tagged rc7

src/search_engine/engines/btjunkie.py

@@ -0,0 +1,35 @@
+#VERSION: 1.10
+#AUTHORS: Fabien Devaux (fab@gnux.info)
+from novaprinter import prettyPrinter
+import urllib
+import re
+
+class btjunkie(object):
+	url = 'http://btjunkie.org'
+	name = 'btjunkie'
+
+	def search(self, what):
+		i = 1
+		while True:
+			res = 0
+			dat = urllib.urlopen(self.url+'/search?q=%s&o=52&p=%d'%(what,i)).read().decode('utf8', 'replace')
+			# I know it's not very readable, but the SGML parser feels in pain
+			section_re = re.compile('(?s)href="/torrent.*?<tr>')
+			torrent_re = re.compile('(?s)href="(?P<link>.*?[^"]+).*?'
+			'class="BlckUnd">(?P<name>.*?)</a>.*?'
+			'>(?P<size>\d+MB)</font>.*?'
+			'>(?P<seeds>\d+)</font>.*?'
+			'>(?P<leech>\d+)</font>')
+			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('</?font.*?>', '', torrent_infos['name'])
+					torrent_infos['engine_url'] = self.url
+					torrent_infos['link'] = self.url+torrent_infos['link']
+					prettyPrinter(torrent_infos)
+					res = res + 1
+			if res == 0:
+				break
+			i = i + 1

src/search_engine/engines/isohunt.py

@@ -0,0 +1,78 @@
+#VERSION: 1.00
+#AUTHORS: Gekko Dam Beer (gekko04@users.sourceforge.net)
+from novaprinter import prettyPrinter
+import sgmllib
+import urllib
+
+class isohunt(object):
+	url = 'http://isohunt.com'
+	name = 'isoHunt'
+
+	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
+
+		def start_tr(self, attr):
+			params = dict(attr)
+			if 'onclick' in params:
+				Durl='http://isohunt.com/download'
+				self.current_item = {}
+				self.td_counter = 0
+				try:
+					self.current_item['link'] = '%s/%s'%(Durl, params['onclick'].split('/')[2])
+				except IndexError:
+					self.current_item['link'] = None
+
+		def handle_data(self, data):
+			if self.td_counter == 3:
+				if not self.current_item.has_key('name'):
+					self.current_item['name'] = ''
+				self.current_item['name']+= data.strip()
+			if self.td_counter == 4:
+				if not self.current_item.has_key('size'):
+					self.current_item['size'] = ''
+				self.current_item['size']+= data.strip()
+			if self.td_counter == 5:
+				if not self.current_item.has_key('seeds'):
+					self.current_item['seeds'] = ''
+				self.current_item['seeds']+= data.strip()
+			if self.td_counter == 6:
+				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 > 7:
+					self.td_counter = None
+					# add item to results
+					if self.current_item:
+						self.current_item['engine_url'] = self.url
+						if not self.current_item.has_key('seeds') or not self.current_item['seeds'].isdigit():
+							self.current_item['seeds'] = 0
+						if not self.current_item.has_key('leech') or not self.current_item['leech'].isdigit():
+							self.current_item['leech'] = 0
+						if self.current_item['link'] is not None:
+							prettyPrinter(self.current_item)
+							self.results.append('a')
+
+	def __init__(self):
+		self.results = []
+		self.parser = self.SimpleSGMLParser(self.results, self.url)
+
+	def search(self, what):
+		i = 1
+		while True:
+			results = []
+			parser = self.SimpleSGMLParser(results, self.url)
+			dat = urllib.urlopen(self.url+'/torrents.php?ihq=%s&ihp=%s'%(what,i)).read().decode('utf-8', 'replace')
+			parser.feed(dat)
+			parser.close()
+			if len(results) <= 0:
+				break
+			i += 1

