Moved search code into a subfolder

src/searchengine/nova/engines/btjunkie.py

@@ -0,0 +1,119 @@
+#VERSION: 2.23
+#AUTHORS: Christophe Dumez (chris@qbittorrent.org)
+
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+#    * Redistributions of source code must retain the above copyright notice,
+#      this list of conditions and the following disclaimer.
+#    * Redistributions in binary form must reproduce the above copyright
+#      notice, this list of conditions and the following disclaimer in the
+#      documentation and/or other materials provided with the distribution.
+#    * Neither the name of the author nor the names of its contributors may be
+#      used to endorse or promote products derived from this software without
+#      specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+
+from novaprinter import prettyPrinter
+from helpers import retrieve_url, download_file
+import sgmllib
+import re
+
+class btjunkie(object):
+  url = 'http://btjunkie.org'
+  name = 'btjunkie'
+  supported_categories = {'all': '0', 'movies': '6', 'tv': '4', 'music': '1', 'games': '2', 'anime': '7', 'software': '3'}
+
+  def __init__(self):
+    self.results = []
+    self.parser = self.SimpleSGMLParser(self.results, self.url)
+
+  def download_torrent(self, info):
+    print download_file(info)
+
+  class SimpleSGMLParser(sgmllib.SGMLParser):
+    def __init__(self, results, url, *args):
+      sgmllib.SGMLParser.__init__(self)
+      self.url = url
+      self.th_counter = None
+      self.current_item = None
+      self.results = results
+      
+    def start_a(self, attr):
+      params = dict(attr)
+      #print params
+      if params.has_key('href') and params['href'].startswith("http://dl.btjunkie.org/torrent"):
+        self.current_item = {}
+        self.th_counter = 0
+        self.current_item['link']=params['href'].strip()
+    
+    def handle_data(self, data):
+      if self.th_counter == 0:
+        if not self.current_item.has_key('name'):
+          self.current_item['name'] = ''
+        self.current_item['name']+= data.strip()
+      elif self.th_counter == 3:
+        if not self.current_item.has_key('size'):
+          self.current_item['size'] = ''
+        self.current_item['size']+= data.strip()
+      elif self.th_counter == 5:
+        if not self.current_item.has_key('seeds'):
+          self.current_item['seeds'] = ''
+        self.current_item['seeds']+= data.strip()
+      elif self.th_counter == 6:
+        if not self.current_item.has_key('leech'):
+          self.current_item['leech'] = ''
+        self.current_item['leech']+= data.strip()
+      
+    def start_th(self,attr):
+        if isinstance(self.th_counter,int):
+          self.th_counter += 1
+          if self.th_counter > 6:
+            self.th_counter = None
+            # Display item
+            if self.current_item:
+              self.current_item['engine_url'] = self.url
+              if not self.current_item['seeds'].isdigit():
+                self.current_item['seeds'] = 0
+              if not self.current_item['leech'].isdigit():
+                self.current_item['leech'] = 0
+              prettyPrinter(self.current_item)
+              self.results.append('a')
+
+  def search(self, what, cat='all'):
+    # Remove {} since btjunkie does not seem
+    # to handle those very well
+    what = what.replace('{', '').replace('}', '')
+    ret = []
+    i = 1
+    while True and i<11:
+      results = []
+      parser = self.SimpleSGMLParser(results, self.url)
+      dat = retrieve_url(self.url+'/search?q=%s&c=%s&o=52&p=%d'%(what, self.supported_categories[cat], i))
+      # Remove <font> tags from page
+      p = re.compile( '<[/]?font.*?>')
+      dat = p.sub('', dat)
+      #print dat
+      #return
+      results_re = re.compile('(?s)class="tab_results">.*')
+      for match in results_re.finditer(dat):
+        res_tab = match.group(0)
+        parser.feed(res_tab)
+        parser.close()
+        break
+      if len(results) <= 0:
+        break
+      i += 1
+      

src/searchengine/nova/engines/isohunt.py

@@ -0,0 +1,67 @@
+#VERSION: 1.32
+#AUTHORS: Christophe Dumez (chris@qbittorrent.org)
+
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+#    * Redistributions of source code must retain the above copyright notice,
+#      this list of conditions and the following disclaimer.
+#    * Redistributions in binary form must reproduce the above copyright
+#      notice, this list of conditions and the following disclaimer in the
+#      documentation and/or other materials provided with the distribution.
+#    * Neither the name of the author nor the names of its contributors may be
+#      used to endorse or promote products derived from this software without
+#      specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+from novaprinter import prettyPrinter
+import re
+from helpers import retrieve_url, download_file
+
+class isohunt(object):
+	url = 'http://isohunt.com'
+	name = 'isoHunt'
+	supported_categories = {'all': '', 'movies': '1', 'tv': '3', 'music': '2', 'games': '4', 'anime': '7', 'software': '5', 'pictures': '6', 'books': '9'}
+
+	def download_torrent(self, info):
+		print download_file(info)
+
+	def search(self, what, cat='all'):
+		# Remove {} since isohunt does not seem
+		# to handle those very well
+		what = what.replace('{', '').replace('}', '')
+		i = 1
+		while True and i<11:
+			res = 0
+			dat = retrieve_url(self.url+'/torrents.php?ihq=%s&iht=%s&ihp=%s&ihs1=2&iho1=d'%(what, self.supported_categories[cat],i))
+			# I know it's not very readable, but the SGML parser feels in pain
+			section_re = re.compile('(?s)id=link.*?</tr><tr')
+			torrent_re = re.compile('(?s)torrent_details/(?P<link>.*?[^/]+).*?'
+			'>(?P<name>.*?)</a>.*?'
+			'>(?P<size>[\d,\.]+\s+MB)</td>.*?'
+			'>(?P<seeds>\d+)</td>.*?'
+			'>(?P<leech>\d+)</td>')
+			for match in section_re.finditer(dat):
+				txt = match.group(0)
+				m = torrent_re.search(txt)
+				if m:
+					torrent_infos = m.groupdict()
+					torrent_infos['name'] = re.sub('<.*?>', '', torrent_infos['name'])
+					torrent_infos['engine_url'] = self.url
+					torrent_infos['link'] = 'http://isohunt.com/download/'+torrent_infos['link']
+					prettyPrinter(torrent_infos)
+					res = res + 1
+			if res == 0:
+				break
+			i = i + 1

