github/qBittorrent
1
0
Fork 0
mirror of https://github.com/qbittorrent/qBittorrent synced 2025-08-19 12:59:56 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Merge pull request #2550 from DoumanAsh/multiprocessor_search

Browse source 
[search engine] Replace threading with multiprocessing
This commit is contained in:
sledgehammer999 2015-06-11 19:14:11 +03:00
commit 3d40834c57
22 changed files with 1650 additions and 1470 deletions
Download patch file Download diff file Expand all files Collapse all files

207
src/searchengine/nova/engines/extratorrent.py
View file

@ -1,4 +1,4 @@
#VERSION: 1.2 #VERSION: 2.0
#AUTHORS: Christophe Dumez (chris@qbittorrent.org) #AUTHORS: Christophe Dumez (chris@qbittorrent.org)
# Redistribution and use in source and binary forms, with or without # Redistribution and use in source and binary forms, with or without
@ -25,92 +25,139 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE # ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE. # POSSIBILITY OF SUCH DAMAGE.
from HTMLParser import HTMLParser
from httplib import HTTPConnection as http
#qBt
from novaprinter import prettyPrinter from novaprinter import prettyPrinter
from helpers import retrieve_url, download_file from helpers import download_file
import sgmllib
import re
class extratorrent(object): class extratorrent(object):
url = 'http://extratorrent.cc' """ Search engine class """
name = 'extratorrent' url = 'http://extratorrent.cc'
supported_categories = {'all': '', 'movies': '4', 'tv': '8', 'music': '5', 'games': '3', 'anime': '1', 'software': '7', 'books': '2', 'pictures': '6'} name = 'ExtraTorrent'
supported_categories = {'all' : '0',
'movies' : '4',
'tv' : '8',
'music' : '5',
'games' : '3',
'anime' : '1',
'software' : '7',
'books' : '2',
'pictures' : '6'}
def __init__(self): def download_torrent(self, info):
self.results = [] """ Downloader """
self.parser = self.SimpleSGMLParser(self.results, self.url) print(download_file(info))
def download_torrent(self, info): class MyHtmlParseWithBlackJack(HTMLParser):
print download_file(info) """ Parser class """
def __init__(self, list_searches, url):
HTMLParser.__init__(self)
self.url = url
self.list_searches = list_searches
self.current_item = None
self.cur_item_name = None
self.pending_size = False
self.next_queries = True
self.pending_next_queries = False
self.next_queries_set = set()
class SimpleSGMLParser(sgmllib.SGMLParser): def handle_starttag(self, tag, attrs):
def __init__(self, results, url, *args):
sgmllib.SGMLParser.__init__(self)
self.url = url
self.td_counter = None
self.current_item = None
self.start_name = False
self.results = results
def start_a(self, attr):
params = dict(attr)
#print params
if params.has_key('href') and params['href'].startswith("/torrent_download/"):
self.current_item = {}
self.td_counter = 0
self.start_name = False
torrent_id = '/'.join(params['href'].split('/')[2:])
self.current_item['link']=self.url+'/download/'+torrent_id
elif params.has_key('href') and params['href'].startswith("/torrent/") and params['href'].endswith(".html"):
self.current_item['desc_link'] = self.url + params['href'].strip()
self.start_name = True
def handle_data(self, data):
if self.td_counter == 2:
if not self.current_item.has_key('name') and self.start_name:
self.current_item['name'] = data.strip()
elif self.td_counter == 3:
if not self.current_item.has_key('size'):
self.current_item['size'] = ''
self.current_item['size']+= data.replace(" ", " ").strip()
elif self.td_counter == 4:
if not self.current_item.has_key('seeds'):
self.current_item['seeds'] = ''
self.current_item['seeds']+= data.strip()
elif self.td_counter == 5:
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 > 5:
self.td_counter = None
# Display item
if self.current_item: if self.current_item:
self.current_item['engine_url'] = self.url if tag == "a":
if not self.current_item['seeds'].isdigit(): params = dict(attrs)
self.current_item['seeds'] = 0 link = params['href']
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'): if not link.startswith("/torrent"):
ret = [] return
i = 1
while True and i<11: if link[8] == "/":
results = [] #description
parser = self.SimpleSGMLParser(results, self.url) self.current_item["desc_link"] = "".join((self.url, link))
dat = retrieve_url(self.url+'/advanced_search/?with=%s&s_cat=%s&page=%d'%(what, self.supported_categories[cat], i)) #remove view at the beginning
results_re = re.compile('(?s)<table class="tl"><thead>.*') self.current_item["name"] = params["title"][5:].replace("&amp;", "&")
for match in results_re.finditer(dat): self.pending_size = True
res_tab = match.group(0) elif link[8] == "_":
parser.feed(res_tab) #download link
link = link.replace("torrent_", "", 1)
self.current_item["link"] = "".join((self.url, link))
elif tag == "td":
if self.pending_size:
self.cur_item_name = "size"
self.current_item["size"] = ""
self.pending_size = False
for attr in attrs:
if attr[0] == "class":
if attr[1][0] == "s":
self.cur_item_name = "seeds"
self.current_item["seeds"] = ""
elif attr[1][0] == "l":
self.cur_item_name = "leech"
self.current_item["leech"] = ""
break
elif tag == "tr":
for attr in attrs:
if attr[0] == "class" and attr[1].startswith("tl"):
self.current_item = dict()
self.current_item["engine_url"] = self.url
break
elif self.pending_next_queries:
if tag == "a":
params = dict(attrs)
if params["title"] in self.next_queries_set:
return
self.list_searches.append(params['href'])
self.next_queries_set.add(params["title"])
if params["title"] == "10":
self.pending_next_queries = False
else:
self.pending_next_queries = False
elif self.next_queries:
if tag == "b" and ("class", "pager_no_link") in attrs:
self.next_queries = False
self.pending_next_queries = True
def handle_data(self, data):
if self.cur_item_name:
temp = self.current_item[self.cur_item_name]
self.current_item[self.cur_item_name] = " ".join((temp, data))
#Due to utf-8 we need to handle data two times if there is space
if not self.cur_item_name == "size":
self.cur_item_name = None
def handle_endtag(self, tag):
if self.current_item:
if tag == "tr":
prettyPrinter(self.current_item)
self.current_item = None
def search(self, what, cat="all"):
""" Performs search """
connection = http("extratorrent.cc")
query = "".join(("/search/?new=1&search=", what, "&s_cat=", self.supported_categories[cat]))
connection.request("GET", query)
response = connection.getresponse()
if response.status != 200:
return
list_searches = []
parser = self.MyHtmlParseWithBlackJack(list_searches, self.url)
parser.feed(response.read().decode('utf-8'))
parser.close() parser.close()
break
if len(results) <= 0:
break
i += 1
for search_query in list_searches:
connection.request("GET", search_query)
response = connection.getresponse()
parser.feed(response.read().decode('utf-8'))
parser.close()
connection.close()
return

6
src/searchengine/nova/engines/legittorrents.py
View file

@ -1,4 +1,4 @@
#VERSION: 1.02 #VERSION: 1.03
#AUTHORS: Christophe Dumez (chris@qbittorrent.org) #AUTHORS: Christophe Dumez (chris@qbittorrent.org)
# Redistribution and use in source and binary forms, with or without # Redistribution and use in source and binary forms, with or without
@ -36,10 +36,6 @@ class legittorrents(object):
name = 'legittorrents' name = 'legittorrents'
supported_categories = {'all': '', 'movies': '1', 'tv': '13', 'music': '2', 'games': '3', 'anime': '5', 'books': '6'} supported_categories = {'all': '', 'movies': '1', 'tv': '13', 'music': '2', 'games': '3', 'anime': '5', 'books': '6'}
def __init__(self):
self.results = []
self.parser = self.SimpleSGMLParser(self.results, self.url)
def download_torrent(self, info): def download_torrent(self, info):
print download_file(info) print download_file(info)