src/search_engine/engines/mininova.py

@@ -0,0 +1,62 @@
+#VERSION: 1.11
+#AUTHORS: Fabien Devaux (fab@gnux.info)
+from novaprinter import prettyPrinter
+import urllib
+from xml.dom import minidom
+import re
+
+class mininova(object):
+	url = 'http://www.mininova.org'
+	name = 'Mininova'
+	table_items = 'added cat name size seeds leech'.split()
+
+	def search(self, what):
+		order = 'seeds' # must be one in self.table_items
+
+		def get_link(lnk):
+                        lnks = lnk.getElementsByTagName('a')
+                        i = 0
+                        try:
+                          while not lnks.item(i).attributes.get('href').value.startswith('/get'):
+                            i += 1
+                        except:
+                          return None
+                        return (self.url+lnks.item(i).attributes.get('href').value).strip()
+
+		def get_text(txt):
+			if txt.nodeType == txt.TEXT_NODE:
+				return txt.toxml()
+			else:
+				return ''.join([ get_text(n) for n in txt.childNodes])
+		page = 1
+		while True:
+			res = 0
+			dat = urllib.urlopen(self.url+'/search/%s/seeds/%d'%(what, page)).read().decode('utf-8', 'replace')
+			dat = re.sub("<a href=\"http://www.boardreader.com/index.php.*\"", "<a href=\"plop\"", dat)
+			dat = re.sub("<=", "&lt;=", dat)
+			dat = re.sub("&\s", "&amp; ", dat)
+			x = minidom.parseString(dat.encode('utf-8', 'replace'))
+			table = x.getElementsByTagName('table').item(0)
+			if not table: return
+			for tr in table.getElementsByTagName('tr'):
+				tds = tr.getElementsByTagName('td')
+				if tds:
+					i = 0
+					vals = {}
+					for td in tds:
+						if self.table_items[i] == 'name':
+							vals['link'] = get_link(td)
+						vals[self.table_items[i]] = get_text(td).strip()
+						i += 1
+					vals['engine_url'] = self.url
+					if not vals['seeds'].isdigit():
+						vals['seeds'] = 0
+					if not vals['leech'].isdigit():
+						vals['leech'] = 0
+                                        if vals['link'] is None:
+                                          continue
+					prettyPrinter(vals)
+					res = res + 1
+			if res == 0:
+				break
+			page = page +1

src/search_engine/engines/piratebay.py

@@ -0,0 +1,79 @@
+#VERSION: 1.00
+#AUTHORS: Fabien Devaux (fab@gnux.info)
+from novaprinter import prettyPrinter
+import sgmllib
+import urllib
+
+class piratebay(object):
+	url = 'http://thepiratebay.org'
+	name = 'The Pirate Bay'
+
+	def __init__(self):
+		self.results = []
+		self.parser = self.SimpleSGMLParser(self.results, self.url)
+
+	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
+
+		def start_a(self, attr):
+			params = dict(attr)
+			if params['href'].startswith('/browse'):
+				self.current_item = {}
+				self.td_counter = 0
+                        elif params['href'].startswith('/tor'):
+				self.code = params['href'].split('/')[2]
+			elif params['href'].startswith('http://torrents.thepiratebay.org/%s'%self.code):
+				self.current_item['link']=params['href'].strip()
+				self.td_counter = self.td_counter+1
+
+		def handle_data(self, data):
+			if self.td_counter == 1:
+				if not self.current_item.has_key('name'):
+					self.current_item['name'] = ''
+				self.current_item['name']+= data.strip()
+			if self.td_counter == 5:
+				if not self.current_item.has_key('size'):
+					self.current_item['size'] = ''
+				self.current_item['size']+= data.strip()
+			elif self.td_counter == 6:
+				if not self.current_item.has_key('seeds'):
+					self.current_item['seeds'] = ''
+				self.current_item['seeds']+= data.strip()
+			elif self.td_counter == 7:
+				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 > 7:
+					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):
+		ret = []
+		i = 0
+		order = 'se'
+		while True:
+			results = []
+			parser = self.SimpleSGMLParser(results, self.url)
+			dat = urllib.urlopen(self.url+'/search/%s/%u/0/0' % (what, i)).read()
+			parser.feed(dat)
+			parser.close()
+			if len(results) <= 0:
+				break
+			i += 1

src/search_engine/engines/torrentreactor.py

@@ -0,0 +1,78 @@
+#VERSION: 1.00
+#AUTHORS: Gekko Dam Beer (gekko04@users.sourceforge.net)
+from novaprinter import prettyPrinter
+import sgmllib
+import urllib
+
+class torrentreactor(object):
+	url = 'http://www.torrentreactor.net'
+	name = 'TorrentReactor.Net'
+
+	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 params['href'].startswith('http://dl.torrentreactor.net/download.php'):
+				self.current_item = {}
+				self.td_counter = 0
+				equal = params['href'].find("=")
+				amp = params['href'].find("&", equal+1)
+				self.id = str(int(params['href'][equal+1:amp]))
+
+		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 > 7:
+					self.td_counter = None
+					# add item to results
+					if self.current_item:
+						self.current_item['link']='http://download.torrentreactor.net/download.php?id=%s&name=%s'%(self.id, urllib.quote(self.current_item['name']))
+						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):
+		i = 0
+		while True:
+			results = []
+			parser = self.SimpleSGMLParser(results, self.url)
+			dat = urllib.urlopen(self.url+'/search.php?search=&words=%s&cid=&sid=&type=2&orderby=a.seeds&asc=0&skip=%s'%(what,(i*35))).read().decode('utf-8', 'replace')
+			parser.feed(dat)
+			parser.close()
+			if len(results) <= 0:
+				break
+			i += 1

src/search_engine/engines/versions.txt

@@ -0,0 +1,5 @@
+isohunt: 1.00
+torrentreactor: 1.00
+btjunkie: 1.10
+mininova: 1.11
+piratebay: 1.00