src/searchengine/nova/engines/mininova.py

@@ -0,0 +1,111 @@
+#VERSION: 1.40
+#AUTHORS: Christophe Dumez (chris@qbittorrent.org)
+
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+#    * Redistributions of source code must retain the above copyright notice,
+#      this list of conditions and the following disclaimer.
+#    * Redistributions in binary form must reproduce the above copyright
+#      notice, this list of conditions and the following disclaimer in the
+#      documentation and/or other materials provided with the distribution.
+#    * Neither the name of the author nor the names of its contributors may be
+#      used to endorse or promote products derived from this software without
+#      specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+from novaprinter import prettyPrinter
+from helpers import retrieve_url, download_file
+import sgmllib
+import re
+
+class mininova(object):
+  # Mandatory properties
+  url = 'http://www.mininova.org'
+  name = 'Mininova'
+  supported_categories = {'all': '0', 'movies': '4', 'tv': '8', 'music': '5', 'games': '3', 'anime': '1', 'software': '7', 'pictures': '6', 'books': '2'}
+
+  def __init__(self):
+    self.results = []
+    self.parser = self.SimpleSGMLParser(self.results, self.url)
+
+  def download_torrent(self, info):
+    print download_file(info)
+
+  class SimpleSGMLParser(sgmllib.SGMLParser):
+    def __init__(self, results, url, *args):
+      sgmllib.SGMLParser.__init__(self)
+      self.url = url
+      self.td_counter = None
+      self.current_item = None
+      self.results = results
+      
+    def start_a(self, attr):
+      params = dict(attr)
+      #print params
+      if params.has_key('href') and params['href'].startswith("/get/"):
+        self.current_item = {}
+        self.td_counter = 0
+        self.current_item['link']=self.url+params['href'].strip()
+    
+    def handle_data(self, data):
+      if self.td_counter == 0:
+        if not self.current_item.has_key('name'):
+          self.current_item['name'] = ''
+        self.current_item['name']+= data
+      elif self.td_counter == 1:
+        if not self.current_item.has_key('size'):
+          self.current_item['size'] = ''
+        self.current_item['size']+= data.strip()
+      elif self.td_counter == 2:
+        if not self.current_item.has_key('seeds'):
+          self.current_item['seeds'] = ''
+        self.current_item['seeds']+= data.strip()
+      elif self.td_counter == 3:
+        if not self.current_item.has_key('leech'):
+          self.current_item['leech'] = ''
+        self.current_item['leech']+= data.strip()
+      
+    def start_td(self,attr):
+        if isinstance(self.td_counter,int):
+          self.td_counter += 1
+          if self.td_counter > 4:
+            self.td_counter = None
+            # Display item
+            if self.current_item:
+              self.current_item['engine_url'] = self.url
+              if not self.current_item['seeds'].isdigit():
+                self.current_item['seeds'] = 0
+              if not self.current_item['leech'].isdigit():
+                self.current_item['leech'] = 0
+              prettyPrinter(self.current_item)
+              self.results.append('a')
+
+  def search(self, what, cat='all'):
+    ret = []
+    i = 1
+    while True and i<11:
+      results = []
+      parser = self.SimpleSGMLParser(results, self.url)
+      dat = retrieve_url(self.url+'/search/%s/%s/seeds/%d'%(what, self.supported_categories[cat], i))
+      results_re = re.compile('(?s)<h1>Search results for.*')
+      for match in results_re.finditer(dat):
+        res_tab = match.group(0)
+        parser.feed(res_tab)
+        parser.close()
+        break
+      if len(results) <= 0:
+        break
+      i += 1
+      

src/searchengine/nova/engines/piratebay.py

@@ -0,0 +1,113 @@
+#VERSION: 1.30
+#AUTHORS: Fabien Devaux (fab@gnux.info)
+#CONTRIBUTORS: Christophe Dumez (chris@qbittorrent.org)
+
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+#    * Redistributions of source code must retain the above copyright notice,
+#      this list of conditions and the following disclaimer.
+#    * Redistributions in binary form must reproduce the above copyright
+#      notice, this list of conditions and the following disclaimer in the
+#      documentation and/or other materials provided with the distribution.
+#    * Neither the name of the author nor the names of its contributors may be
+#      used to endorse or promote products derived from this software without
+#      specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+from novaprinter import prettyPrinter
+import sgmllib
+from helpers import retrieve_url, download_file
+
+class piratebay(object):
+	url = 'http://thepiratebay.org'
+	name = 'The Pirate Bay'
+	supported_categories = {'all': '0', 'movies': '200', 'music': '100', 'games': '400', 'software': '300'}
+	
+	def __init__(self):
+		self.results = []
+		self.parser = self.SimpleSGMLParser(self.results, self.url)
+		
+	def download_torrent(self, info):
+		print download_file(info)
+
+	class SimpleSGMLParser(sgmllib.SGMLParser):
+		def __init__(self, results, url, *args):
+			sgmllib.SGMLParser.__init__(self)
+			self.td_counter = None
+			self.current_item = None
+			self.results = results
+			self.url = url
+			self.code = 0
+			self.in_name = None
+
+		def start_a(self, attr):
+			params = dict(attr)
+			if params['href'].startswith('/torrent/'):
+				self.current_item = {}
+				self.td_counter = 0
+				self.code = params['href'].split('/')[2]
+				self.in_name = True
+			elif params['href'].startswith('http://torrents.thepiratebay.org/%s'%self.code):
+				self.current_item['link']=params['href'].strip()
+				self.in_name = False
+
+		def handle_data(self, data):
+			if self.td_counter == 0:
+				if self.in_name:
+					if not self.current_item.has_key('name'):
+						self.current_item['name'] = ''
+					self.current_item['name']+= data.strip()
+				else:
+					#Parse size
+					if 'Size' in data:
+						self.current_item['size'] = data[data.index("Size")+5:]
+						self.current_item['size'] = self.current_item['size'][:self.current_item['size'].index(',')]
+			elif self.td_counter == 1:
+				if not self.current_item.has_key('seeds'):
+					self.current_item['seeds'] = ''
+				self.current_item['seeds']+= data.strip()
+			elif self.td_counter == 2:
+				if not self.current_item.has_key('leech'):
+					self.current_item['leech'] = ''
+				self.current_item['leech']+= data.strip()
+
+		def start_td(self,attr):
+			if isinstance(self.td_counter,int):
+				self.td_counter += 1
+				if self.td_counter > 3:
+					self.td_counter = None
+					# Display item
+					if self.current_item:
+						self.current_item['engine_url'] = self.url
+						if not self.current_item['seeds'].isdigit():
+							self.current_item['seeds'] = 0
+						if not self.current_item['leech'].isdigit():
+							self.current_item['leech'] = 0
+						prettyPrinter(self.current_item)
+						self.results.append('a')
+	def search(self, what, cat='all'):
+		ret = []
+		i = 0
+		order = 'se'
+		while True and i<11:
+			results = []
+			parser = self.SimpleSGMLParser(results, self.url)
+			dat = retrieve_url(self.url+'/search/%s/%u/7/%s' % (what, i, self.supported_categories[cat]))
+			print self.url+'/search/%s/%u/7/%s' % (what, i, self.supported_categories[cat])
+			parser.feed(dat)
+			parser.close()
+			if len(results) <= 0:
+				break
+			i += 1

