Using new api and make it more powerful

README.md

@@ -3,47 +3,45 @@
 
 ![warning](http://ounix1xcw.bkt.clouddn.com/warning.png)
 
-（学习使用异或加密 :see_no_evil:
+（学习使用异或加密 :see_no_evil: )
 
 ## 介绍
 用于获取网易云音乐缓存文件的mp3文件
 
-缓存文件 在手机上的在 `netease/cloudmusic/Cache/`里的`Music1`里， 歌词在`Lyric`里，（电脑上的路径可以在设置里找到还可以自己设置）
+缓存文件 在手机上的在 `netease/cloudmusic/Cache/`里的`Music1`里
 思路就是利用缓存文件,解密得到MP3文件, 并通过其metadata,命名文件,顺便从api或者网页抓取歌词,详细介绍可以看[这里](https://mbinary.coding.me/decrypt-netease-music.html) 
 
 ## 需求
 * python3
 * python 模块
-  - mutagen
-  - lxml
   - requests
-  - json
+  - mutagen (optional)
 
- 可以pip install 安装，常见问题可以自行搜索解决
+可以pip3 install 安装
 
 ## 使用
+
 ### 找到缓存文件
- 找到缓存文件的路径， 形如`.../netease/cloudmusic/Cache/Music1`，如果想单独复制过来，请复制 `Music1`和`Lyric`文件夹在同一目录下，再得到路径,
+ 找到缓存文件的路径，`netease/cloudmusic/Cache/Music1`，复制到电脑上, 在电脑上的路径记为 `PATH`
+
 ### 运行
 * 在命令行模式下
-`python3 decrypt.py  *PATH`
-
- 如果不在 netease-music.py所在目录下，可以切换到，或者用它的绝对路径，
- path是上一步得到的路径
+`python3 decrypt.py  PATH`
+这里的 `PATH`  就是缓存文件的位置
 
-* 代码中
- 可以打开代码文件然后修改path，然后运行即可
+也可以将这脚本复制到缓存文件目录的父目录中, 直接运行脚本即可
 
 ## 结果
- 你就可以到Music1所在目录下的`cached_网易云音乐`看到lyric, music了 :smiley: 
+ 你就可以到 `Music1` 的父目录下 看到 `cached_网易云音乐`, 以及其中的 `lyric`, `music` :smiley: 
 
- ![](src/lrc.png)
+ ![](src/result.jpg)
+
+ ![](src/lyric.jpg)
 
- ![](src/music.png)
+ ![](src/music.jpg)
 
-## 说明
-这个脚本还有很多地方不完善,而且还可以加入一些功能,欢迎fork&PR
+## 贡献
+欢迎fork&PR
 
 ## Licence
- [MIT](LICENCE-MIT.txt)
-
+ [MIT](LICENCE)

decrypt.py

@@ -1,164 +1,110 @@
 #coding : utf-8
-from mutagen.easyid3 import EasyID3
-from mutagen.mp3 import MP3
-from itertools import zip_longest
-from collections import Iterable
-from lxml import etree
-from operator import or_
+import os
 import sys
-import requests 
-import json
 import glob
-import re
-import os
+import requests 
+
+DESDIR = 'cached_网易云音乐'
+LRCDIR = os.path.join(DESDIR,'lyric')
+MSCDIR = os.path.join(DESDIR,'music')
 
+API = 'https://api.imjad.cn/cloudmusic/?'
+# two args: id  type
+# type=song, lyric, comments, detail, artist, album, search
+# eg  API = 'https://api.imjad.cn/cloudmusic/?type=song&id=1234132'    download music
 