185
src/searchengine/nova/engines/mininova.py
View file

@ -1,4 +1,4 @@
#VERSION: 1.51 #VERSION: 2.00
#AUTHORS: Christophe Dumez (chris@qbittorrent.org) #AUTHORS: Christophe Dumez (chris@qbittorrent.org)
#CONTRIBUTORS: Diego de las Heras (diegodelasheras@gmail.com) #CONTRIBUTORS: Diego de las Heras (diegodelasheras@gmail.com)
@ -26,90 +26,123 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE # ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE. # POSSIBILITY OF SUCH DAMAGE.
from HTMLParser import HTMLParser
from httplib import HTTPConnection as http
from novaprinter import prettyPrinter from novaprinter import prettyPrinter
from helpers import retrieve_url, download_file from helpers import download_file
import sgmllib
import re
class mininova(object): class mininova(object):
# Mandatory properties """ Search engine class """
url = 'http://www.mininova.org' url = 'http://www.mininova.org'
name = 'Mininova' name = 'Mininova'
supported_categories = {'all': '0', 'movies': '4', 'tv': '8', 'music': '5', 'games': '3', 'anime': '1', 'software': '7', 'pictures': '6', 'books': '2'} supported_categories = {'all' : '0',
'movies' : '4',
'tv' : '8',
'music' : '5',
'games' : '3',
'anime' : '1',
'software' : '7',
'pictures' : '6',
'books' : '2'}
def __init__(self): def download_torrent(self, info):
self.results = [] print(download_file(info))
self.parser = self.SimpleSGMLParser(self.results, self.url)
def download_torrent(self, info): class MyHtmlParseWithBlackJack(HTMLParser):
print download_file(info) """ Parser class """
def __init__(self, list_searches, url):
HTMLParser.__init__(self)
self.list_searches = list_searches
self.url = url
self.table_results = False
self.current_item = None
self.cur_item_name = None
self.next_queries = True
class SimpleSGMLParser(sgmllib.SGMLParser): def handle_starttag_tr(self, _):
def __init__(self, results, url, *args): """ Handler of tr start tag """
sgmllib.SGMLParser.__init__(self) self.current_item = dict()
self.url = url
self.td_counter = None
self.current_item = None
self.results = results
def start_a(self, attr): def handle_starttag_a(self, attrs):
params = dict(attr) """ Handler of a start tag """
#print params params = dict(attrs)
if params.has_key('href'): link = params["href"]
if params['href'].startswith("/get/"):
self.current_item = {}
self.td_counter = 0
self.current_item['link']=self.url+params['href'].strip()
elif params['href'].startswith("/tor/") and self.current_item is not None:
self.current_item['desc_link']=self.url+params['href'].strip()
def handle_data(self, data): if link.startswith("/tor/"):
if self.td_counter == 0: #description
if not self.current_item.has_key('name'): self.current_item["desc_link"] = "".join((self.url, link))
self.current_item['name'] = '' #get download link from description by id
self.current_item['name']+= data self.current_item["link"] = "".join((self.url, "/get/", link[5:-2]))
elif self.td_counter == 1: self.cur_item_name = "name"
if not self.current_item.has_key('size'): self.current_item["name"] = ""
self.current_item['size'] = '' elif self.next_queries and link.startswith("/search"):
self.current_item['size']+= data.strip() if params["title"].startswith("Page"):
elif self.td_counter == 2: self.list_searches.append(link)
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): def handle_starttag_td(self, attrs):
if isinstance(self.td_counter,int): """ Handler of td start tag """
self.td_counter += 1 if ("align", "right") in attrs:
if self.td_counter > 4: if not "size" in self.current_item:
self.td_counter = None self.cur_item_name = "size"
# Display item self.current_item["size"] = ""
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'): def handle_starttag_span(self, attrs):
ret = [] """ Handler of span start tag """
i = 1 if ("class", "g") in attrs:
while True and i<11: self.cur_item_name = "seeds"
results = [] self.current_item["seeds"] = ""
parser = self.SimpleSGMLParser(results, self.url) elif ("class", "b") in attrs:
dat = retrieve_url(self.url+'/search/%s/%s/seeds/%d'%(what, self.supported_categories[cat], i)) self.cur_item_name = "leech"
results_re = re.compile('(?s)<h1>Search results for.*') self.current_item["leech"] = ""
for match in results_re.finditer(dat):
res_tab = match.group(0) def handle_starttag(self, tag, attrs):
parser.feed(res_tab) """ Parser's start tag handler """
if self.table_results:
dispatcher = getattr(self, "_".join(("handle_starttag", tag)), None)
if dispatcher:
dispatcher(attrs)
elif tag == "table":
self.table_results = ("class", "maintable") in attrs
def handle_endtag(self, tag):
""" Parser's end tag handler """
if tag == "tr" and self.current_item:
self.current_item["engine_url"] = self.url
prettyPrinter(self.current_item)
self.current_item = None
elif self.cur_item_name:
if tag == "a" or tag == "td":
self.cur_item_name = None
def handle_data(self, data):
""" Parser's data handler """
if self.cur_item_name:
temp = self.current_item[self.cur_item_name]
self.current_item[self.cur_item_name] = " ".join((temp, data))
def search(self, what, cat="all"):
""" Performs search """
connection = http("www.mininova.org")
query = "/".join(("/search", what, self.supported_categories[cat], "seeds"))
connection.request("GET", query)
response = connection.getresponse()
if response.status != 200:
return
list_searches = []
parser = self.MyHtmlParseWithBlackJack(list_searches, self.url)
parser.feed(response.read().decode('utf-8'))
parser.close() parser.close()
break
if len(results) <= 0:
break
i += 1
parser.next_queries = False
for search_query in list_searches:
connection.request("GET", search_query)
response = connection.getresponse()
parser.feed(response.read().decode('utf-8'))
parser.close()
connection.close()
return

BIN
src/searchengine/nova/engines/torrentreactor.png
View file

Binary file not shown.
Side by side Swipe Overlay

Before

Width:  |  Height:  |  Size: 252 B

After

Width:  |  Height:  |  Size: 951 B

Before After
Before After

150
src/searchengine/nova/engines/torrentreactor.py
View file

@ -1,4 +1,4 @@
#VERSION: 1.33 #VERSION: 1.36
#AUTHORS: Gekko Dam Beer (gekko04@users.sourceforge.net) #AUTHORS: Gekko Dam Beer (gekko04@users.sourceforge.net)
#CONTRIBUTORS: Christophe Dumez (chris@qbittorrent.org) #CONTRIBUTORS: Christophe Dumez (chris@qbittorrent.org)
# Bruno Barbieri (brunorex@gmail.com) # Bruno Barbieri (brunorex@gmail.com)
@ -28,92 +28,84 @@
# POSSIBILITY OF SUCH DAMAGE. # POSSIBILITY OF SUCH DAMAGE.
from novaprinter import prettyPrinter from novaprinter import prettyPrinter
from helpers import retrieve_url, download_file from helpers import download_file, retrieve_url
from urllib2 import HTTPError
from HTMLParser import HTMLParser
import urllib import urllib
import re from HTMLParser import HTMLParser
from re import compile as re_compile
class torrentreactor(object): class torrentreactor(object):
url = 'http://www.torrentreactor.net' url = 'http://www.torrentreactor.net'
name = 'TorrentReactor.Net' name = 'TorrentReactor'
supported_categories = {'all': '', 'movies': '5', 'tv': '8', 'music': '6', 'games': '3', 'anime': '1', 'software': '2'} supported_categories = {'all': '', 'movies': '5', 'tv': '8', 'music': '6', 'games': '3', 'anime': '1', 'software': '2'}
def download_torrent(self, info): def download_torrent(self, info):
print download_file(info) print(download_file(info))
class SimpleHTMLParser(HTMLParser): class SimpleHTMLParser(HTMLParser):
def __init__(self, results, url, *args): def __init__(self, results, url, *args):
HTMLParser.__init__(self) HTMLParser.__init__(self)
self.td_counter = None self.td_counter = None
self.current_item = None self.current_item = None
self.results = results self.results = results
self.id = None self.id = None
self.url = url self.url = url
self.dispatcher = { 'a' : self.start_a, 'td' : self.start_td } self.torrents_matcher = re_compile("/torrents/\d+.*")
self.dispatcher = { 'a' : self.start_a, 'td' : self.start_td }
def handle_starttag(self, tag, attrs): def handle_starttag(self, tag, attrs):
if tag in self.dispatcher: if tag in self.dispatcher:
self.dispatcher[tag](attrs) self.dispatcher[tag](attrs)
def start_a(self, attr): def start_a(self, attr):
params = dict(attr) params = dict(attr)
if re.match("/torrents/\d+.*", params['href']): if self.torrents_matcher.match(params['href']):
self.current_item = {} self.current_item = {}
self.current_item['desc_link'] = self.url+params['href'].strip() self.current_item['desc_link'] = self.url+params['href'].strip()
elif 'torrentreactor.net/download.php' in params['href']: elif 'torrentreactor.net/download.php' in params['href']:
self.td_counter = 0 self.td_counter = 0
self.current_item['link'] = params['href'].strip() self.current_item['link'] = params['href'].strip()
self.current_item['name'] = urllib.unquote_plus(params['href'].split('&')[1].split('name=')[1]) self.current_item['name'] = urllib.unquote_plus(params['href'].split('&')[1].split('name=')[1])
def handle_data(self, data): def handle_data(self, data):
if self.td_counter == 1: if self.td_counter == 1:
if not self.current_item.has_key('size'): if 'size' not in self.current_item:
self.current_item['size'] = '' self.current_item['size'] = ''
self.current_item['size']+= data.strip() self.current_item['size']+= data.strip()
elif self.td_counter == 2: elif self.td_counter == 2:
if not self.current_item.has_key('seeds'): if 'seeds' not in self.current_item:
self.current_item['seeds'] = '' self.current_item['seeds'] = ''
self.current_item['seeds']+= data.strip() self.current_item['seeds']+= data.strip()
elif self.td_counter == 3: elif self.td_counter == 3:
if not self.current_item.has_key('leech'): if 'leech' not in self.current_item:
self.current_item['leech'] = '' self.current_item['leech'] = ''
self.current_item['leech']+= data.strip() self.current_item['leech']+= data.strip()
def start_td(self,attr): def start_td(self,attr):
if isinstance(self.td_counter,int): if isinstance(self.td_counter,int):
self.td_counter += 1 self.td_counter += 1
if self.td_counter > 3: if self.td_counter > 3:
self.td_counter = None self.td_counter = None
# add item to results # add item to results
if self.current_item: if self.current_item:
self.current_item['engine_url'] = self.url self.current_item['engine_url'] = self.url
if not self.current_item['seeds'].isdigit(): if not self.current_item['seeds'].isdigit():
self.current_item['seeds'] = 0 self.current_item['seeds'] = 0
if not self.current_item['leech'].isdigit(): if not self.current_item['leech'].isdigit():
self.current_item['leech'] = 0 self.current_item['leech'] = 0
prettyPrinter(self.current_item) prettyPrinter(self.current_item)
self.has_results = True self.has_results = True
self.results.append('a') self.results.append('a')
def __init__(self): def search(self, what, cat='all'):
self.results = [] i = 0
self.parser = self.SimpleHTMLParser(self.results, self.url) dat = ''
def search(self, what, cat='all'): while i < 11:
i = 0 results = []
dat = '' parser = self.SimpleHTMLParser(results, self.url)
while True and i<11: dat = retrieve_url('%s/torrent-search/%s/%s?sort=seeders.desc&type=all&period=none&categories=%s'%(self.url, what, (i*35), self.supported_categories[cat]))
results = [] parser.feed(dat)
parser = self.SimpleHTMLParser(results, self.url) parser.close()
if len(results) <= 0:
try: break
dat = retrieve_url(self.url+'/torrent-search/%s/%s?sort=seeders.desc&type=all&period=none&categories=%s'%(what, (i*35), self.supported_categories[cat])) i += 1
except HTTPError:
break
parser.feed(dat)
parser.close()
if len(results) <= 0:
break
i += 1

