introducing Torrent dict, torrent info abstraction dict class

ox/mininova.py

@@ -1,14 +1,17 @@
 # -*- Mode: Python; -*-
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=2:sts=2:ts=2
+
+from datetime import datetime
 import re
 import socket
 from urllib import quote
 
 from oxutils.cache import getUrl, getUrlUnicode
-from oxutils import findRegexp, cache, stripTags, decodeHtml, getTorrentInfo
+from oxutils import findRegexp, cache, stripTags, decodeHtml, getTorrentInfo, intValue
 from oxutils.normalize import normalizeImdbId
 
+from torrent import Torrent
 
 socket.setdefaulttimeout(10.0)
 
@@ -74,7 +77,7 @@ def getData(mininovaId):
     torrent[key] = value
 
   torrent[u'title'] = findRegexp(data, '<title>(.*?):.*?</title>')
-  torrent[u'imdb'] = findRegexp(data, 'title/tt(\d{7})')
+  torrent[u'imdbId'] = findRegexp(data, 'title/tt(\d{7})')
   torrent[u'description'] = findRegexp(data, '<div id="description">(.*?)</div>')
   if torrent['description']:
     torrent['description'] = decodeHtml(stripTags(torrent['description'])).strip()
@@ -82,3 +85,16 @@ def getData(mininovaId):
   torrent[u'torrent_info'] = getTorrentInfo(t)
   return torrent
 
+
+class Mininova(Torrent):
+  def __init__(self, mininovaId):
+    self.data = getData(mininovaId)
+    Torrent.__init__(self)
+    ratio = self.data['share ratio'].split(',')
+    self['seeder'] = int(intValue(ratio[0].replace(',','').strip()))
+    self['leecher'] = int(intValue(ratio[1].replace(',','').strip()))
+    self['downloaded'] = int(intValue(self.data['downloads'].replace(',','').strip()))
+    published =  self.data['added on']
+    published = published.split(' +')[0]
+    self['published'] =  datetime.strptime(published, "%a, %d %b %Y %H:%M:%S")
+

ox/thepiratebay.py

@@ -2,6 +2,7 @@
 # -*- coding: utf-8 -*-
 # vi:si:et:sw=2:sts=2:ts=2
 
+from datetime import datetime
 import re
 import socket
 from urllib import quote, urlencode
@@ -11,6 +12,7 @@ from oxutils.cache import getUrl, getUrlUnicode
 from oxutils import findRegexp, cache, stripTags, decodeHtml, getTorrentInfo
 from oxutils.normalize import normalizeImdbId
 
+from torrent import Torrent
 
 socket.setdefaulttimeout(10.0)
 
@@ -68,6 +70,8 @@ def getData(piratebayId):
     'spoken language(s)': u'language',
     'texted language(s)': u'subtitle language',
     'by': u'uploader',
+    'leechers': 'leecher',
+    'seeders': 'seeder',
   }
   piratebayId = getId(piratebayId)
   torrent = dict()
@@ -79,7 +83,8 @@ def getData(piratebayId):
   torrent[u'title'] = findRegexp(data, '<title>(.*?) \(download torrent\) - TPB</title>')
   if not torrent[u'title']:
     return None
-  torrent[u'imdb'] = findRegexp(data, 'title/tt(\d{7})')
+  torrent[u'title'] = decodeHtml(torrent[u'title']).strip()
+  torrent[u'imdbId'] = findRegexp(data, 'title/tt(\d{7})')
   torrent[u'torrent_link']="http://torrents.thepiratebay.org/%s/%s.torrent" % (piratebayId, quote(torrent['title']))
   for d in re.compile('dt>(.*?):</dt>.*?<dd.*?>(.*?)</dd>', re.DOTALL).findall(data):
     key = d[0].lower().strip()
@@ -91,3 +96,12 @@ def getData(piratebayId):
   torrent[u'torrent_info'] = getTorrentInfo(t)
   return torrent
 
+
+class Thepiratebay(Torrent):
+  def __init__(self, piratebayId):
+    self.data = getData(piratebayId)
+    Torrent.__init__(self)
+    published =  self.data['uploaded']
+    published = published.replace(' GMT', '').split(' +')[0]
+    self['published'] =  datetime.strptime(published, "%Y-%m-%d %H:%M:%S")
+

ox/torrent.py

@@ -0,0 +1,35 @@
+# -*- Mode: Python; -*-
+# -*- coding: utf-8 -*-
+# vi:si:et:sw=2:sts=2:ts=2
+
+from oxutils import intValue
+
+
+class Torrent(dict):
+  _string_keys = ('id', 'title', 'description', 'infohash', 'torrent_link', 'comment_link', 
+                 'imdbId', 'announce', 'domain', 'published', 'language', 'subtitle language')
+  _int_keys = ('size', 'seeder', 'leecher', 'downloaded', 'files')
+  _dict_keys = ('torrent_info', )
+  _list_keys = ()
+  data = {}
+
+  def __init__(self):
+    for key in self._string_keys:
+      self[key] = self.data.get(key, u'')
+    for key in self._dict_keys:
+      self[key] = self.data.get(key, {})
+    for key in self._list_keys:
+      self[key] = self.data.get(key, [])
+    for key in self._int_keys:
+      value = self.data.get(key, -1)
+      if not isinstance(value, int):
+        value = int(intValue(value))
+      self[key] = value
+    self['infohash'] = self.data['torrent_info']['hash']
+    self['size'] = self.data['torrent_info']['size']
+    self['announce'] = self.data['torrent_info']['announce']
+    if 'files' in self.data['torrent_info']:
+      self['files'] = len(self.data['torrent_info']['files'])
+    else:
+      self['files'] =  1
+