-class netEaseMusic:
+
+class netease_music:
     def __init__(self,path=''):
-        if path == '':path = input('input the path of  cached netease_music')
+        '''path is the direcoty that contains Music files(cached)'''
+        if path == '': path = input('input the path of  cached netease_music')
         self.path = path
         os.chdir(path)
-        self.names=glob.glob('*.uc!')
+        self.files=glob.glob('*.uc!')
         self.id_mp = {}
-        for i in self.names:self.id_mp[self.getId(i)] = i
-        self.absPaths=[os.path.abspath(i) for i in self.names]
-        self.prep()
-        self.headers={
-            'Referer':'http://music.163.com/',
-            'Host':'music.163.com',
-            'Connection':'keep-alive',
-            'User-Agent': 'ozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',
-            'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'
-            }
-        self.nameXpath ='//div[@class="tit"]/em[@class="f-ff2"]/text()'
-        self.lrcSentencePt=re.compile(r'\[\d+:\d+\.\d+\](.*?)\\n')         # wrong  (r'\[\d+,\d+\](\(\d+,\d+\)(\w))+\n')     
-    def prep(self):   
-        self.prt= os.path.dirname(os.getcwd())
-        self.cd('cached_网易云音乐')
-        self.cd('cached_网易云音乐/lyric')
-        self.cd('cached_网易云音乐/music')
-
-    def cd(self,s):
-        '''cd to the dir path+s, (create it first if not exists)'''
-        try:
-            os.chdir(self.prt)
-            os.chdir(s)
-        except:
-            os.mkdir(s)
-            os.chdir(s)
-
+        for i in self.files:self.id_mp[self.getId(i)] = i
+        if not os.path.exists(DESDIR):os.mkdir(DESDIR)
+        if not os.path.exists(LRCDIR):os.mkdir(LRCDIR)
+        if not os.path.exists(MSCDIR):os.mkdir(MSCDIR)
+        # import re
+        # self.nameXpath ='//div[@class="tit"]/em[@class="f-ff2"]/text()'
+        # self.lrcSentencePt=re.compile(r'\[\d+:\d+\.\d+\](.*?)\\n')         # wrong  (r'\[\d+,\d+\](\(\d+,\d+\)(\w))+\n')      
+
     def getId(self,name):
-        if name[-1] not in '0987654321':
-            name = os.path.basename(name)
         return name[:name.find('-')]
-    def getIdFromIdx(self,idxFileName):
-        with open(idxFileName,'r') as f:
-            try:
-                info = json.load(f)   #  r'\"musicId\":(\d+)'
-            except:
-                raise Exception('file {} is breaken'.format(idxFileName))
-        return info['musicId']
-    def getInfo(self,musicId):
-        try:return self.getInfoFromMp3(musicId)
-        except:
-            with open(musicId,'rb') as f:
-                s = f.read().decode('utf8',errors ='ignore')
-                dic = {}
-                mch = re.findall(r'\[ar:(.*?)\]',s)
-                #  to keep consistent with the id3 tag : namely the value is a list
-                dic['artist']=mch[0] if  mch !=[] else ['']  
-                mch = re.findall(r'\[ti:(.*?)\]',s)
-                dic['title']=mch[0] if  mch !=[] else ['']
-                return dic
 
-    def _genFileName(self,dic,musicId):
-        name = musicId
-        if 'title' in dic:
-            name =  dic['title'][0]
-            if 'artist' in dic:  name+='--'+dic['artist'][0]
-        else:
-            try:name  = self.crawlName(musicId)
-            except Exception as e:
-                print(repr(e))
-        return name
+    def getInfoFromWeb(self,musicId):
+        dic = {}
+        url = API+'type=detail&id=' + str(musicId)
+        info = requests.get(url).json()['songs'][0]
+        dic['artist']= [ info['ar'][0]['name']  ]
+        dic['title']=  [ info['al']['name']     ]
+        dic['cover'] = [ info['al']['picUrl']   ]
+        return dic
 
+    def getInfoFromFile(self,path):
+        if not os.path.exists(path):
+            print('Can not find file '+path)
+            return {}
+        try:
+            from mutagen.easyid3 import EasyID3
+            from mutagen.mp3 import MP3
+            return dict(MP3(path,ID3 = EasyID3))
+        except: 
+            print('[Error ] You can use pip3 to install mutagen or connet to the Internet')
+            raise Exception('Failed to get info of '+path)
+
+    def genName(self,dic):         
+        title = dic['title'][0]
+        artist = dic['artist'][0]
+        if artist in title: title = title.replace(artist,'').strip()
+        return title + '--' + artist
+
     def decrypt(self,fileName):
         with open (fileName,'rb') as f:
             btay = bytearray(f.read())
         musicId = self.getId(fileName)
-        self.cd('cached_网易云音乐/music')
-        with open(str(musicId),'wb') as out:
-            for i,j in enumerate(btay):
-                btay[i] = j ^ 0xa3
-            out.write(bytes(btay))
-        dic = self.getInfo(musicId)
-        newName = self.id_mp[musicId] =  self._genFileName(dic,musicId)
-        if newName == '':newName = musicId
-        try:os.rename(musicId,newName+'.mp3')
-        except:pass
+        idpath = os.path.join(MSCDIR,musicId)
+        if not os.path.exists(idpath):
+            with open(idpath,'wb') as out:
+                for i,j in enumerate(btay):
+                    btay[i] = j ^ 0xa3
+                out.write(bytes(btay))
+        dic = {}
+        try:
+            dic = self.getInfoFromWeb(musicId)
+        except Exception as e:
+            dic = self.getInfoFromFile(os.path.join(MSCDIR,musicId))
+        name = self.genName(dic)
+        self.id_mp [musicId] = name
+        path = os.path.join(MSCDIR,name+'.mp3')
+        if os.path.exists(idpath) and not os.path.exists(path):
+            os.rename(idpath,path)
         return musicId
 