4
src/searchengine/nova/engines/torrentz.py
View file

@ -1,4 +1,4 @@
#VERSION: 2.13 #VERSION: 2.14
#AUTHORS: Diego de las Heras (diegodelasheras@gmail.com) #AUTHORS: Diego de las Heras (diegodelasheras@gmail.com)
# Redistribution and use in source and binary forms, with or without # Redistribution and use in source and binary forms, with or without
@ -105,7 +105,7 @@ class torrentz(object):
while i < 6: while i < 6:
results_list = [] results_list = []
# "what" is already urlencoded # "what" is already urlencoded
html = retrieve_url(self.url + '/any?f=%s&p=%d' % (what, i)) html = retrieve_url('%s/any?f=%s&p=%d' % (self.url, what, i))
parser = self.MyHtmlParser(results_list, self.url, trackers) parser = self.MyHtmlParser(results_list, self.url, trackers)
parser.feed(html) parser.feed(html)
parser.close() parser.close()

11
src/searchengine/nova/engines/versions.txt
View file

@ -1,8 +1,9 @@
torrentreactor: 1.33
mininova: 1.51
piratebay: 2.11
extratorrent: 1.2 extratorrent: 1.2
torrentreactor: 1.36
mininova: 2.00
piratebay: 2.11
extratorrent: 2.0
kickasstorrents: 1.26 kickasstorrents: 1.26
btdigg: 1.24 btdigg: 1.24
legittorrents: 1.02 torrentz: 2.14
torrentz: 2.13 legittorrents: 1.03

220
src/searchengine/nova/nova2.py
View file

@ -26,7 +26,7 @@
# POSSIBILITY OF SUCH DAMAGE. # POSSIBILITY OF SUCH DAMAGE.
#VERSION: 1.32 #VERSION: 1.40
# Author: # Author:
# Fabien Devaux <fab AT gnux DOT info> # Fabien Devaux <fab AT gnux DOT info>
@ -37,16 +37,15 @@
# #
# Licence: BSD # Licence: BSD
import sys
import threading
import os
import glob
import urllib import urllib
from os import path
import fix_encoding from glob import glob
from sys import argv
from multiprocessing import Pool, cpu_count
from fix_encoding import fix_encoding
THREADED = True THREADED = True
CATEGORIES = ('all', 'movies', 'tv', 'music', 'games', 'anime', 'software', 'pictures', 'books') CATEGORIES = {'all', 'movies', 'tv', 'music', 'games', 'anime', 'software', 'pictures', 'books'}
################################################################################ ################################################################################
# Every engine should have a "search" method taking # Every engine should have a "search" method taking
@ -56,108 +55,129 @@ CATEGORIES = ('all', 'movies', 'tv', 'music', 'games', 'anime', 'software', 'pic
# As a convention, try to list results by decrasing number of seeds or similar # As a convention, try to list results by decrasing number of seeds or similar
################################################################################ ################################################################################
supported_engines = [] def initialize_engines():
""" Import available engines
engines = glob.glob(os.path.join(os.path.dirname(__file__), 'engines','*.py')) Return list of available engines
for engine in engines: """
e = engine.split(os.sep)[-1][:-3] supported_engines = []
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): engines = glob(path.join(path.dirname(__file__), 'engines', '*.py'))
xml = "<%s>\n"%short_name for engine in engines:
exec "engine = %s()"%short_name engi = path.basename(engine).split('.')[0].strip()
xml += "<name>%s</name>\n"%engine.name if len(engi) == 0 or engi.startswith('_'):
xml += "<url>%s</url>\n"%engine.url continue
xml += "<categories>" try:
if hasattr(engine, 'supported_categories'): #import engines.[engine]
supported_categories = engine.supported_categories.keys() engine_module = __import__(".".join(("engines", engi)))
supported_categories.remove('all') #get low-level module
xml += " ".join(supported_categories) engine_module = getattr(engine_module, engi)
xml += "</categories>\n" #bind class name
xml += "</%s>\n"%short_name globals()[engi] = getattr(engine_module, engi)
return xml supported_engines.append(engi)
except:
pass
def displayCapabilities(): return supported_engines
"""
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 engines_to_xml(supported_engines):
def __init__(self, engine, what, cat='all'): """ Generates xml for supported engines """
threading.Thread.__init__(self) tab = " " * 4
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__': for short_name in supported_engines:
# Make sure we enforce utf-8 encoding search_engine = globals()[short_name]()
fix_encoding.fix_encoding()
if len(sys.argv) < 2: supported_categories = ""
raise SystemExit('./nova2.py [all|engine1[,engine2]*] <category> <keywords>\navailable engines: %s'% if hasattr(search_engine, "supported_categories"):
(','.join(supported_engines))) supported_categories = " ".join((key for key in search_engine.supported_categories.keys()
if key is not "all"))
if len(sys.argv) == 2: yield "".join((tab, "<", short_name, ">\n",
if sys.argv[1] == "--capabilities": tab, tab, "<name>", search_engine.name, "</name>\n",
displayCapabilities() tab, tab, "<url>", search_engine.url, "</url>\n",
sys.exit(0) tab, tab, "<categories>", supported_categories, "</categories>\n",
else: tab, "</", short_name, ">\n"))
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(',')] def displayCapabilities(supported_engines):
"""
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 = "".join(("<capabilities>\n",
"".join(engines_to_xml(supported_engines)),
"</capabilities>"))
print(xml)
if 'all' in engines_list: def run_search(engine_list):
engines_list = supported_engines """ Run search in engine
cat = sys.argv[2].lower() @param engine_list List with engine, query and category
if cat not in CATEGORIES: @retval False if any exceptions occured
raise SystemExit('Invalid category!') @retval True otherwise
"""
engine, what, cat = engine_list
try:
engine = engine()
#avoid exceptions due to invalid category
if hasattr(engine, 'supported_categories'):
cat = cat if cat in engine.supported_categories else "all"
engine.search(what, cat)
else:
engine.search(what)
return True
except:
return False
what = urllib.quote(' '.join(sys.argv[3:])) def main(args):
fix_encoding()
supported_engines = initialize_engines()
threads = [] if not args:
for engine in engines_list: raise SystemExit("./nova2.py [all|engine1[,engine2]*] <category> <keywords>\n"
try: "available engines: %s" % (','.join(supported_engines)))
if THREADED:
exec "l = EngineLauncher(%s(), what, cat)"%engine elif args[0] == "--capabilities":
threads.append(l) displayCapabilities(supported_engines)
l.start() return
else:
exec "e = %s()"%engine elif len(args) < 3:
if hasattr(engine, 'supported_categories'): raise SystemExit("./nova2.py [all|engine1[,engine2]*] <category> <keywords>\n"
if cat == 'all' or cat in e.supported_categories.keys(): "available engines: %s" % (','.join(supported_engines)))
e.search(what, cat)
elif self.cat == 'all': #get only unique engines with set
e.search(what) engines_list = set(e.lower() for e in args[0].strip().split(','))
engine().search(what, cat)
except: if 'all' in engines_list:
pass engines_list = supported_engines
if THREADED: else:
for t in threads: #discard un-supported engines
t.join() engines_list = [engine for engine in engines_list
if engine in supported_engines]
if not engines_list:
#engine list is empty. Nothing to do here
return
cat = args[1].lower()
if cat not in CATEGORIES:
raise SystemExit(" - ".join(('Invalid category', cat)))
what = urllib.quote(' '.join(args[2:]))
if THREADED:
#child process spawning is controlled min(number of searches, number of cpu)
pool = Pool(min(len(engines_list), cpu_count()))
pool.map(run_search, ([globals()[engine], what, cat] for engine in engines_list))
else:
map(run_search, ([globals()[engine], what, cat] for engine in engines_list))
if __name__ == "__main__":
main(argv[1:])

