vkget/vkget.py

   1 #!/usr/bin/env python2
   2
   3 # VKGet - CLI mp3 audio downloader for vkontakte.ru
   4 # Copyright (C) 2010-2011 Andrew Dunai
   5 #
   6 # This program is free software; you can redistribute it and/or modify
   7 # it under the terms of the GNU General Public License as published by
   8 # the Free Software Foundation; either version 2 of the License, or
   9 # (at your option) any later version.
  10 # You should have received a copy of the GNU General Public
  11 # License along with this library; if not, write to the
  12 # Free Software Foundation, Inc., 59 Temple Place - Suite 330,
  13 # Boston, MA 02111-1307, USA.
  14 #
  15
  16 import httplib, urllib
  17 import sys, os, re
  18
  19 if len(sys.argv)!=2:
  20         print "Usage: vkget.py <search query>"
  21         exit(1)
  22
  23 def remove_html_tags(data):
  24         p = re.compile(r'<.*?>')
  25         return p.sub('', data).replace('&nbsp;', ' ');
  26
  27 def fetchCookies(response):
  28 #       result=[]
  29         result=''
  30         i=0
  31         for header,content in response.getheaders():
  32                 if header.lower()=='set-cookie':
  33                         for cookie in content.split(', '):
  34                                 i+=1
  35                                 if i%2:
  36 #                                       result.append(cookie[0:cookie.index(';')])
  37                                         result+=cookie[0:cookie.index(';')]+'; '
  38 #                       result.append(content[0:content.index(" ")])
  39         return result[0:-2]
  40
  41 #conn = httplib.HTTPConnection("m.vk.com")
  42 #conn.request("POST", "/")
  43
  44 authParams = urllib.urlencode({
  45         'act':'login',
  46         'to':'',
  47         'from_host':'m.vk.com',
  48         'pda':1,
  49         'email':'awaken.seven@gmail.com',
  50         'pass':'andersonbot',
  51         })
  52
  53 headers = {"Content-type": "application/x-www-form-urlencoded", "Accept":"text/plain"}
  54
  55 print " > Logging in..."
  56 conn = httplib.HTTPConnection("login.vk.com:80")
  57 #conn.request("POST", "/?act=login&to=&from_host=m.vk.com&pda=1", authParams, authHeaders);
  58 conn.request("POST", "/", authParams, headers)
  59 response = conn.getresponse()
  60 html = response.read()
  61
  62 print " > Parsing post-authoriation cookies and proceeding login..."
  63 headers["Cookie"] = fetchCookies(response);
  64
  65 redirect=response.getheaders()[6][1]
  66 redirect=redirect[redirect.rfind('/'):1000]
  67
  68 conn = httplib.HTTPConnection("m.vk.com:80")
  69 conn.request("GET", redirect, '', headers);
  70 #print "GETTING" + redirect;
  71
  72 response = conn.getresponse()
  73 #print response.getheaders()
  74 html=response.read()
  75 #print html
  76
  77 headers["Cookie"] += fetchCookies(response)
  78
  79 #print " > ..."
  80
  81 ###conn = httplib.HTTPConnection("m.vk.com:80")
  82 ###conn.request("GET", "/", '', headers);
  83
  84 ###response = conn.getresponse()
  85 #print response.getheaders()
  86 ###html=response.read()
  87 #print html
  88
  89 #authParams2 = urllib.urlencode({
  90 #       's':s,
  91 #       'op':'slogin',
  92 #       'redirect':1,
  93 #       'expire':0,
  94 #       'to':''
  95 #       })
  96 #conn.close()
  97
  98 #print " > Authorizing..."
  99 #conn = httplib.HTTPConnection("m.vk.com:80")
 100 #conn.request("POST", "/login", authParams2, headers);
 101 #response = conn.getresponse()
 102 #headers["Cookie"] += fetchCookies(response)
 103 ##print headers["Cookie"];
 104
 105 #searchParams = urllib.urlencode({
 106 #       'from':'audio',
 107 #       'q':sys.argv[1],
 108 #       'section':'audio',
 109 #       })
 110
 111 print " > Searching for a track..."
 112 conn = httplib.HTTPConnection("vk.com")
 113 conn.request("GET", "/gsearch.php?from=audio&q="+sys.argv[1].replace(' ','+')+"&section=audio", "", headers)
 114 response = conn.getresponse()
 115 html = response.read()
 116
 117 print " > Fetching URL..."
 118 try:
 119         start=html.index('operate(')+9;
 120 except ValueError:
 121         print " > Nothing found :("
 122         exit(0)
 123 end=html.index(');', start);
 124 operate=html[start:end].split(',');
 125 operate[3]=operate[3][1:-1];
 126
 127 start=html.index('audioTitle')+15
 128 end=html.index('fl_l', start)-15;
 129 track=remove_html_tags(html[start:end])
 130
 131 url="http://cs"+operate[1]+".vkontakte.ru/u"+operate[2]+"/audio/"+operate[3]+".mp3"
 132
 133 print " > Done!"
 134 print " > Track name: "+track
 135 print " > Track URL: "+url
 136
 137 os.system('wget -c '+url+' -O "'+track+'.mp3"')