-    def crawlName(self,musicId):
-        url = 'https://music.163.com/#/song?id='+str(musicId)
-        r= requests.get(url,headers = self.headers)
-        if r.status_code !=200:
-            print(r.status_code)
-            raise  Exception('crawl Name Failed! Bad Responde from '+url)
-        sl = etree.HTML(r.text)
-        try:
-            li = sl.xpath(self.nameXpath)[0]
-            return '' if li ==[] else li[0]
-        except:
-            raise  Exception('not find music name of id : '+str(musicId))
-    def crawlLrc(self,musicId):
-        url = ('http://music.163.com/api/song/lyric?id=' + str(musicId) + '&lv=1&kv=1&tv=-1')
-        try:
-            return requests.get(url).text
-        except:
-            raise   Exception('crawl lyric Failed! Bad Responde from '+url)
-    def lrcFromFile(self,musicId):
-        self.cd('Lyric')
-        ### 直接字符串操作路径可能出错
-        try:
-            with open(str(musicId),'r') as f:   
-                return  f.read()
-        except:
-            try:
-                with open(str(musicId),'rb') as f:   
-                    return  f.read().decode('utf8',errors = 'ignore')  # key point
-            except:return self.crawlLrc(musicId)
     def getLyric(self,musicId):
-        lrc = self.lrcFromFile(musicId)
         name = self.id_mp[musicId]
-        lrc_lst = self.lrcSentencePt.findall(lrc)
-        if lrc_lst==[]:
-            try:
-                lrc = self.crawlLrc(musicId)
-                lrc_lst = self.lrcSentencePt.findall(lrc)
-            except:
-                print('fail to get lyric of music  '+name)
-                return  
-        self.cd('cached_网易云音乐/lyric')
-        with open(name +'.txt','w',encoding ='utf8') as f:
-            f.write(name+'\n\n')
-            f.write('\n'.join(lrc_lst))
-        return lrc_lst
-
-
-    def getInfoFromMp3(self,musicPath):
-        tag = MP3(musicPath,ID3 = EasyID3)
-        return dict(tag)
+        # 'http://music.163.com/api/song/lyric?id='
+        url = API+'type=lyric&id=' + str(musicId)
+        try:
+            lrc = requests.get(url).json()
+            file = os.path.join(LRCDIR,name +'.lrc')
+            if not os.path.exists(file):
+                with open(file,'w',encoding ='utf8') as f:
+                    f.write(str(lrc))
+        except Exception as e:
+            print(e,' Failed to get lyric of music '+name)
 
     def getMusic(self):
-        for i in self.absPaths:
+        for ct,i in enumerate(self.files):
             musicId  = self.decrypt(i)
-            print(self.id_mp[musicId])
+            print('[Music {}]'.format(ct+1).ljust(12)+self.id_mp[musicId])
             self.getLyric(musicId)
 
 
 if __name__=='__main__':
-	path = sys.argv[1:][0].strip()
-	#path = 'C:\\Users\\mbinary\\Desktop\\source\\\\myscripts\\Music1'
-	hd = netEaseMusic(path)
-	hd.getMusic()
+	if len(sys.argv) > 1: path = sys.argv[1].strip()
+	else : path = os.path.join(os.getcwd(),'Music1')
+	handler= netease_music(path)
+	handler.getMusic()