44
src/searchengine/nova/nova2dl.py
View file

@ -25,7 +25,7 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE # ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE. # POSSIBILITY OF SUCH DAMAGE.
#VERSION: 1.10 #VERSION: 1.20
# Author: # Author:
# Christophe DUMEZ (chris@qbittorrent.org) # Christophe DUMEZ (chris@qbittorrent.org)
@ -39,26 +39,26 @@ supported_engines = dict()
engines = glob.glob(os.path.join(os.path.dirname(__file__), 'engines','*.py')) engines = glob.glob(os.path.join(os.path.dirname(__file__), 'engines','*.py'))
for engine in engines: for engine in engines:
e = engine.split(os.sep)[-1][:-3] e = engine.split(os.sep)[-1][:-3]
if len(e.strip()) == 0: continue if len(e.strip()) == 0: continue
if e.startswith('_'): continue if e.startswith('_'): continue
try: try:
exec "from engines.%s import %s"%(e,e) exec("from engines.%s import %s"%(e,e))
exec "engine_url = %s.url"%e exec("engine_url = %s.url"%e)
supported_engines[engine_url] = e supported_engines[engine_url] = e
except: except:
pass pass
if __name__ == '__main__': if __name__ == '__main__':
if len(sys.argv) < 3: if len(sys.argv) < 3:
raise SystemExit('./nova2dl.py engine_url download_parameter') raise SystemExit('./nova2dl.py engine_url download_parameter')
engine_url = sys.argv[1].strip() engine_url = sys.argv[1].strip()
download_param = sys.argv[2].strip() download_param = sys.argv[2].strip()
if engine_url not in supported_engines.keys(): if engine_url not in list(supported_engines.keys()):
raise SystemExit('./nova2dl.py: this engine_url was not recognized') raise SystemExit('./nova2dl.py: this engine_url was not recognized')
exec "engine = %s()"%supported_engines[engine_url] exec("engine = %s()"%supported_engines[engine_url])
if hasattr(engine, 'download_torrent'): if hasattr(engine, 'download_torrent'):
engine.download_torrent(download_param) engine.download_torrent(download_param)
else: else:
print download_file(download_param) print(download_file(download_param))
sys.exit(0) sys.exit(0)

67
src/searchengine/nova/novaprinter.py
View file

@ -25,45 +25,44 @@
# POSSIBILITY OF SUCH DAMAGE. # POSSIBILITY OF SUCH DAMAGE.
import sys, codecs import sys, codecs
from io import open
# Force UTF-8 printing # Force UTF-8 printing
sys.stdout = codecs.getwriter('utf-8')(sys.stdout) sys.stdout = codecs.getwriter('utf-8')(sys.stdout)
def prettyPrinter(dictionary): def prettyPrinter(dictionary):
# Convert everything to unicode for safe printing dictionary['size'] = anySizeToBytes(dictionary['size'])
for key,value in dictionary.items(): outtext = "|".join((dictionary["link"], dictionary["name"].replace("|", " "), str(dictionary["size"]), str(dictionary["seeds"]), str(dictionary["leech"]), dictionary["engine_url"]))
if isinstance(dictionary[key], str): if 'desc_link' in dictionary:
dictionary[key] = unicode(dictionary[key], 'utf-8') outtext = "|".join((outtext, dictionary["desc_link"]))
dictionary['size'] = anySizeToBytes(dictionary['size'])
if dictionary.has_key('desc_link'): with open(1, 'w', encoding='utf-8', closefd=False) as utf8_stdout:
print u"%s|%s|%s|%s|%s|%s|%s"%(dictionary['link'],dictionary['name'].replace('|',' '),dictionary['size'],dictionary['seeds'],dictionary['leech'],dictionary['engine_url'],dictionary['desc_link']) utf8_stdout.write(unicode("".join((outtext, "\n"))))
else:
print u"%s|%s|%s|%s|%s|%s"%(dictionary['link'],dictionary['name'].replace('|',' '),dictionary['size'],dictionary['seeds'],dictionary['leech'],dictionary['engine_url'])
def anySizeToBytes(size_string): def anySizeToBytes(size_string):
""" """
Convert a string like '1 KB' to '1024' (bytes) Convert a string like '1 KB' to '1024' (bytes)
""" """
# separate integer from unit # separate integer from unit
try: try:
size, unit = size_string.split() size, unit = size_string.split()
except: except:
try: try:
size = size_string.strip() size = size_string.strip()
unit = ''.join([c for c in size if c.isalpha()]) unit = ''.join([c for c in size if c.isalpha()])
if len(unit) > 0: if len(unit) > 0:
size = size[:-len(unit)] size = size[:-len(unit)]
except: except:
return -1 return -1
if len(size) == 0: if len(size) == 0:
return -1 return -1
size = float(size) size = float(size)
if len(unit) == 0: if len(unit) == 0:
return int(size) return int(size)
short_unit = unit.upper()[0] short_unit = unit.upper()[0]
# convert # convert
units_dict = { 'T': 40, 'G': 30, 'M': 20, 'K': 10 } units_dict = {'T': 40, 'G': 30, 'M': 20, 'K': 10}
if units_dict.has_key( short_unit ): if units_dict.has_key(short_unit):
size = size * 2**units_dict[short_unit] size = size * 2**units_dict[short_unit]
return int(size) return int(size)