src/searchengine/nova/engines/torrentdownloads.py

@@ -0,0 +1,140 @@
+#VERSION: 1.06
+#AUTHORS: Christophe Dumez (chris@qbittorrent.org)
+
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+#    * Redistributions of source code must retain the above copyright notice,
+#      this list of conditions and the following disclaimer.
+#    * Redistributions in binary form must reproduce the above copyright
+#      notice, this list of conditions and the following disclaimer in the
+#      documentation and/or other materials provided with the distribution.
+#    * Neither the name of the author nor the names of its contributors may be
+#      used to endorse or promote products derived from this software without
+#      specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+
+from novaprinter import prettyPrinter
+from helpers import retrieve_url
+import StringIO, gzip, urllib2, tempfile
+import sgmllib
+import re
+import os
+
+class torrentdownloads(object):
+  url = 'http://www.torrentdownloads.net'
+  name = 'TorrentDownloads'
+  supported_categories = {'all': '0', 'movies': '4', 'tv': '8', 'music': '5', 'games': '3', 'anime': '1', 'software': '7', 'books': '2'}
+
+  def __init__(self):
+    self.results = []
+    #self.parser = self.SimpleSGMLParser(self.results, self.url)
+
+  def download_torrent(self, url):
+    """ Download file at url and write it to a file, return the path to the file and the url """
+    file, path = tempfile.mkstemp()
+    file = os.fdopen(file, "w")
+    # Download url
+    req = urllib2.Request(url)
+    response = urllib2.urlopen(req)
+    dat = response.read()
+    # Check if it is gzipped
+    if dat[:2] == '\037\213':
+        # Data is gzip encoded, decode it
+        compressedstream = StringIO.StringIO(dat)
+        gzipper = gzip.GzipFile(fileobj=compressedstream)
+        extracted_data = gzipper.read()
+        dat = extracted_data
+        
+    # Write it to a file
+    file.write(dat.strip())
+    file.close()
+    # return file path
+    print path+" "+url
+
+  class SimpleSGMLParser(sgmllib.SGMLParser):
+    def __init__(self, results, url, what, *args):
+      sgmllib.SGMLParser.__init__(self)
+      self.url = url
+      self.li_counter = None
+      self.current_item = None
+      self.results = results
+      self.what = what.upper().split('+')
+      if len(self.what) == 0:
+        self.what = None
+      
+    def start_a(self, attr):
+      params = dict(attr)
+      #print params
+      if params.has_key('href') and params['href'].startswith("http://www.torrentdownloads.net/torrent/"):
+        self.current_item = {}
+        self.li_counter = 0
+        self.current_item['link']=params['href'].strip().replace('/torrent', '/download', 1)
+    
+    def handle_data(self, data):
+      if self.li_counter == 0:
+        if not self.current_item.has_key('name'):
+          self.current_item['name'] = ''
+        self.current_item['name']+= data
+      elif self.li_counter == 1:
+        if not self.current_item.has_key('size'):
+          self.current_item['size'] = ''
+        self.current_item['size']+= data.strip().replace(" ", " ")
+      elif self.li_counter == 2:
+        if not self.current_item.has_key('seeds'):
+          self.current_item['seeds'] = ''
+        self.current_item['seeds']+= data.strip()
+      elif self.li_counter == 3:
+        if not self.current_item.has_key('leech'):
+          self.current_item['leech'] = ''
+        self.current_item['leech']+= data.strip()
+      
+    def start_li(self,attr):
+        if isinstance(self.li_counter,int):
+          self.li_counter += 1
+          if self.li_counter > 3:
+            self.li_counter = None
+            # Display item
+            if self.current_item:
+              self.current_item['engine_url'] = self.url
+              if not self.current_item['seeds'].isdigit():
+                self.current_item['seeds'] = 0
+              if not self.current_item['leech'].isdigit():
+                self.current_item['leech'] = 0
+              # Search should use AND operator as a default
+              tmp = self.current_item['name'].upper();
+              if self.what is not None:
+                for w in self.what:
+                  if tmp.find(w) < 0: return
+              prettyPrinter(self.current_item)
+              self.results.append('a')
+
+  def search(self, what, cat='all'):
+    ret = []
+    i = 1
+    while i<11:
+      results = []
+      parser = self.SimpleSGMLParser(results, self.url, what)
+      dat = retrieve_url(self.url+'/search/?page=%d&search=%s&s_cat=%s&srt=seeds&pp=50&order=desc'%(i, what, self.supported_categories[cat]))
+      results_re = re.compile('(?s)<div class="torrentlist">.*')
+      for match in results_re.finditer(dat):
+        res_tab = match.group(0)
+        parser.feed(res_tab)
+        parser.close()
+        break
+      if len(results) <= 0:
+        break
+      i += 1
+      

