subdivxget

   1 #!/usr/bin/env python
   2
   3 import sys
   4 import urllib
   5 import zipfile
   6 import subprocess
   7 import HTMLParser
   8
   9 class SubDivXQuery:
  10         def __init__(self, to_search, page_number):
  11                 self.host = "www.subdivx.com"
  12                 self.page = "/index.php"
  13                 self.down_page = "/bajar.php"
  14                 self.query = dict(
  15                         buscar = to_search,
  16                         pg = page_number,
  17                         accion = 5,
  18                         masdesc = '',
  19                         subtitulos = 1,
  20                         realiza_b = 1,
  21                 )
  22         @property
  23         def url(self):
  24                 return 'http://%s%s?%s' % (self.host, self.page,
  25                                 urllib.urlencode(self.query))
  26         @property
  27         def page_uri(self):
  28                 return self.page + '?' + urllib.urlencode(self.query)
  29         @property
  30         def down_uri(self):
  31                 return 'http://' + self.host + self.down_page
  32
  33
  34 class SubDivXHTMLParser(HTMLParser.HTMLParser):
  35
  36         IDLE = 1
  37         HEADER = 2
  38
  39         def __init__(self, down_uri):
  40                 HTMLParser.HTMLParser.__init__(self)
  41                 self.down_uri = down_uri
  42                 self.depth = 0
  43                 self.parsing = False
  44                 self.subs = []
  45                 self.attr = None
  46
  47         def handle_starttag(self, tag, attrs):
  48                 attrs = dict(attrs)
  49                 if tag == 'div' and attrs.get('id') == 'menu_detalle_buscador':
  50                         self.cur = dict()
  51                         self.subs.append(self.cur)
  52                         self.parsing = True
  53                 if not self.parsing:
  54                         return
  55                 if tag == 'div':
  56                         if attrs.get('id') == 'buscador_detalle':
  57                                 self.parsing = True
  58                         elif attrs.get('id') == 'buscador_detalle_sub':
  59                                 self.attr = 'desc'
  60                 elif tag == 'a':
  61                         if attrs.get('class') == 'titulo_menu_izq':
  62                                 self.attr = 'title'
  63                         elif attrs.get('href', '').startswith(self.down_uri):
  64                                 self.cur['url'] = attrs['href']
  65                 if self.parsing:
  66                         self.depth += 1
  67
  68         def handle_endtag(self, tag):
  69                 if self.parsing:
  70                         self.depth -= 1
  71                 if self.depth == 0:
  72                         self.parsing = False
  73
  74         def handle_data(self, data):
  75                 if self.parsing:
  76                         data = data.strip()
  77                         if self.attr is not None and data:
  78                                 self.cur[self.attr] = data
  79                                 self.attr = None
  80                         elif data in ('Downloads:', 'Cds:', 'Comentarios:',
  81                                         'Formato:'):
  82                                 self.attr = data[:-1].lower()
  83                         elif data == 'Subido por:':
  84                                 self.attr = 'autor'
  85                         elif data == 'el':
  86                                 self.attr = 'fecha'
  87
  88
  89 def subdivx_get_subs(query_str):
  90         page_number = 1
  91         subs = []
  92         while True:
  93                 query = SubDivXQuery(query_str, page_number)
  94                 url = urllib.urlopen(query.url)
  95                 parser = SubDivXHTMLParser(query.down_uri)
  96
  97                 for line in url:
  98                         parser.feed(line)
  99
 100                 url.close()
 101
 102                 if not parser.subs:
 103                         break
 104
 105                 subs.extend(parser.subs)
 106                 page_number += 1
 107
 108         return sorted(subs, key=lambda s: int(s['downloads']), reverse=True)
 109
 110
 111 def get_subs(query_str):
 112         zip_exts = ('application/zip',)
 113         rar_exts = ('application/rar', 'application/x-rar-compressed')
 114
 115         for sub in subdivx_get_subs(query_str):
 116                 print '''\
 117         - %(title)s (%(autor)s - %(fecha)s - %(downloads)s - %(comentarios)s)
 118           %(desc)s
 119                 DOWNLOADING ...
 120         ''' % sub
 121                 fname, headers = urllib.urlretrieve(sub['url'])
 122                 if 'Content-Type' in headers:
 123                         if headers['Content-Type'] in zip_exts:
 124                                 z = zipfile.ZipFile(fname, 'r')
 125                                 z.printdir()
 126                                 for fn in z.namelist():
 127                                         if fn.endswith('.srt') or fn.endswith('.sub'):
 128                                                 if '..' in fn or fn.startswith('/'):
 129                                                         print 'Dangerous file name:', fn
 130                                                         continue
 131                                                 print 'Extracting', fn, '...'
 132                                                 z.extract(fn)
 133                         elif headers['Content-Type'] in rar_exts:
 134                                 if subprocess.call(['rar', 'x', fname]) != 0:
 135                                         print 'Error unraring file %s' % fname
 136                         else:
 137                                 print 'Unrecognized file type:', headers['Content-Type']
 138                 else:
 139                         print 'No Content-Type!'
 140
 141
 142 for q in sys.argv[1:]:
 143         get_subs(q)
 144