628
src/searchengine/nova/socks.py
View file

@ -42,350 +42,350 @@ _defaultproxy = None
_orgsocket = socket.socket _orgsocket = socket.socket
class ProxyError(Exception): class ProxyError(Exception):
def __init__(self, value): def __init__(self, value):
self.value = value self.value = value
def __str__(self): def __str__(self):
return repr(self.value) return repr(self.value)
class GeneralProxyError(ProxyError): class GeneralProxyError(ProxyError):
def __init__(self, value): def __init__(self, value):
self.value = value self.value = value
def __str__(self): def __str__(self):
return repr(self.value) return repr(self.value)
class Socks5AuthError(ProxyError): class Socks5AuthError(ProxyError):
def __init__(self, value): def __init__(self, value):
self.value = value self.value = value
def __str__(self): def __str__(self):
return repr(self.value) return repr(self.value)
class Socks5Error(ProxyError): class Socks5Error(ProxyError):
def __init__(self, value): def __init__(self, value):
self.value = value self.value = value
def __str__(self): def __str__(self):
return repr(self.value) return repr(self.value)
class Socks4Error(ProxyError): class Socks4Error(ProxyError):
def __init__(self, value): def __init__(self, value):
self.value = value self.value = value
def __str__(self): def __str__(self):
return repr(self.value) return repr(self.value)
class HTTPError(ProxyError): class HTTPError(ProxyError):
def __init__(self, value): def __init__(self, value):
self.value = value self.value = value
def __str__(self): def __str__(self):
return repr(self.value) return repr(self.value)
_generalerrors = ("success", _generalerrors = ("success",
"invalid data", "invalid data",
"not connected", "not connected",
"not available", "not available",
"bad proxy type", "bad proxy type",
"bad input") "bad input")
_socks5errors = ("succeeded", _socks5errors = ("succeeded",
"general SOCKS server failure", "general SOCKS server failure",
"connection not allowed by ruleset", "connection not allowed by ruleset",
"Network unreachable", "Network unreachable",
"Host unreachable", "Host unreachable",
"Connection refused", "Connection refused",
"TTL expired", "TTL expired",
"Command not supported", "Command not supported",
"Address type not supported", "Address type not supported",
"Unknown error") "Unknown error")
_socks5autherrors = ("succeeded", _socks5autherrors = ("succeeded",
"authentication is required", "authentication is required",
"all offered authentication methods were rejected", "all offered authentication methods were rejected",
"unknown username or invalid password", "unknown username or invalid password",
"unknown error") "unknown error")
_socks4errors = ("request granted", _socks4errors = ("request granted",
"request rejected or failed", "request rejected or failed",
"request rejected because SOCKS server cannot connect to identd on the client", "request rejected because SOCKS server cannot connect to identd on the client",
"request rejected because the client program and identd report different user-ids", "request rejected because the client program and identd report different user-ids",
"unknown error") "unknown error")
def setdefaultproxy(proxytype=None,addr=None,port=None,rdns=True,username=None,password=None): def setdefaultproxy(proxytype=None,addr=None,port=None,rdns=True,username=None,password=None):
"""setdefaultproxy(proxytype, addr[, port[, rdns[, username[, password]]]]) """setdefaultproxy(proxytype, addr[, port[, rdns[, username[, password]]]])
Sets a default proxy which all further socksocket objects will use, Sets a default proxy which all further socksocket objects will use,
unless explicitly changed. unless explicitly changed.
""" """
global _defaultproxy global _defaultproxy
_defaultproxy = (proxytype,addr,port,rdns,username,password) _defaultproxy = (proxytype,addr,port,rdns,username,password)
class socksocket(socket.socket): class socksocket(socket.socket):
"""socksocket([family[, type[, proto]]]) -> socket object """socksocket([family[, type[, proto]]]) -> socket object
Open a SOCKS enabled socket. The parameters are the same as Open a SOCKS enabled socket. The parameters are the same as
those of the standard socket init. In order for SOCKS to work, those of the standard socket init. In order for SOCKS to work,
you must specify family=AF_INET, type=SOCK_STREAM and proto=0. 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): def __init__(self, family=socket.AF_INET, type=socket.SOCK_STREAM, proto=0, _sock=None):
_orgsocket.__init__(self,family,type,proto,_sock) _orgsocket.__init__(self,family,type,proto,_sock)
if _defaultproxy != None: if _defaultproxy != None:
self.__proxy = _defaultproxy self.__proxy = _defaultproxy
else: else:
self.__proxy = (None, None, None, None, None, None) self.__proxy = (None, None, None, None, None, None)
self.__proxysockname = None self.__proxysockname = None
self.__proxypeername = None self.__proxypeername = None
def __recvall(self, bytes): def __recvall(self, bytes):
"""__recvall(bytes) -> data """__recvall(bytes) -> data
Receive EXACTLY the number of bytes requested from the socket. Receive EXACTLY the number of bytes requested from the socket.
Blocks until the required number of bytes have been received. Blocks until the required number of bytes have been received.
""" """
data = "" data = ""
while len(data) < bytes: while len(data) < bytes:
d = self.recv(bytes-len(data)) d = self.recv(bytes-len(data))
if not d: if not d:
raise GeneralProxyError("connection closed unexpectedly") raise GeneralProxyError("connection closed unexpectedly")
data = data + d data = data + d
return data return data
def setproxy(self,proxytype=None,addr=None,port=None,rdns=True,username=None,password=None): def setproxy(self,proxytype=None,addr=None,port=None,rdns=True,username=None,password=None):
"""setproxy(proxytype, addr[, port[, rdns[, username[, password]]]]) """setproxy(proxytype, addr[, port[, rdns[, username[, password]]]])
Sets the proxy to be used. Sets the proxy to be used.
proxytype - The type of the proxy to be used. Three types proxytype - The type of the proxy to be used. Three types
are supported: PROXY_TYPE_SOCKS4 (including socks4a), are supported: PROXY_TYPE_SOCKS4 (including socks4a),
PROXY_TYPE_SOCKS5 and PROXY_TYPE_HTTP PROXY_TYPE_SOCKS5 and PROXY_TYPE_HTTP
addr - The address of the server (IP or DNS). addr - The address of the server (IP or DNS).
port - The port of the server. Defaults to 1080 for SOCKS port - The port of the server. Defaults to 1080 for SOCKS
servers and 8080 for HTTP proxy servers. servers and 8080 for HTTP proxy servers.
rdns - Should DNS queries be preformed on the remote side rdns - Should DNS queries be preformed on the remote side
(rather than the local side). The default is True. (rather than the local side). The default is True.
Note: This has no effect with SOCKS4 servers. Note: This has no effect with SOCKS4 servers.
username - Username to authenticate with to the server. username - Username to authenticate with to the server.
The default is no authentication. The default is no authentication.
password - Password to authenticate with to the server. password - Password to authenticate with to the server.
Only relevant when username is also provided. Only relevant when username is also provided.
""" """
self.__proxy = (proxytype,addr,port,rdns,username,password) self.__proxy = (proxytype,addr,port,rdns,username,password)
def __negotiatesocks5(self,destaddr,destport): def __negotiatesocks5(self,destaddr,destport):
"""__negotiatesocks5(self,destaddr,destport) """__negotiatesocks5(self,destaddr,destport)
Negotiates a connection through a SOCKS5 server. Negotiates a connection through a SOCKS5 server.
""" """
# First we'll send the authentication packages we support. # First we'll send the authentication packages we support.
if (self.__proxy[4]!=None) and (self.__proxy[5]!=None): if (self.__proxy[4]!=None) and (self.__proxy[5]!=None):
# The username/password details were supplied to the # The username/password details were supplied to the
# setproxy method so we support the USERNAME/PASSWORD # setproxy method so we support the USERNAME/PASSWORD
# authentication (in addition to the standard none). # authentication (in addition to the standard none).
self.sendall("\x05\x02\x00\x02") self.sendall("\x05\x02\x00\x02")
else: else:
# No username/password were entered, therefore we # No username/password were entered, therefore we
# only support connections with no authentication. # only support connections with no authentication.
self.sendall("\x05\x01\x00") self.sendall("\x05\x01\x00")
# We'll receive the server's response to determine which # We'll receive the server's response to determine which
# method was selected # method was selected
chosenauth = self.__recvall(2) chosenauth = self.__recvall(2)
if chosenauth[0] != "\x05": if chosenauth[0] != "\x05":
self.close() self.close()
raise GeneralProxyError((1,_generalerrors[1])) raise GeneralProxyError((1,_generalerrors[1]))
# Check the chosen authentication method # Check the chosen authentication method
if chosenauth[1] == "\x00": if chosenauth[1] == "\x00":
# No authentication is required # No authentication is required
pass pass
elif chosenauth[1] == "\x02": elif chosenauth[1] == "\x02":
# Okay, we need to perform a basic username/password # Okay, we need to perform a basic username/password
# authentication. # authentication.
self.sendall("\x01" + chr(len(self.__proxy[4])) + self.__proxy[4] + chr(len(self.__proxy[5])) + self.__proxy[5]) self.sendall("\x01" + chr(len(self.__proxy[4])) + self.__proxy[4] + chr(len(self.__proxy[5])) + self.__proxy[5])
authstat = self.__recvall(2) authstat = self.__recvall(2)
if authstat[0] != "\x01": if authstat[0] != "\x01":
# Bad response # Bad response
self.close() self.close()
raise GeneralProxyError((1,_generalerrors[1])) raise GeneralProxyError((1,_generalerrors[1]))
if authstat[1] != "\x00": if authstat[1] != "\x00":
# Authentication failed # Authentication failed
self.close() self.close()
raise Socks5AuthError,((3,_socks5autherrors[3])) raise Socks5AuthError,((3,_socks5autherrors[3]))
# Authentication succeeded # Authentication succeeded
else: else:
# Reaching here is always bad # Reaching here is always bad
self.close() self.close()
if chosenauth[1] == "\xFF": if chosenauth[1] == "\xFF":
raise Socks5AuthError((2,_socks5autherrors[2])) raise Socks5AuthError((2,_socks5autherrors[2]))
else: else:
raise GeneralProxyError((1,_generalerrors[1])) raise GeneralProxyError((1,_generalerrors[1]))
# Now we can request the actual connection # Now we can request the actual connection
req = "\x05\x01\x00" req = "\x05\x01\x00"