src/searchengine/nova/engines/torrentreactor.py

@@ -0,0 +1,105 @@
+#VERSION: 1.21
+#AUTHORS: Gekko Dam Beer (gekko04@users.sourceforge.net)
+#CONTRIBUTORS: Christophe Dumez (chris@qbittorrent.org)
+
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+#    * Redistributions of source code must retain the above copyright notice,
+#      this list of conditions and the following disclaimer.
+#    * Redistributions in binary form must reproduce the above copyright
+#      notice, this list of conditions and the following disclaimer in the
+#      documentation and/or other materials provided with the distribution.
+#    * Neither the name of the author nor the names of its contributors may be
+#      used to endorse or promote products derived from this software without
+#      specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+from novaprinter import prettyPrinter
+import sgmllib
+from helpers import retrieve_url, download_file
+
+class torrentreactor(object):
+	url = 'http://www.torrentreactor.net'
+	name = 'TorrentReactor.Net'
+	supported_categories = {'all': '', 'movies': '5', 'tv': '8', 'music': '6', 'games': '3', 'anime': '1', 'software': '2'}
+
+	def download_torrent(self, info):
+		print download_file(info)
+		
+	class SimpleSGMLParser(sgmllib.SGMLParser):
+		def __init__(self, results, url, *args):
+			sgmllib.SGMLParser.__init__(self)
+			self.td_counter = None
+			self.current_item = None
+			self.results = results
+			self.id = None
+			self.url = url
+
+		def start_a(self, attr):
+			params = dict(attr)
+			if 'torrentreactor.net/download.php' in params['href']:
+				self.current_item = {}
+				self.td_counter = 0
+				self.current_item['link'] = params['href'].strip()
+
+		def handle_data(self, data):
+			if self.td_counter == 0:
+				if not self.current_item.has_key('name'):
+					self.current_item['name'] = ''
+				self.current_item['name']+= data.strip()
+			if self.td_counter == 1:
+				if not self.current_item.has_key('size'):
+					self.current_item['size'] = ''
+				self.current_item['size']+= data.strip()
+			elif self.td_counter == 2:
+				if not self.current_item.has_key('seeds'):
+					self.current_item['seeds'] = ''
+				self.current_item['seeds']+= data.strip()
+			elif self.td_counter == 3:
+				if not self.current_item.has_key('leech'):
+					self.current_item['leech'] = ''
+				self.current_item['leech']+= data.strip()
+
+		def start_td(self,attr):
+			if isinstance(self.td_counter,int):
+				self.td_counter += 1
+				if self.td_counter > 3:
+					self.td_counter = None
+					# add item to results
+					if self.current_item:
+						self.current_item['engine_url'] = self.url
+						if not self.current_item['seeds'].isdigit():
+							self.current_item['seeds'] = 0
+						if not self.current_item['leech'].isdigit():
+							self.current_item['leech'] = 0
+						prettyPrinter(self.current_item)
+						self.has_results = True
+						self.results.append('a')
+
+	def __init__(self):
+		self.results = []
+		self.parser = self.SimpleSGMLParser(self.results, self.url)
+
+	def search(self, what, cat='all'):
+		i = 0
+		while True and i<11:
+			results = []
+			parser = self.SimpleSGMLParser(results, self.url)
+			dat = retrieve_url(self.url+'/search.php?search=&words=%s&cid=%s&sid=&type=2&orderby=a.seeds&asc=0&skip=%s'%(what, self.supported_categories[cat], (i*35)))
+			parser.feed(dat)
+			parser.close()
+			if len(results) <= 0:
+				break
+			i += 1

src/searchengine/nova/engines/versions.txt

@@ -0,0 +1,7 @@
+isohunt: 1.32
+torrentreactor: 1.21
+btjunkie: 2.23
+mininova: 1.40
+piratebay: 1.30
+vertor: 1.1
+torrentdownloads: 1.06

src/searchengine/nova/engines/vertor.py

@@ -0,0 +1,124 @@
+#VERSION: 1.1
+#AUTHORS: Christophe Dumez (chris@qbittorrent.org)
+
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+#    * Redistributions of source code must retain the above copyright notice,
+#      this list of conditions and the following disclaimer.
+#    * Redistributions in binary form must reproduce the above copyright
+#      notice, this list of conditions and the following disclaimer in the
+#      documentation and/or other materials provided with the distribution.
+#    * Neither the name of the author nor the names of its contributors may be
+#      used to endorse or promote products derived from this software without
+#      specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+
+from novaprinter import prettyPrinter
+from helpers import retrieve_url, download_file
+import sgmllib
+import re
+
+class vertor(object):
+  url = 'http://www.vertor.com'
+  name = 'vertor'
+  supported_categories = {'all': '0', 'movies': '5', 'tv': '8', 'music': '6', 'games': '3', 'anime': '1', 'software': '2'}
+
+  def __init__(self):
+    self.results = []
+    self.parser = self.SimpleSGMLParser(self.results, self.url)
+
+  def download_torrent(self, info):
+    print download_file(info)
+
+  class SimpleSGMLParser(sgmllib.SGMLParser):
+    def __init__(self, results, url, *args):
+      sgmllib.SGMLParser.__init__(self)
+      self.url = url
+      self.td_counter = None
+      self.current_item = None
+      self.results = results
+      self.in_name = False
+      self.outside_td = True;
+      
+    def start_a(self, attr):
+      params = dict(attr)
+      #print params
+      if params.has_key('href') and params['href'].startswith("http://www.vertor.com/index.php?mod=download"):
+        self.current_item = {}
+        self.td_counter = 0
+        self.current_item['link']=params['href'].strip()
+      elif self.td_counter == 0 and params.has_key('href') and params['href'].startswith("/torrents/") \
+      and not self.current_item.has_key('name'):
+	self.in_name = True
+        
+    def end_a(self):
+      if self.in_name:
+	self.in_name = False
+    
+    def handle_data(self, data):
+      if self.in_name:
+        if not self.current_item.has_key('name'):
+          self.current_item['name'] = ''
+        self.current_item['name']+= data.strip()
+      elif self.td_counter == 2 and not self.outside_td:
+        if not self.current_item.has_key('size'):
+          self.current_item['size'] = ''
+        self.current_item['size']+= data.strip()
+      elif self.td_counter == 4 and not self.outside_td:
+        if not self.current_item.has_key('seeds'):
+          self.current_item['seeds'] = ''
+        self.current_item['seeds']+= data.strip()
+      elif self.td_counter == 5 and not self.outside_td:
+        if not self.current_item.has_key('leech'):
+          self.current_item['leech'] = ''
+        self.current_item['leech']+= data.strip()
+        
+    def end_td(self):
+      self.outside_td = True
+      
+    def start_td(self,attr):
+        if isinstance(self.td_counter,int):
+	  self.outside_td = False
+          self.td_counter += 1
+          if self.td_counter > 5:
+            self.td_counter = None
+            # Display item
+            if self.current_item:
+              self.current_item['engine_url'] = self.url
+              if not self.current_item['seeds'].isdigit():
+                self.current_item['seeds'] = 0
+              if not self.current_item['leech'].isdigit():
+                self.current_item['leech'] = 0
+              prettyPrinter(self.current_item)
+              self.results.append('a')
+
+  def search(self, what, cat='all'):
+    ret = []
+    i = 0
+    while True and i<11:
+      results = []
+      parser = self.SimpleSGMLParser(results, self.url)
+      dat = retrieve_url(self.url+'/index.php?mod=search&words=%s&cid=%s&orderby=a.seeds&asc=0&search=&exclude=&p=%d'%(what, self.supported_categories[cat], i))
+      results_re = re.compile('(?s)<table class="listing">.*')
+      for match in results_re.finditer(dat):
+        res_tab = match.group(0)
+        parser.feed(res_tab)
+        parser.close()
+        break
+      if len(results) <= 0:
+        break
+      i += 1
+      

