': 'music.163.com',
             'Referer': 'http://music.163.com/',
             'Upgrade-Insecure-Requests': '1',
             'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                           'Chrome/66.0.3359.181 Safari/537.36'}
    try:
        r = requests.post(url, headers=headers, data=data)
        r.encoding = "utf-8"
        if r.status_code == 200:
            # 返回json格式的数据
            return r.json()
    except:
        print("爬取失败!")

# 生成16个随机字符
def generate_random_strs(length):
    string = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789"
    # 控制次数参数i
    i = 0
    # 初始化随机字符串
    random_strs  = ""
    while i < length:
        e = random.random() * len(string)
        # 向下取整
        e = math.floor(e)
        random_strs = random_strs + list(string)[e]
        i = i + 1
    return random_strs

# AES加密
def AESencrypt(msg, key):
    # 如果不是16的倍数则进行填充(paddiing)
    padding = 16 - len(msg) % 16
    # 这里使用padding对应的单字符进行填充
    msg = msg + padding * chr(padding)
    # 用来加密或者解密的初始向量(必须是16位)
    iv = '0102030405060708'
    cipher = AES.new(key, AES.MODE_CBC, iv)
    # 加密后得到的是bytes类型的数据
    encryptedbytes = cipher.encrypt(msg)
    # 使用Base64进行编码,返回byte字符串
    encodestrs = base64.b64encode(encryptedbytes)
    # 对byte字符串按utf-8进行解码
    enctext = encodestrs.decode('utf-8')
    return enctext

# RSA加密
def RSAencrypt(randomstrs, key, f):
    # 随机字符串逆序排列
    string = randomstrs[::-1]
    # 将随机字符串转换成byte类型数据
    text = bytes(string, 'utf-8')
    seckey = int(codecs.encode(text, encoding='hex'), 16)**int(key, 16) % int(f, 16)
    return format(seckey, 'x').zfill(256)

# 获取参数
def get_params(page):
    # msg也可以写成msg = {"offset":"页面偏移量=(页数-1) *　20", "limit":"20"},offset和limit这两个参数必须有(js)
    # limit最大值为100,当设为100时,获取第二页时,默认前一页是20个评论,也就是说第二页最新评论有80个,有20个是第一页显示的
    # msg = '{"rid":"R_SO_4_1302938992","offset":"0","total":"True","limit":"100","csrf_token":""}'
    # 偏移量
    offset = (page-1) * 20
    # offset和limit是必选参数,其他参数是可选的,其他参数不影响data数据的生成
    msg = '{"offset":' + str(offset) + ',"total":"True","limit":"20","csrf_token":""}'
    key = '0CoJUm6Qyw8W8jud'
    f = '00e0b509f6259df8642dbc35662901477df22677ec152b5ff68ace615bb7b725152b3ab17a876aea8a5aa76d2e417629ec4ee341f56135fccf695280104e0312ecbda92557c93870114af6c9d05c4f7f0c3685b7a46bee255932575cce10b424d813cfe4875d3e82047b97ddef52741d546b8e289dc6935b3ece0462db0a22b8e7'
    e = '010001'
    enctext = AESencrypt(msg, key)
    # 生成长度为16的随机字符串
    i = generate_random_strs(16)
    # 两次AES加密之后得到params的值
    encText = AESencrypt(enctext, i)
    # RSA加密之后得到encSecKey的值
    encSecKey = RSAencrypt(i, e, f)
    return encText, encSecKey

def hotcomments(html, songname, i, pages, total, filepath):
    # 写入文件
    with open(filepath, 'a', encoding='utf-8') as f:
        f.write("正在获取歌曲{}的第{}页评论,总共有{}页{}条评论！\n".format(songname, i, pages, total))
    print("正在获取歌曲{}的第{}页评论,总共有{}页{}条评论！\n".format(songname, i, pages, total))
    # 精彩评论
    m = 1
    # 键在字典中则返回True, 否则返回False
    if 'hotComments' in html:
        for item in html['hotComments']:
            # 提取发表热门评论的用户名
            user = item['user']
            # 写入文件
            print("热门评论{}: {} : {}    点赞次数: {}".format(m, user['nickname'], item['content'], item['likedCount']))
            with open(filepath, 'a', encoding='utf-8') as f:
                f.write("热门评论{}: {} : {}   点赞次数: {}\n".format(m, user['nickname'], item['content'], item['likedCount']))
                # 回复评论
                if len(item['beReplied']) != 0:
                    for reply in item['beReplied']:
                        # 提取发表回复评论的用户名
                        replyuser = reply['user']
                        print("回复：{} : {}".format(replyuser['nickname'], reply['content']))
                        f.write("回复：{} : {}\n".format(replyuser['nickname'], reply['content']))
            m += 1

def comments(html, songname, i, pages, total, filepath):
    with open(filepath, 'a', encoding='utf-8') as f:
        f.write("\n正在获取歌曲{}的第{}页评论,总共有{}页{}条评论！\n".format(songname, i, pages, total))
    print("\n正在获取歌曲{}的第{}页评论,总共有{}页{}条评论！\n".format(songname, i, pages, total))
    # 全部评论
    j = 1
    for item in html['comments']:
        # 提取发表评论的用户名
        user = item['user']
        print("全部评论{}: {} : {}    点赞次数: {}".format(j, user['nickname'], item['content'], item['likedCount']))
        with open(filepath, 'a', encoding='utf-8') as f:
            f.write("全部评论{}: {} : {}   点赞次数: {}\n".format(j, user['nickname'], item['content'], item['likedCount']))
            # 回复评论
            if len(item['beReplied']) != 0:
                for reply in item['beReplied']:
                    # 提取发表回复评论的用户名
                    replyuser = reply['user']
                    print("回复：{} : {}".format(replyuser['nickname'], reply['content']))
                    f.write("回复：{} : {}\n".format(replyuser['nickname'], reply['content']))
        j += 1

def main():
    # 歌曲id号
    songid = 38592976
    # 歌曲名字
    songname = "Dream it possible"
    # 文件存储路径
    filepath = songname + ".txt"
    page = 1
    params, encSecKey = get_params(page)
    url = 'https://music.163.com/weapi/v1/resource/comments/R_SO_4_' + str(songid) + '?csrf_token='
    data = {'params': params, 'encSecKey': encSecKey}
    # url = 'https://music.163.com/#/song?id=19292984'
    # 获取第一页评论
    html = get_comments_json(url, data)
    # 评论总数
    total = html['total']
    # 总页数
    pages = math.ceil(total / 20)
    hotcomments(html, songname, page, pages, total, filepath)
    comments(html, songname, page, pages, total, filepath)

    # 开始获取歌曲的全部评论
    page = 2
    while page <= pages:
        params, encSecKey = get_params(page)
        data = {'params': params, 'encSecKey': encSecKey}
        html = get_comments_json(url, data)
        # 从第二页开始获取评论
        comments(html, songname, page, pages, total, filepath)
        page += 1

if __name__ == "__main__":
    main()