作者 Huahua [actionscript] 2007-02-25 22:17 (点击下载)

  1. #!/usr/bin/python
  2. # -*- coding: UTF-8 -*-
  3. # Author: Huang Jiahua <jhuangjiahua(at)gmail.com>
  4. # License: GNU LGPL
  5. # 
  6. # getlyric.py 
  7. # 百度歌词 下载工具
  8. # 用法，将本脚本放在 ~/bin/getlyric.py 
  9. # 加上可执行权限
  10. # 执行 getlyric.py  歌名 
  11. # 就可以显示 lrc 格式歌词
  12. #
  13. # getlyric.py  -p 歌名 
  14. # 表示去掉 lrc 标记
  15. #
  16. # getlyric.py  -c 歌名 
  17. # 表示重新下载歌词 
  18. #
  19.  
  20. """Get the Lyric from web
  21. call getlyric.getlyric(keyword) will return lyric for keyword
  22. the keyword will be title, artist, etc
  23. """
  24. __revision__ = '0.1'
  25.  
  26. import os,sys,re,urllib
  27.  
  28.  
  29. homedir = os.environ['HOME']
  30. lyricdir = os.path.join(homedir,'.lyrics')
  31. if not os.path.isdir(lyricdir): os.mkdir(lyricdir)
  32.  
  33.  
  34.  
  35. ## gbk2utf8(docurl(mkurl(urllib.quote(keyword.decode('utf8').encode('gbk')))))
  36.  
  37. def _gbk2utf8(stri):
  38.         '''iconv gbk -> utf8
  39.         errors be given to set  'ignore' or 'replace' handling scheme 
  40.         '''
  41.         stri = stri.decode('gb18030','replace').encode('utf8','replace')
  42.         return stri
  43.  
  44. def _utf82gbk(stri):
  45.         '''iconv utf8 -> gb18030
  46.         errors be given to set  'ignore' or 'replace' handling scheme 
  47.         '''
  48.         stri = stri.decode('utf8','replace').encode('gb18030','replace')
  49.         return stri
  50.  
  51. def _docurl(url):
  52.         '''get content from url
  53.         '''
  54.         return urllib.urlopen(url).read()
  55.  
  56. def _txt2url(txt):
  57.         '''urllib.quote('abc def') -> 'abc%20def'
  58.         '''
  59.         return urllib.quote(txt)
  60.  
  61. def get_baidulrc_list(keyword):
  62.         '''Get lyric list form mp3.baidu.com
  63.         return lyric url list
  64.         '''
  65.         url = 'http://mp3.baidu.com/m?f=ms&tn=baidump3lyric&ct=150994944&lf=2&rn=10&word='
  66.         url = url + _txt2url(_utf82gbk(keyword)) + '&lm=-1'
  67.         cont = _docurl(url)
  68.         ## find http://XXXX/XXXX.lrc from html
  69.         lrc_list=re.findall(r'\http\S*?\.lrc',cont)
  70.         return lrc_list
  71.  
  72.  
  73. def get_netbaidulrc(keyword):
  74.         '''Get lyric form mp3.baidu.com
  75.         return lyric formed
  76.         '''
  77.         lrc_list = get_baidulrc_list(keyword)
  78.         if (len(lrc_list) > 0):
  79.                 url = lrc_list[0]
  80.                 lyric = _gbk2utf8(_docurl(lrc_list[0]))
  81.                 return lyric
  82.  
  83.         return ''
  84.  
  85. def get_netlyric(keyword):
  86.         '''Get lyric content from network
  87.         return lyric formed
  88.         '''
  89.         return get_netbaidulrc(keyword)
  90.  
  91. def getlyric(keyword):
  92.         '''Get lyric content, with local cache
  93.         it will use local cache first
  94.         return lyric formed
  95.         '''
  96.         lyricfile = os.path.join(lyricdir, keyword+'.lrc')
  97.         if os.path.isfile(lyricfile):
  98.                 return open(lyricfile).read()
  99.         lyric = get_netlyric(keyword)
  100.         if (lyric==''): return ''
  101.         open(lyricfile,'w').write(lyric)
  102.         return lyric
  103.  
  104. def getlyric_plain(keyword):
  105.         '''get plain formatted lyric
  106.         the content removed [00:12.53][03:45.26]
  107.         it will use local cache first
  108.         return lyric plain
  109.         '''
  110.         lyric = getlyric(keyword)
  111.         lyric = re.sub(r'\[.*\]','',lyric)
  112.         return re.sub('\r\n\r\n','',lyric)
  113.  
  114. def regetlyric(keyword):
  115.         '''Reget lyric from network
  116.         it will reget and  sync local cache
  117.         return lyric plain
  118.         '''
  119.         lyricfile = os.path.join(lyricdir, keyword+'.lrc')
  120.         lyric = get_netlyric(keyword)
  121.         if (lyric==''): return getlyric(keyword)
  122.         open(lyricfile,'w').write(lyric)
  123.         return lyric
  124.  
  125. def regetlyric_plain(keyword):
  126.         '''Reget lyric from network
  127.         the content removed [00:12.53][03:45.26]
  128.         it will use local cache first
  129.         return get plain formatted lyric
  130.         '''
  131.         lyric = getlyric(keyword)
  132.         lyric = re.sub(r'\[.*\]','',lyric)
  133.         return re.sub('\r\n\r\n','',lyric)
  134.  
  135. ## test command
  136. if __name__=="__main__":
  137.         if (sys.argv[1] == '-h'):
  138.                 print 'Get the Lyric from web'
  139.                 print 'Usage:', sys.argv[0], ''''[options] KEYWORD\noptions:
  140.                 -h    print help
  141.                 -p    plain formatted
  142.                 -c    reget lyric from network'''
  143.         elif (sys.argv[1] == '-p'):
  144.                 print getlyric_plain(sys.argv[2])
  145.         elif (sys.argv[1] == '-c'):
  146.                 print regetlyric(sys.argv[2])
  148.         else:
  149.                 print getlyric(sys.argv[1])
  150.         keyword = sys.argv[1]
  153.

提交下面的校正或者修改. (点击这里开始一个新的帖子)
姓名: 在 cookie 中记住我的名字

屏幕抓图:(jpeg 或 png)