src/searchengine/nova/helpers.py

@@ -0,0 +1,99 @@
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+#    * Redistributions of source code must retain the above copyright notice,
+#      this list of conditions and the following disclaimer.
+#    * Redistributions in binary form must reproduce the above copyright
+#      notice, this list of conditions and the following disclaimer in the
+#      documentation and/or other materials provided with the distribution.
+#    * Neither the name of the author nor the names of its contributors may be
+#      used to endorse or promote products derived from this software without
+#      specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+#VERSION: 1.31
+
+# Author:
+#  Christophe DUMEZ (chris@qbittorrent.org)
+
+import re, htmlentitydefs
+import tempfile
+import os
+import StringIO, gzip, urllib2
+import socket
+import socks
+import re
+
+# SOCKS5 Proxy support
+if os.environ.has_key("sock_proxy") and len(os.environ["sock_proxy"].strip()) > 0:
+    proxy_str = os.environ["sock_proxy"].strip()
+    m=re.match(r"^(?:(?P<username>[^:]+):(?P<password>[^@]+)@)?(?P<host>[^:]+):(?P<port>\w+)$", proxy_str)
+    if m is not None:
+        socks.setdefaultproxy(socks.PROXY_TYPE_SOCKS5, m.group('host'), int(m.group('port')), True, m.group('username'), m.group('password'))
+        socket.socket = socks.socksocket
+
+def htmlentitydecode(s):
+    # First convert alpha entities (such as &eacute;)
+    # (Inspired from http://mail.python.org/pipermail/python-list/2007-June/443813.html)
+    def entity2char(m):
+        entity = m.group(1)
+        if entity in htmlentitydefs.name2codepoint:
+            return unichr(htmlentitydefs.name2codepoint[entity])
+        return u" "  # Unknown entity: We replace with a space.
+    t = re.sub(u'&(%s);' % u'|'.join(htmlentitydefs.name2codepoint), entity2char, s)
+  
+    # Then convert numerical entities (such as &#233;)
+    t = re.sub(u'&#(\d+);', lambda x: unichr(int(x.group(1))), t)
+   
+    # Then convert hexa entities (such as &#x00E9;)
+    return re.sub(u'&#x(\w+);', lambda x: unichr(int(x.group(1),16)), t)
+    
+def retrieve_url(url):
+    """ Return the content of the url page as a string """
+    req = urllib2.Request(url)
+    response = urllib2.urlopen(req)
+    dat = response.read()
+    info = response.info()
+    charset = 'utf-8'
+    try:
+        ignore, charset = info['Content-Type'].split('charset=')
+    except:
+        pass
+    dat = dat.decode(charset, 'replace')
+    dat = htmlentitydecode(dat)
+    return dat.encode('utf-8', 'replace')
+
+def download_file(url, referer=None):
+    """ Download file at url and write it to a file, return the path to the file and the url """
+    file, path = tempfile.mkstemp()
+    file = os.fdopen(file, "w")
+    # Download url
+    req = urllib2.Request(url)
+    if referer is not None:
+        req.add_header('referer', referer)
+    response = urllib2.urlopen(req)
+    dat = response.read()
+    # Check if it is gzipped
+    if dat[:2] == '\037\213':
+        # Data is gzip encoded, decode it
+        compressedstream = StringIO.StringIO(dat)
+        gzipper = gzip.GzipFile(fileobj=compressedstream)
+        extracted_data = gzipper.read()
+        dat = extracted_data
+        
+    # Write it to a file
+    file.write(dat)
+    file.close()
+    # return file path
+    return path+" "+url

src/searchengine/nova/nova2.py

@@ -0,0 +1,157 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+#    * Redistributions of source code must retain the above copyright notice,
+#      this list of conditions and the following disclaimer.
+#    * Redistributions in binary form must reproduce the above copyright
+#      notice, this list of conditions and the following disclaimer in the
+#      documentation and/or other materials provided with the distribution.
+#    * Neither the name of the author nor the names of its contributors may be
+#      used to endorse or promote products derived from this software without
+#      specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+
+#VERSION: 1.23
+
+# Author:
+#  Fabien Devaux <fab AT gnux DOT info>
+# Contributors:
+#  Christophe Dumez <chris@qbittorrent.org> (qbittorrent integration)
+#  Thanks to gab #gcu @ irc.freenode.net (multipage support on PirateBay)
+#  Thanks to Elias <gekko04@users.sourceforge.net> (torrentreactor and isohunt search engines)
+#
+# Licence: BSD
+
+import sys
+import threading
+import os
+import glob
+
+THREADED = True
+CATEGORIES = ('all', 'movies', 'tv', 'music', 'games', 'anime', 'software', 'pictures', 'books')
+
+################################################################################
+# Every engine should have a "search" method taking
+# a space-free string as parameter (ex. "family+guy")
+# it should call prettyPrinter() with a dict as parameter.
+# The keys in the dict must be: link,name,size,seeds,leech,engine_url
+# As a convention, try to list results by decrasing number of seeds or similar
+################################################################################
+
+supported_engines = []
+
+engines = glob.glob(os.path.join(os.path.dirname(__file__), 'engines','*.py'))
+for engine in engines:
+	e = engine.split(os.sep)[-1][:-3]
+	if len(e.strip()) == 0: continue
+	if e.startswith('_'): continue
+	try:
+		exec "from engines.%s import %s"%(e,e)
+		supported_engines.append(e)
+	except:
+		pass
+
+def engineToXml(short_name):
+	xml = "<%s>\n"%short_name
+	exec "engine = %s()"%short_name
+	xml += "<name>%s</name>\n"%engine.name
+	xml += "<url>%s</url>\n"%engine.url
+	xml += "<categories>"
+	if hasattr(engine, 'supported_categories'):
+		supported_categories = engine.supported_categories.keys()
+		supported_categories.remove('all')
+		xml += " ".join(supported_categories)
+	xml += "</categories>\n"
+	xml += "</%s>\n"%short_name
+	return xml
+
+def displayCapabilities():
+	"""
+	Display capabilities in XML format
+	<capabilities>
+	  <engine_short_name>
+	    <name>long name</name>
+	    <url>http://example.com</url>
+	    <categories>movies music games</categories>
+	  </engine_short_name>
+	</capabilities>
+	"""
+	xml = "<capabilities>"
+	for short_name in supported_engines:
+		xml += engineToXml(short_name)
+	xml += "</capabilities>"
+	print xml
+
+class EngineLauncher(threading.Thread):
+	def __init__(self, engine, what, cat='all'):
+		threading.Thread.__init__(self)
+		self.engine = engine
+		self.what = what
+		self.cat = cat
+	def run(self):
+		if hasattr(self.engine, 'supported_categories'):
+			if self.cat == 'all' or self.cat in self.engine.supported_categories.keys():
+				self.engine.search(self.what, self.cat)
+		elif self.cat == 'all':
+				self.engine.search(self.what)
+
+if __name__ == '__main__':
+	if len(sys.argv) < 2:
+		raise SystemExit('./nova2.py [all|engine1[,engine2]*] <category> <keywords>\navailable engines: %s'%
+				(','.join(supported_engines)))
+
+	if len(sys.argv) == 2:
+		if sys.argv[1] == "--capabilities":
+			displayCapabilities()
+			sys.exit(0)
+		else:
+			raise SystemExit('./nova.py [all|engine1[,engine2]*] <category> <keywords>\navailable engines: %s'%
+					(','.join(supported_engines)))
+
+	engines_list = [e.lower() for e in sys.argv[1].strip().split(',')]
+
+	if 'all' in engines_list:
+		engines_list = supported_engines
+		
+	cat = sys.argv[2].lower()
+	
+	if cat not in CATEGORIES:
+		raise SystemExit('Invalid category!')
+	
+	what = '+'.join(sys.argv[3:])
+	
+	threads = []
+	for engine in engines_list:
+		try:
+			if THREADED:
+				exec "l = EngineLauncher(%s(), what, cat)"%engine
+				threads.append(l)
+				l.start()
+			else:
+				exec "e = %s()"%engine
+				if hasattr(engine, 'supported_categories'):
+					if cat == 'all' or cat in e.supported_categories.keys():
+						e.search(what, cat)
+				elif self.cat == 'all':
+						e.search(what)
+						engine().search(what, cat)
+		except:
+			pass
+	if THREADED:
+		for t in threads:
+			t.join()