# If the given destination address is an IP address, we'll # If the given destination address is an IP address, we'll
# use the IPv4 address request even if remote resolving was specified. # use the IPv4 address request even if remote resolving was specified.
try: try:
ipaddr = socket.inet_aton(destaddr) ipaddr = socket.inet_aton(destaddr)
req = req + "\x01" + ipaddr req = req + "\x01" + ipaddr
except socket.error: except socket.error:
# Well it's not an IP number, so it's probably a DNS name. # Well it's not an IP number, so it's probably a DNS name.
if self.__proxy[3]==True: if self.__proxy[3]==True:
# Resolve remotely # Resolve remotely
ipaddr = None ipaddr = None
req = req + "\x03" + chr(len(destaddr)) + destaddr req = req + "\x03" + chr(len(destaddr)) + destaddr
else: else:
# Resolve locally # Resolve locally
ipaddr = socket.inet_aton(socket.gethostbyname(destaddr)) ipaddr = socket.inet_aton(socket.gethostbyname(destaddr))
req = req + "\x01" + ipaddr req = req + "\x01" + ipaddr
req = req + struct.pack(">H",destport) req = req + struct.pack(">H",destport)
self.sendall(req) self.sendall(req)
# Get the response # Get the response
resp = self.__recvall(4) resp = self.__recvall(4)
if resp[0] != "\x05": if resp[0] != "\x05":
self.close() self.close()
raise GeneralProxyError((1,_generalerrors[1])) raise GeneralProxyError((1,_generalerrors[1]))
elif resp[1] != "\x00": elif resp[1] != "\x00":
# Connection failed # Connection failed
self.close() self.close()
if ord(resp[1])<=8: if ord(resp[1])<=8:
raise Socks5Error((ord(resp[1]),_generalerrors[ord(resp[1])])) raise Socks5Error((ord(resp[1]),_generalerrors[ord(resp[1])]))
else: else:
raise Socks5Error((9,_generalerrors[9])) raise Socks5Error((9,_generalerrors[9]))
# Get the bound address/port # Get the bound address/port
elif resp[3] == "\x01": elif resp[3] == "\x01":
boundaddr = self.__recvall(4) boundaddr = self.__recvall(4)
elif resp[3] == "\x03": elif resp[3] == "\x03":
resp = resp + self.recv(1) resp = resp + self.recv(1)
boundaddr = self.__recvall(ord(resp[4])) boundaddr = self.__recvall(ord(resp[4]))
else: else:
self.close() self.close()
raise GeneralProxyError((1,_generalerrors[1])) raise GeneralProxyError((1,_generalerrors[1]))
boundport = struct.unpack(">H",self.__recvall(2))[0] boundport = struct.unpack(">H",self.__recvall(2))[0]
self.__proxysockname = (boundaddr,boundport) self.__proxysockname = (boundaddr,boundport)
if ipaddr != None: if ipaddr != None:
self.__proxypeername = (socket.inet_ntoa(ipaddr),destport) self.__proxypeername = (socket.inet_ntoa(ipaddr),destport)
else: else:
self.__proxypeername = (destaddr,destport) self.__proxypeername = (destaddr,destport)
def getproxysockname(self): def getproxysockname(self):
"""getsockname() -> address info """getsockname() -> address info
Returns the bound IP address and port number at the proxy. Returns the bound IP address and port number at the proxy.
""" """
return self.__proxysockname return self.__proxysockname
def getproxypeername(self): def getproxypeername(self):
"""getproxypeername() -> address info """getproxypeername() -> address info
Returns the IP and port number of the proxy. Returns the IP and port number of the proxy.
""" """
return _orgsocket.getpeername(self) return _orgsocket.getpeername(self)
def getpeername(self): def getpeername(self):
"""getpeername() -> address info """getpeername() -> address info
Returns the IP address and port number of the destination Returns the IP address and port number of the destination
machine (note: getproxypeername returns the proxy) machine (note: getproxypeername returns the proxy)
""" """
return self.__proxypeername return self.__proxypeername
def __negotiatesocks4(self,destaddr,destport): def __negotiatesocks4(self,destaddr,destport):
"""__negotiatesocks4(self,destaddr,destport) """__negotiatesocks4(self,destaddr,destport)
Negotiates a connection through a SOCKS4 server. Negotiates a connection through a SOCKS4 server.
""" """
# Check if the destination address provided is an IP address # Check if the destination address provided is an IP address
rmtrslv = False rmtrslv = False
try: try:
ipaddr = socket.inet_aton(destaddr) ipaddr = socket.inet_aton(destaddr)
except socket.error: except socket.error:
# It's a DNS name. Check where it should be resolved. # It's a DNS name. Check where it should be resolved.
if self.__proxy[3]==True: if self.__proxy[3]==True:
ipaddr = "\x00\x00\x00\x01" ipaddr = "\x00\x00\x00\x01"
rmtrslv = True rmtrslv = True
else: else:
ipaddr = socket.inet_aton(socket.gethostbyname(destaddr)) ipaddr = socket.inet_aton(socket.gethostbyname(destaddr))
# Construct the request packet # Construct the request packet
req = "\x04\x01" + struct.pack(">H",destport) + ipaddr req = "\x04\x01" + struct.pack(">H",destport) + ipaddr
# The username parameter is considered userid for SOCKS4 # The username parameter is considered userid for SOCKS4
if self.__proxy[4] != None: if self.__proxy[4] != None:
req = req + self.__proxy[4] req = req + self.__proxy[4]
req = req + "\x00" req = req + "\x00"
# DNS name if remote resolving is required # DNS name if remote resolving is required
# NOTE: This is actually an extension to the SOCKS4 protocol # NOTE: This is actually an extension to the SOCKS4 protocol
# called SOCKS4A and may not be supported in all cases. # called SOCKS4A and may not be supported in all cases.
if rmtrslv==True: if rmtrslv==True:
req = req + destaddr + "\x00" req = req + destaddr + "\x00"
self.sendall(req) self.sendall(req)
# Get the response from the server # Get the response from the server
resp = self.__recvall(8) resp = self.__recvall(8)
if resp[0] != "\x00": if resp[0] != "\x00":
# Bad data # Bad data
self.close() self.close()
raise GeneralProxyError((1,_generalerrors[1])) raise GeneralProxyError((1,_generalerrors[1]))
if resp[1] != "\x5A": if resp[1] != "\x5A":
# Server returned an error # Server returned an error
self.close() self.close()
if ord(resp[1]) in (91,92,93): if ord(resp[1]) in (91,92,93):
self.close() self.close()
raise Socks4Error((ord(resp[1]),_socks4errors[ord(resp[1])-90])) raise Socks4Error((ord(resp[1]),_socks4errors[ord(resp[1])-90]))
else: else:
raise Socks4Error((94,_socks4errors[4])) raise Socks4Error((94,_socks4errors[4]))
# Get the bound address/port # Get the bound address/port
self.__proxysockname = (socket.inet_ntoa(resp[4:]),struct.unpack(">H",resp[2:4])[0]) self.__proxysockname = (socket.inet_ntoa(resp[4:]),struct.unpack(">H",resp[2:4])[0])
if rmtrslv != None: if rmtrslv != None:
self.__proxypeername = (socket.inet_ntoa(ipaddr),destport) self.__proxypeername = (socket.inet_ntoa(ipaddr),destport)
else: else:
self.__proxypeername = (destaddr,destport) self.__proxypeername = (destaddr,destport)
def __negotiatehttp(self,destaddr,destport): def __negotiatehttp(self,destaddr,destport):
"""__negotiatehttp(self,destaddr,destport) """__negotiatehttp(self,destaddr,destport)
Negotiates a connection through an HTTP server. Negotiates a connection through an HTTP server.
""" """
# If we need to resolve locally, we do this now # If we need to resolve locally, we do this now
if self.__proxy[3] == False: if self.__proxy[3] == False:
addr = socket.gethostbyname(destaddr) addr = socket.gethostbyname(destaddr)
else: else:
addr = destaddr addr = destaddr
self.sendall("CONNECT " + addr + ":" + str(destport) + " HTTP/1.1\r\n" + "Host: " + destaddr + "\r\n\r\n") 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" # We read the response until we get the string "\r\n\r\n"
resp = self.recv(1) resp = self.recv(1)
while resp.find("\r\n\r\n")==-1: while resp.find("\r\n\r\n")==-1:
resp = resp + self.recv(1) resp = resp + self.recv(1)
# We just need the first line to check if the connection # We just need the first line to check if the connection
# was successful # was successful
statusline = resp.splitlines()[0].split(" ",2) statusline = resp.splitlines()[0].split(" ",2)
if statusline[0] not in ("HTTP/1.0","HTTP/1.1"): if statusline[0] not in ("HTTP/1.0","HTTP/1.1"):
self.close() self.close()
raise GeneralProxyError((1,_generalerrors[1])) raise GeneralProxyError((1,_generalerrors[1]))
try: try:
statuscode = int(statusline[1]) statuscode = int(statusline[1])
except ValueError: except ValueError:
self.close() self.close()
raise GeneralProxyError((1,_generalerrors[1])) raise GeneralProxyError((1,_generalerrors[1]))
if statuscode != 200: if statuscode != 200:
self.close() self.close()
raise HTTPError((statuscode,statusline[2])) raise HTTPError((statuscode,statusline[2]))
self.__proxysockname = ("0.0.0.0",0) self.__proxysockname = ("0.0.0.0",0)
self.__proxypeername = (addr,destport) self.__proxypeername = (addr,destport)
def connect(self,destpair): def connect(self,destpair):
"""connect(self,despair) """connect(self,despair)
Connects to the specified destination through a proxy. Connects to the specified destination through a proxy.
destpar - A tuple of the IP/DNS address and the port number. destpar - A tuple of the IP/DNS address and the port number.
(identical to socket's connect). (identical to socket's connect).
To select the proxy server use setproxy(). To select the proxy server use setproxy().
""" """
# Do a minimal input check first # 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): 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])) raise GeneralProxyError((5,_generalerrors[5]))
if self.__proxy[0] == PROXY_TYPE_SOCKS5: if self.__proxy[0] == PROXY_TYPE_SOCKS5:
if self.__proxy[2] != None: if self.__proxy[2] != None:
portnum = self.__proxy[2] portnum = self.__proxy[2]
else: else:
portnum = 1080 portnum = 1080
_orgsocket.connect(self,(self.__proxy[1],portnum)) _orgsocket.connect(self,(self.__proxy[1],portnum))
self.__negotiatesocks5(destpair[0],destpair[1]) self.__negotiatesocks5(destpair[0],destpair[1])
elif self.__proxy[0] == PROXY_TYPE_SOCKS4: elif self.__proxy[0] == PROXY_TYPE_SOCKS4:
if self.__proxy[2] != None: if self.__proxy[2] != None:
portnum = self.__proxy[2] portnum = self.__proxy[2]
else: else:
portnum = 1080 portnum = 1080
_orgsocket.connect(self,(self.__proxy[1],portnum)) _orgsocket.connect(self,(self.__proxy[1],portnum))
self.__negotiatesocks4(destpair[0],destpair[1]) self.__negotiatesocks4(destpair[0],destpair[1])
elif self.__proxy[0] == PROXY_TYPE_HTTP: elif self.__proxy[0] == PROXY_TYPE_HTTP:
if self.__proxy[2] != None: if self.__proxy[2] != None:
portnum = self.__proxy[2] portnum = self.__proxy[2]
else: else:
portnum = 8080 portnum = 8080
_orgsocket.connect(self,(self.__proxy[1],portnum)) _orgsocket.connect(self,(self.__proxy[1],portnum))
self.__negotiatehttp(destpair[0],destpair[1]) self.__negotiatehttp(destpair[0],destpair[1])
elif self.__proxy[0] == None: elif self.__proxy[0] == None:
_orgsocket.connect(self,(destpair[0],destpair[1])) _orgsocket.connect(self,(destpair[0],destpair[1]))
else: else:
raise GeneralProxyError((4,_generalerrors[4])) raise GeneralProxyError((4,_generalerrors[4]))

