diff --git a/fin.py b/fin.py new file mode 100644 index 0000000..3add0a6 --- /dev/null +++ b/fin.py @@ -0,0 +1,189 @@ +#1.找到未加密的参数 +#2.通过函数window.asrsea()进行加密 +#2.想办法把参数进行加密，params--->encText encSecKey--->encSecKey + +import requests +from Crypto.Cipher import AES +from base64 import b64encode +import json +import re + +#爬取软件名称：网易云 +def get_wyy(): + url="https://music.163.com/" + headers = { + "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/100.0.4896.127 Safari/537.36"} + resp=requests.get(url=url, headers=headers) + #print(resp.text) + obj=re.compile(r"(?P<name>.*?)",re.S) + result = obj.finditer(resp.text) + for it in result: + name = it.group('name') + return name + +#歌词信息 +def get_lyric(song_id): + headers = { + "user-agent" : "Mozilla/5.0", + "Referer" : "http://music.163.com", + "Host" : "music.163.com" + } + if not isinstance(song_id, str): #判断函数是否是一个已知的类型，类似type（） + song_id = str(song_id) + url = f"http://music.163.com/api/song/lyric?id={song_id}+&lv=1&tv=-1" + try: + resp = requests.get(url, headers=headers) + resp.raise_for_status() #判断返回的Response类型状态是不是200,如果是200，他将表示返回的内容是正确的;如果不是200，他就会产生一个HttpError的异常. + resp.encoding = resp.apparent_encoding #从网页的响应内容分析编码的方式 + json_obj = json.loads(resp.text) #将str类型的数据转成dict + # print(json_obj) + return json_obj["lrc"]["lyric"] + except: + return "访问异常" + + +e = "010001" +f = "00e0b509f6259df8642dbc35662901477df22677ec152b5ff68ace615bb7b725152b3ab17a876aea8a5aa76d2e417629ec4ee341f56135fccf695280104e0312ecbda92557c93870114af6c9d05c4f7f0c3685b7a46bee255932575cce10b424d813cfe4875d3e82047b97ddef52741d546b8e289dc6935b3ece0462db0a22b8e7" +g = "0CoJUm6Qyw8W8jud" +i = "0hyFaCNAVzOIdoht" + +url = 'https://music.163.com/weapi/comment/resource/comments/get?csrf_token=' +headers = { + 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36' + } + +def get_encSecKey(): + return "4022359ea3110bcd034e0160c3b89e5e172fd0110a3cf765d9f366d9fd09840a1f4a4705ac43719fdb8bfeb44d3b92334733061ad10942131184a4dfba0ac9d2cf867b8b6236523c1ca5f44c0d2d82c1c2665a3137a9241c7373539c1aa8e5e9bb9d33dafc764b5d76c2ab34fc94df85e27a934c8a603fa713f2cf38c2b7bbae" + +#对数据进行加密 +def get_params(data): #data得是json字符串 + first = enc_params(data,g) + second = enc_params(first,i) + return second #返回的就是params + +def to_16(data): + pad = 16-len(data)%16 + data +=chr(pad) * pad + return data + +#加密过程 +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) #创建加密器 + bs = aes.encrypt(data.encode('utf-8')) #加密，加密的内容长度必须是16的倍数， + return str(b64encode(bs),"utf-8") #转化成字符串 + +#处理加密过程 +''' +function a(a = 16) { ↓ + var d, e, b = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789", c = ""; + for (d = 0; a > d; d += 1) #循环16次 + e = Math.random() * b.length, #取随机数 3.15154 + e = Math.floor(e), #取整 3 + c += b.charAt(e); #取字符串中的第e个字符 3 + return c #循环16次取b中的字符返回一个值c +} +function b(a, b) { #a为要加密的内容 + var c = CryptoJS.enc.Utf8.parse(b) #由下几行可知c为密钥，则b为密钥 + , d = CryptoJS.enc.Utf8.parse("0102030405060708") + , e = CryptoJS.enc.Utf8.parse(a) #将数据a用utf-8转换 + , f = CryptoJS.AES.encrypt(e, c, { #缺少加密密钥，从而得知c密钥 + iv: d, #AES算法中的偏移量 + mode: CryptoJS.mode.CBC #模式：CBC + }); + return f.toString() #把f转换成字符串返回 +} +function c(a, b, c) { #c不产生随机数random + 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:'一堆破烂玩意' , g:'0CoJUm6Qyw8W8jud' + var h = {} #空对象 + , i = a(16); #i设置成定值 +/* + return h.encText = b(d, g), + h.encText = b(h.encText, i), + h.encSecKey = c(i, e, f), + h +/* + #上式逻辑与下式相同 + h.encText = b(d, g), #g为密钥 + h.encText = b(h.encText, i), #返回的就是params i为密钥 + h.encSecKey = c(i, e, f), #得到的就是encSecKey e，f为默认值参数，i为随机数,将i固定得到一个固定的encSecKey + return h +} +''' + +def get_comment(): + page = int(input('请输入需要爬取的评论页数：')) + print('开始爬！！！！！') + for j in range(page): + page_num = str(j*20) + data = { + 'csrf_token': "", + 'cursor': "-1", + 'offset': page_num, + 'orderType': "1", + 'pageNo': "1", + 'pageSize': "20", + 'rid': "R_SO_4_" + song_id, #查看不同歌曲评论只需要找到对应歌曲的id + 'threadId': "R_SO_4_" + song_id #还有我 + } + + response = requests.post(url,data={ + "params":get_params(json.dumps(data)), + "encSecKey":get_encSecKey() + },headers=headers) + print(response.text) + + result = json.loads(response.content.decode('utf-8')) + fp = open('./歌曲信息.txt', 'a', encoding='utf-8') + # with open ('./网易云评论.txt', 'w', encoding='utf-8') as fp: + + #hotComments + #fp.write('最佳损友' + '\n') + fp.write('hotComments' + '\n') + for hot in range(len(result['data']['hotComments'])): + fp.write('账号：' + str(result['data']['hotComments'][hot]['user']['userId']) + '\n') + fp.write('昵称：' + result['data']['hotComments'][hot]['user']['nickname'] + '\n') + fp.write('评论：' + result['data']['hotComments'][hot]['content'] + '\n') + + if result['data']['hotComments'][hot]['user']['vipRights'] == None: + fp.write('vip:yes' + '\n') + else: + fp.write('vip:no' + '\n') + fp.write('点赞数' + str(result['data']['hotComments'][hot]['likedCount']) + '\n') + fp.write('-------------------------------------' + '\n') + + + #comments + fp.write('comments' + '\n') + for r in range(20): + fp.write('昵称：'+result['data']['comments'][r]['user']['nickname']+'\n') + fp.write('评论：'+result['data']['comments'][r]['content']+'\n') + + if result['data']['comments'][r]['user']['vipRights'] == None: + fp.write('vip: No'+'\n') + else: + fp.write('vip: Yes'+'\n') + fp.write('点赞数：'+str(result['data']['comments'][r]['likedCount'])+'\n') + fp.write('-------------------------------------'+'\n') + + fp.close() + print('爬取完毕！！！') + + +if __name__ == '__main__': + song_id = input('请输入想看的歌曲ID呢（在歌曲网址的最后面有一串id=......）:') + lyric = get_lyric(song_id) + name = get_wyy() + with open("./歌曲信息.txt", "w", encoding='utf-8') as file: + file.writelines(name + '\n') + file.writelines(lyric + '\n') + get_comment() + + +