src/searchengine/nova/nova2dl.py

@@ -0,0 +1,64 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+#    * Redistributions of source code must retain the above copyright notice,
+#      this list of conditions and the following disclaimer.
+#    * Redistributions in binary form must reproduce the above copyright
+#      notice, this list of conditions and the following disclaimer in the
+#      documentation and/or other materials provided with the distribution.
+#    * Neither the name of the author nor the names of its contributors may be
+#      used to endorse or promote products derived from this software without
+#      specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+#VERSION: 1.10
+
+# Author:
+#  Christophe DUMEZ (chris@qbittorrent.org)
+
+import sys
+import os
+import glob
+from helpers import download_file
+
+supported_engines = dict()
+
+engines = glob.glob(os.path.join(os.path.dirname(__file__), 'engines','*.py'))
+for engine in engines:
+	e = engine.split(os.sep)[-1][:-3]
+	if len(e.strip()) == 0: continue
+	if e.startswith('_'): continue
+	try:
+		exec "from engines.%s import %s"%(e,e)
+		exec "engine_url = %s.url"%e
+		supported_engines[engine_url] = e
+	except:
+		pass
+
+if __name__ == '__main__':
+	if len(sys.argv) < 3:
+		raise SystemExit('./nova2dl.py engine_url download_parameter')
+	engine_url = sys.argv[1].strip()
+	download_param = sys.argv[2].strip()
+	if engine_url not in supported_engines.keys():
+		raise SystemExit('./nova2dl.py: this engine_url was not recognized')
+	exec "engine = %s()"%supported_engines[engine_url]
+	if hasattr(engine, 'download_torrent'):
+		engine.download_torrent(download_param)
+	else:
+		print download_file(download_param)
+	sys.exit(0)

src/searchengine/nova/novaprinter.py

@@ -0,0 +1,66 @@
+#VERSION: 1.33
+
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+#
+#    * Redistributions of source code must retain the above copyright notice,
+#      this list of conditions and the following disclaimer.
+#    * Redistributions in binary form must reproduce the above copyright
+#      notice, this list of conditions and the following disclaimer in the
+#      documentation and/or other materials provided with the distribution.
+#    * Neither the name of the author nor the names of its contributors may be
+#      used to endorse or promote products derived from this software without
+#      specific prior written permission.
+#
+# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+import sys, codecs
+
+# Force UTF-8 printing
+sys.stdout = codecs.getwriter('utf-8')(sys.stdout)
+
+def prettyPrinter(dictionary):
+	# Convert everything to unicode for safe printing
+	for key,value in dictionary.items():
+		if isinstance(dictionary[key], str):
+			dictionary[key] = unicode(dictionary[key], 'utf-8')
+	dictionary['size'] = anySizeToBytes(dictionary['size'])
+	print u"%s|%s|%s|%s|%s|%s"%(dictionary['link'],dictionary['name'],dictionary['size'],dictionary['seeds'],dictionary['leech'],dictionary['engine_url'])
+
+def anySizeToBytes(size_string):
+	"""
+	Convert a string like '1 KB' to '1024' (bytes)
+	"""
+	# separate integer from unit
+	try:
+		size, unit = size_string.split()
+	except:
+		try:
+			size = size_string.strip()
+			unit = ''.join([c for c in size if c.isalpha()])
+			if len(unit) > 0:
+				size = size[:-len(unit)]
+		except:
+			return -1
+	if len(size) == 0:
+		return -1
+	size = float(size)
+	if len(unit) == 0:
+		return int(size)
+	short_unit = unit.upper()[0]
+
+	# convert
+	units_dict = { 'T': 40, 'G': 30, 'M': 20, 'K': 10 }
+	if units_dict.has_key( short_unit ):
+		size = size * 2**units_dict[short_unit]
+	return int(size)