207
src/searchengine/nova3/engines/extratorrent.py
View file

@ -1,4 +1,4 @@
#VERSION: 1.2 #VERSION: 2.0
#AUTHORS: Christophe Dumez (chris@qbittorrent.org) #AUTHORS: Christophe Dumez (chris@qbittorrent.org)
# Redistribution and use in source and binary forms, with or without # Redistribution and use in source and binary forms, with or without
@ -25,92 +25,139 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE # ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE. # POSSIBILITY OF SUCH DAMAGE.
from html.parser import HTMLParser
from http.client import HTTPConnection as http
#qBt
from novaprinter import prettyPrinter from novaprinter import prettyPrinter
from helpers import retrieve_url, download_file from helpers import download_file
import sgmllib3
import re
class extratorrent(object): class extratorrent(object):
url = 'http://extratorrent.cc' """ Search engine class """
name = 'extratorrent' url = 'http://extratorrent.cc'
supported_categories = {'all': '', 'movies': '4', 'tv': '8', 'music': '5', 'games': '3', 'anime': '1', 'software': '7', 'books': '2', 'pictures': '6'} name = 'ExtraTorrent'
supported_categories = {'all' : '0',
'movies' : '4',
'tv' : '8',
'music' : '5',
'games' : '3',
'anime' : '1',
'software' : '7',
'books' : '2',
'pictures' : '6'}
def __init__(self): def download_torrent(self, info):
self.results = [] """ Downloader """
self.parser = self.SimpleSGMLParser(self.results, self.url) print(download_file(info))
def download_torrent(self, info): class MyHtmlParseWithBlackJack(HTMLParser):
print(download_file(info)) """ Parser class """
def __init__(self, list_searches, url):
HTMLParser.__init__(self)
self.url = url
self.list_searches = list_searches
self.current_item = None
self.cur_item_name = None
self.pending_size = False
self.next_queries = True
self.pending_next_queries = False
self.next_queries_set = set()
class SimpleSGMLParser(sgmllib3.SGMLParser): def handle_starttag(self, tag, attrs):
def __init__(self, results, url, *args):
sgmllib3.SGMLParser.__init__(self)
self.url = url
self.td_counter = None
self.current_item = None
self.start_name = False
self.results = results
def start_a(self, attr):
params = dict(attr)
#print params
if 'href' in params and params['href'].startswith("/torrent_download/"):
self.current_item = {}
self.td_counter = 0
self.start_name = False
torrent_id = '/'.join(params['href'].split('/')[2:])
self.current_item['link']=self.url+'/download/'+torrent_id
elif 'href' in params and params['href'].startswith("/torrent/") and params['href'].endswith(".html"):
self.current_item['desc_link'] = self.url + params['href'].strip()
self.start_name = True
def handle_data(self, data):
if self.td_counter == 2:
if 'name' not in self.current_item and self.start_name:
self.current_item['name'] = data.strip()
elif self.td_counter == 3:
if 'size' not in self.current_item:
self.current_item['size'] = ''
self.current_item['size']+= data.replace("&nbsp;", " ").strip()
elif self.td_counter == 4:
if 'seeds' not in self.current_item:
self.current_item['seeds'] = ''
self.current_item['seeds']+= data.strip()
elif self.td_counter == 5:
if 'leech' not in self.current_item:
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 > 5:
self.td_counter = None
# Display item
if self.current_item: if self.current_item:
self.current_item['engine_url'] = self.url if tag == "a":
if not self.current_item['seeds'].isdigit(): params = dict(attrs)
self.current_item['seeds'] = 0 link = params['href']
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'): if not link.startswith("/torrent"):
ret = [] return
i = 1
while True and i<11: if link[8] == "/":
results = [] #description
parser = self.SimpleSGMLParser(results, self.url) self.current_item["desc_link"] = "".join((self.url, link))
dat = retrieve_url(self.url+'/advanced_search/?with=%s&s_cat=%s&page=%d'%(what, self.supported_categories[cat], i)) #remove view at the beginning
results_re = re.compile('(?s)<table class="tl"><thead>.*') self.current_item["name"] = params["title"][5:].replace("&amp;", "&")
for match in results_re.finditer(dat): self.pending_size = True
res_tab = match.group(0) elif link[8] == "_":
parser.feed(res_tab) #download link
link = link.replace("torrent_", "", 1)
self.current_item["link"] = "".join((self.url, link))
elif tag == "td":
if self.pending_size:
self.cur_item_name = "size"
self.current_item["size"] = ""
self.pending_size = False
for attr in attrs:
if attr[0] == "class":
if attr[1][0] == "s":
self.cur_item_name = "seeds"
self.current_item["seeds"] = ""
elif attr[1][0] == "l":
self.cur_item_name = "leech"
self.current_item["leech"] = ""
break
elif tag == "tr":
for attr in attrs:
if attr[0] == "class" and attr[1].startswith("tl"):
self.current_item = dict()
self.current_item["engine_url"] = self.url
break
elif self.pending_next_queries:
if tag == "a":
params = dict(attrs)
if params["title"] in self.next_queries_set:
return
self.list_searches.append(params['href'])
self.next_queries_set.add(params["title"])
if params["title"] == "10":
self.pending_next_queries = False
else:
self.pending_next_queries = False
elif self.next_queries:
if tag == "b" and ("class", "pager_no_link") in attrs:
self.next_queries = False
self.pending_next_queries = True
def handle_data(self, data):
if self.cur_item_name:
temp = self.current_item[self.cur_item_name]
self.current_item[self.cur_item_name] = " ".join((temp, data))
#Due to utf-8 we need to handle data two times if there is space
if not self.cur_item_name == "size":
self.cur_item_name = None
def handle_endtag(self, tag):
if self.current_item:
if tag == "tr":
prettyPrinter(self.current_item)
self.current_item = None
def search(self, what, cat="all"):
""" Performs search """
connection = http("extratorrent.cc")
query = "".join(("/search/?new=1&search=", what, "&s_cat=", self.supported_categories[cat]))
connection.request("GET", query)
response = connection.getresponse()
if response.status != 200:
return
list_searches = []
parser = self.MyHtmlParseWithBlackJack(list_searches, self.url)
parser.feed(response.read().decode('utf-8'))
parser.close() parser.close()
break
if len(results) <= 0:
break
i += 1
for search_query in list_searches:
connection.request("GET", search_query)
response = connection.getresponse()
parser.feed(response.read().decode('utf-8'))
parser.close()
connection.close()
return