src/searchengine/nova/socks.py

@@ -0,0 +1,387 @@
+"""SocksiPy - Python SOCKS module.
+Version 1.00
+
+Copyright 2006 Dan-Haim. All rights reserved.
+
+Redistribution and use in source and binary forms, with or without modification,
+are permitted provided that the following conditions are met:
+1. Redistributions of source code must retain the above copyright notice, this
+   list of conditions and the following disclaimer.
+2. Redistributions in binary form must reproduce the above copyright notice,
+   this list of conditions and the following disclaimer in the documentation
+   and/or other materials provided with the distribution.
+3. Neither the name of Dan Haim nor the names of his contributors may be used
+   to endorse or promote products derived from this software without specific
+   prior written permission.
+   
+THIS SOFTWARE IS PROVIDED BY DAN HAIM "AS IS" AND ANY EXPRESS OR IMPLIED
+WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO
+EVENT SHALL DAN HAIM OR HIS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
+INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA
+OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
+OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMANGE.
+
+
+This module provides a standard socket-like interface for Python
+for tunneling connections through SOCKS proxies.
+
+"""
+
+import socket
+import struct
+
+PROXY_TYPE_SOCKS4 = 1
+PROXY_TYPE_SOCKS5 = 2
+PROXY_TYPE_HTTP = 3
+
+_defaultproxy = None
+_orgsocket = socket.socket
+
+class ProxyError(Exception):
+	def __init__(self, value):
+		self.value = value
+	def __str__(self):
+		return repr(self.value)
+
+class GeneralProxyError(ProxyError):
+	def __init__(self, value):
+		self.value = value
+	def __str__(self):
+		return repr(self.value)
+
+class Socks5AuthError(ProxyError):
+	def __init__(self, value):
+		self.value = value
+	def __str__(self):
+		return repr(self.value)
+
+class Socks5Error(ProxyError):
+	def __init__(self, value):
+		self.value = value
+	def __str__(self):
+		return repr(self.value)
+
+class Socks4Error(ProxyError):
+	def __init__(self, value):
+		self.value = value
+	def __str__(self):
+		return repr(self.value)
+
+class HTTPError(ProxyError):
+	def __init__(self, value):
+		self.value = value
+	def __str__(self):
+		return repr(self.value)
+
+_generalerrors = ("success",
+		   "invalid data",
+		   "not connected",
+		   "not available",
+		   "bad proxy type",
+		   "bad input")
+
+_socks5errors = ("succeeded",
+		  "general SOCKS server failure",
+		  "connection not allowed by ruleset",
+		  "Network unreachable",
+		  "Host unreachable",
+		  "Connection refused",
+		  "TTL expired",
+		  "Command not supported",
+		  "Address type not supported",
+		  "Unknown error")
+
+_socks5autherrors = ("succeeded",
+		      "authentication is required",
+		      "all offered authentication methods were rejected",
+		      "unknown username or invalid password",
+		      "unknown error")
+
+_socks4errors = ("request granted",
+		  "request rejected or failed",
+		  "request rejected because SOCKS server cannot connect to identd on the client",
+		  "request rejected because the client program and identd report different user-ids",
+		  "unknown error")
+
+def setdefaultproxy(proxytype=None,addr=None,port=None,rdns=True,username=None,password=None):
+	"""setdefaultproxy(proxytype, addr[, port[, rdns[, username[, password]]]])
+	Sets a default proxy which all further socksocket objects will use,
+	unless explicitly changed.
+	"""
+	global _defaultproxy
+	_defaultproxy = (proxytype,addr,port,rdns,username,password)
+	
+class socksocket(socket.socket):
+	"""socksocket([family[, type[, proto]]]) -> socket object
+	
+	Open a SOCKS enabled socket. The parameters are the same as
+	those of the standard socket init. In order for SOCKS to work,
+	you must specify family=AF_INET, type=SOCK_STREAM and proto=0.
+	"""
+	
+	def __init__(self, family=socket.AF_INET, type=socket.SOCK_STREAM, proto=0, _sock=None):
+		_orgsocket.__init__(self,family,type,proto,_sock)
+		if _defaultproxy != None:
+			self.__proxy = _defaultproxy
+		else:
+			self.__proxy = (None, None, None, None, None, None)
+		self.__proxysockname = None
+		self.__proxypeername = None
+	
+	def __recvall(self, bytes):
+		"""__recvall(bytes) -> data
+		Receive EXACTLY the number of bytes requested from the socket.
+		Blocks until the required number of bytes have been received.
+		"""
+		data = ""
+		while len(data) < bytes:
+			data = data + self.recv(bytes-len(data))
+		return data
+	
+	def setproxy(self,proxytype=None,addr=None,port=None,rdns=True,username=None,password=None):
+		"""setproxy(proxytype, addr[, port[, rdns[, username[, password]]]])
+		Sets the proxy to be used.
+		proxytype -	The type of the proxy to be used. Three types
+				are supported: PROXY_TYPE_SOCKS4 (including socks4a),
+				PROXY_TYPE_SOCKS5 and PROXY_TYPE_HTTP
+		addr -		The address of the server (IP or DNS).
+		port -		The port of the server. Defaults to 1080 for SOCKS
+				servers and 8080 for HTTP proxy servers.
+		rdns -		Should DNS queries be preformed on the remote side
+				(rather than the local side). The default is True.
+				Note: This has no effect with SOCKS4 servers.
+		username -	Username to authenticate with to the server.
+				The default is no authentication.
+		password -	Password to authenticate with to the server.
+				Only relevant when username is also provided.
+		"""
+		self.__proxy = (proxytype,addr,port,rdns,username,password)
+	
+	def __negotiatesocks5(self,destaddr,destport):
+		"""__negotiatesocks5(self,destaddr,destport)
+		Negotiates a connection through a SOCKS5 server.
+		"""
+		# First we'll send the authentication packages we support.
+		if (self.__proxy[4]!=None) and (self.__proxy[5]!=None):
+			# The username/password details were supplied to the
+			# setproxy method so we support the USERNAME/PASSWORD
+			# authentication (in addition to the standard none).
+			self.sendall("\x05\x02\x00\x02")
+		else:
+			# No username/password were entered, therefore we
+			# only support connections with no authentication.
+			self.sendall("\x05\x01\x00")
+		# We'll receive the server's response to determine which
+		# method was selected
+		chosenauth = self.__recvall(2)
+		if chosenauth[0] != "\x05":
+			self.close()
+			raise GeneralProxyError((1,_generalerrors[1]))
+		# Check the chosen authentication method
+		if chosenauth[1] == "\x00":
+			# No authentication is required
+			pass
+		elif chosenauth[1] == "\x02":
+			# Okay, we need to perform a basic username/password
+			# authentication.
+			self.sendall("\x01" + chr(len(self.__proxy[4])) + self.__proxy[4] + chr(len(self.proxy[5])) + self.__proxy[5])
+			authstat = self.__recvall(2)
+			if authstat[0] != "\x01":
+				# Bad response
+				self.close()
+				raise GeneralProxyError((1,_generalerrors[1]))
+			if authstat[1] != "\x00":
+				# Authentication failed
+				self.close()
+				raise Socks5AuthError,((3,_socks5autherrors[3]))
+			# Authentication succeeded
+		else:
+			# Reaching here is always bad
+			self.close()
+			if chosenauth[1] == "\xFF":
+				raise Socks5AuthError((2,_socks5autherrors[2]))
+			else:
+				raise GeneralProxyError((1,_generalerrors[1]))
+		# Now we can request the actual connection
+		req = "\x05\x01\x00"
+		# If the given destination address is an IP address, we'll
+		# use the IPv4 address request even if remote resolving was specified.
+		try:
+			ipaddr = socket.inet_aton(destaddr)
+			req = req + "\x01" + ipaddr
+		except socket.error:
+			# Well it's not an IP number,  so it's probably a DNS name.
+			if self.__proxy[3]==True:
+				# Resolve remotely
+				ipaddr = None
+				req = req + "\x03" + chr(len(destaddr)) + destaddr
+			else:
+				# Resolve locally
+				ipaddr = socket.inet_aton(socket.gethostbyname(destaddr))
+				req = req + "\x01" + ipaddr
+		req = req + struct.pack(">H",destport)
+		self.sendall(req)
+		# Get the response
+		resp = self.__recvall(4)
+		if resp[0] != "\x05":
+			self.close()
+			raise GeneralProxyError((1,_generalerrors[1]))
+		elif resp[1] != "\x00":
+			# Connection failed
+			self.close()
+			if ord(resp[1])<=8:
+				raise Socks5Error(ord(resp[1]),_generalerrors[ord(resp[1])])
+			else:
+				raise Socks5Error(9,_generalerrors[9])
+		# Get the bound address/port
+		elif resp[3] == "\x01":
+			boundaddr = self.__recvall(4)
+		elif resp[3] == "\x03":
+			resp = resp + self.recv(1)
+			boundaddr = self.__recvall(resp[4])
+		else:
+			self.close()
+			raise GeneralProxyError((1,_generalerrors[1]))
+		boundport = struct.unpack(">H",self.__recvall(2))[0]
+		self.__proxysockname = (boundaddr,boundport)
+		if ipaddr != None:
+			self.__proxypeername = (socket.inet_ntoa(ipaddr),destport)
+		else:
+			self.__proxypeername = (destaddr,destport)
+	
+	def getproxysockname(self):
+		"""getsockname() -> address info
+		Returns the bound IP address and port number at the proxy.
+		"""
+		return self.__proxysockname
+	
+	def getproxypeername(self):
+		"""getproxypeername() -> address info
+		Returns the IP and port number of the proxy.
+		"""
+		return _orgsocket.getpeername(self)
+	
+	def getpeername(self):
+		"""getpeername() -> address info
+		Returns the IP address and port number of the destination
+		machine (note: getproxypeername returns the proxy)
+		"""
+		return self.__proxypeername
+	
+	def __negotiatesocks4(self,destaddr,destport):
+		"""__negotiatesocks4(self,destaddr,destport)
+		Negotiates a connection through a SOCKS4 server.
+		"""
+		# Check if the destination address provided is an IP address
+		rmtrslv = False
+		try:
+			ipaddr = socket.inet_aton(destaddr)
+		except socket.error:
+			# It's a DNS name. Check where it should be resolved.
+			if self.__proxy[3]==True:
+				ipaddr = "\x00\x00\x00\x01"
+				rmtrslv = True
+			else:
+				ipaddr = socket.inet_aton(socket.gethostbyname(destaddr))
+		# Construct the request packet
+		req = "\x04\x01" + struct.pack(">H",destport) + ipaddr
+		# The username parameter is considered userid for SOCKS4
+		if self.__proxy[4] != None:
+			req = req + self.__proxy[4]
+		req = req + "\x00"
+		# DNS name if remote resolving is required
+		# NOTE: This is actually an extension to the SOCKS4 protocol
+		# called SOCKS4A and may not be supported in all cases.
+		if rmtrslv==True:
+			req = req + destaddr + "\x00"
+		self.sendall(req)
+		# Get the response from the server
+		resp = self.__recvall(8)
+		if resp[0] != "\x00":
+			# Bad data
+			self.close()
+			raise GeneralProxyError((1,_generalerrors[1]))
+		if resp[1] != "\x5A":
+			# Server returned an error
+			self.close()
+			if ord(resp[1]) in (91,92,93):
+				self.close()
+				raise Socks4Error((ord(resp[1]),_socks4errors[ord(resp[1])-90]))
+			else:
+				raise Socks4Error((94,_socks4errors[4]))
+		# Get the bound address/port
+		self.__proxysockname = (socket.inet_ntoa(resp[4:]),struct.unpack(">H",resp[2:4])[0])
+		if rmtrslv != None:
+			self.__proxypeername = (socket.inet_ntoa(ipaddr),destport)
+		else:
+			self.__proxypeername = (destaddr,destport)
+	
+	def __negotiatehttp(self,destaddr,destport):
+		"""__negotiatehttp(self,destaddr,destport)
+		Negotiates a connection through an HTTP server.
+		"""
+		# If we need to resolve locally, we do this now
+		if self.__proxy[3] == False:
+			addr = socket.gethostbyname(destaddr)
+		else:
+			addr = destaddr
+		self.sendall("CONNECT " + addr + ":" + str(destport) + " HTTP/1.1\r\n" + "Host: " + destaddr + "\r\n\r\n")
+		# We read the response until we get the string "\r\n\r\n"
+		resp = self.recv(1)
+		while resp.find("\r\n\r\n")==-1:
+			resp = resp + self.recv(1)
+		# We just need the first line to check if the connection
+		# was successful
+		statusline = resp.splitlines()[0].split(" ",2)
+		if statusline[0] not in ("HTTP/1.0","HTTP/1.1"):
+			self.close()
+			raise GeneralProxyError((1,_generalerrors[1]))
+		try:
+			statuscode = int(statusline[1])
+		except ValueError:
+			self.close()
+			raise GeneralProxyError((1,_generalerrors[1]))
+		if statuscode != 200:
+			self.close()
+			raise HTTPError((statuscode,statusline[2]))
+		self.__proxysockname = ("0.0.0.0",0)
+		self.__proxypeername = (addr,destport)
+	
+	def connect(self,destpair):
+		"""connect(self,despair)
+		Connects to the specified destination through a proxy.
+		destpar - A tuple of the IP/DNS address and the port number.
+		(identical to socket's connect).
+		To select the proxy server use setproxy().
+		"""
+		# Do a minimal input check first
+		if (type(destpair) in (list,tuple)==False) or (len(destpair)<2) or (type(destpair[0])!=str) or (type(destpair[1])!=int):
+			raise GeneralProxyError((5,_generalerrors[5]))
+		if self.__proxy[0] == PROXY_TYPE_SOCKS5:
+			if self.__proxy[2] != None:
+				portnum = self.__proxy[2]
+			else:
+				portnum = 1080
+			_orgsocket.connect(self,(self.__proxy[1],portnum))
+			self.__negotiatesocks5(destpair[0],destpair[1])
+		elif self.__proxy[0] == PROXY_TYPE_SOCKS4:
+			if self.__proxy[2] != None:
+				portnum = self.__proxy[2]
+			else:
+				portnum = 1080
+			_orgsocket.connect(self,(self.__proxy[1],portnum))
+			self.__negotiatesocks4(destpair[0],destpair[1])
+		elif self.__proxy[0] == PROXY_TYPE_HTTP:
+			if self.__proxy[2] != None:
+				portnum = self.__proxy[2]
+			else:
+				portnum = 8080
+			_orgsocket.connect(self,(self.__proxy[1],portnum))
+			self.__negotiatehttp(destpair[0],destpair[1])
+		elif self.__proxy[0] == None:
+			_orgsocket.connect(self,(destpair[0],destpair[1]))
+		else:
+			raise GeneralProxyError((4,_generalerrors[4]))