6
src/searchengine/nova3/engines/legittorrents.py
View file

@ -1,4 +1,4 @@
#VERSION: 1.03 #VERSION: 1.04
#AUTHORS: Christophe Dumez (chris@qbittorrent.org) #AUTHORS: Christophe Dumez (chris@qbittorrent.org)
# Redistribution and use in source and binary forms, with or without # Redistribution and use in source and binary forms, with or without
@ -36,10 +36,6 @@ class legittorrents(object):
name = 'legittorrents' name = 'legittorrents'
supported_categories = {'all': '', 'movies': '1', 'tv': '13', 'music': '2', 'games': '3', 'anime': '5', 'books': '6'} supported_categories = {'all': '', 'movies': '1', 'tv': '13', 'music': '2', 'games': '3', 'anime': '5', 'books': '6'}
def __init__(self):
self.results = []
self.parser = self.SimpleSGMLParser(self.results, self.url)
def download_torrent(self, info): def download_torrent(self, info):
print(download_file(info)) print(download_file(info))

185
src/searchengine/nova3/engines/mininova.py
View file

@ -1,4 +1,4 @@
#VERSION: 1.51 #VERSION: 2.00
#AUTHORS: Christophe Dumez (chris@qbittorrent.org) #AUTHORS: Christophe Dumez (chris@qbittorrent.org)
#CONTRIBUTORS: Diego de las Heras (diegodelasheras@gmail.com) #CONTRIBUTORS: Diego de las Heras (diegodelasheras@gmail.com)
@ -26,90 +26,123 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE # ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE. # POSSIBILITY OF SUCH DAMAGE.
from html.parser import HTMLParser
from http.client import HTTPConnection as http
from novaprinter import prettyPrinter from novaprinter import prettyPrinter
from helpers import retrieve_url, download_file from helpers import download_file
import sgmllib3
import re
class mininova(object): class mininova(object):
# Mandatory properties """ Search engine class """
url = 'http://www.mininova.org' url = 'http://www.mininova.org'
name = 'Mininova' name = 'Mininova'
supported_categories = {'all': '0', 'movies': '4', 'tv': '8', 'music': '5', 'games': '3', 'anime': '1', 'software': '7', 'pictures': '6', 'books': '2'} supported_categories = {'all' : '0',
'movies' : '4',
'tv' : '8',
'music' : '5',
'games' : '3',
'anime' : '1',
'software' : '7',
'pictures' : '6',
'books' : '2'}
def __init__(self): def download_torrent(self, info):
self.results = [] print(download_file(info))
self.parser = self.SimpleSGMLParser(self.results, self.url)
def download_torrent(self, info): class MyHtmlParseWithBlackJack(HTMLParser):
print(download_file(info)) """ Parser class """
def __init__(self, list_searches, url):
HTMLParser.__init__(self)
self.list_searches = list_searches
self.url = url
self.table_results = False
self.current_item = None
self.cur_item_name = None
self.next_queries = True
class SimpleSGMLParser(sgmllib3.SGMLParser): def handle_starttag_tr(self, _):
def __init__(self, results, url, *args): """ Handler of tr start tag """
sgmllib3.SGMLParser.__init__(self) self.current_item = dict()
self.url = url
self.td_counter = None
self.current_item = None
self.results = results
def start_a(self, attr): def handle_starttag_a(self, attrs):
params = dict(attr) """ Handler of a start tag """
#print params params = dict(attrs)
if 'href' in params: link = params["href"]
if params['href'].startswith("/get/"):
self.current_item = {}
self.td_counter = 0
self.current_item['link']=self.url+params['href'].strip()
elif params['href'].startswith("/tor/") and self.current_item is not None:
self.current_item['desc_link']=self.url+params['href'].strip()
def handle_data(self, data): if link.startswith("/tor/"):
if self.td_counter == 0: #description
if 'name' not in self.current_item: self.current_item["desc_link"] = "".join((self.url, link))
self.current_item['name'] = '' #get download link from description by id
self.current_item['name']+= data self.current_item["link"] = "".join((self.url, "/get/", link[5:-2]))
elif self.td_counter == 1: self.cur_item_name = "name"
if 'size' not in self.current_item: self.current_item["name"] = ""
self.current_item['size'] = '' elif self.next_queries and link.startswith("/search"):
self.current_item['size']+= data.strip() if params["title"].startswith("Page"):
elif self.td_counter == 2: self.list_searches.append(link)
if 'seeds' not in self.current_item:
self.current_item['seeds'] = ''
self.current_item['seeds']+= data.strip()
elif self.td_counter == 3:
if 'leech' not in self.current_item:
self.current_item['leech'] = ''
self.current_item['leech']+= data.strip()
def start_td(self,attr): def handle_starttag_td(self, attrs):
if isinstance(self.td_counter,int): """ Handler of td start tag """
self.td_counter += 1 if ("align", "right") in attrs:
if self.td_counter > 4: if not "size" in self.current_item:
self.td_counter = None self.cur_item_name = "size"
# Display item self.current_item["size"] = ""
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'): def handle_starttag_span(self, attrs):
ret = [] """ Handler of span start tag """
i = 1 if ("class", "g") in attrs:
while True and i<11: self.cur_item_name = "seeds"
results = [] self.current_item["seeds"] = ""
parser = self.SimpleSGMLParser(results, self.url) elif ("class", "b") in attrs:
dat = retrieve_url(self.url+'/search/%s/%s/seeds/%d'%(what, self.supported_categories[cat], i)) self.cur_item_name = "leech"
results_re = re.compile('(?s)<h1>Search results for.*') self.current_item["leech"] = ""
for match in results_re.finditer(dat):
res_tab = match.group(0) def handle_starttag(self, tag, attrs):
parser.feed(res_tab) """ Parser's start tag handler """
if self.table_results:
dispatcher = getattr(self, "_".join(("handle_starttag", tag)), None)
if dispatcher:
dispatcher(attrs)
elif tag == "table":
self.table_results = ("class", "maintable") in attrs
def handle_endtag(self, tag):
""" Parser's end tag handler """
if tag == "tr" and self.current_item:
self.current_item["engine_url"] = self.url
prettyPrinter(self.current_item)
self.current_item = None
elif self.cur_item_name:
if tag == "a" or tag == "td":
self.cur_item_name = None
def handle_data(self, data):
""" Parser's data handler """
if self.cur_item_name:
temp = self.current_item[self.cur_item_name]
self.current_item[self.cur_item_name] = " ".join((temp, data))
def search(self, what, cat="all"):
""" Performs search """
connection = http("www.mininova.org")
query = "/".join(("/search", what, self.supported_categories[cat], "seeds"))
connection.request("GET", query)
response = connection.getresponse()
if response.status != 200:
return
list_searches = []
parser = self.MyHtmlParseWithBlackJack(list_searches, self.url)
parser.feed(response.read().decode('utf-8'))
parser.close() parser.close()
break
if len(results) <= 0:
break
i += 1
parser.next_queries = False
for search_query in list_searches:
connection.request("GET", search_query)
response = connection.getresponse()
parser.feed(response.read().decode('utf-8'))
parser.close()
connection.close()
return

BIN
src/searchengine/nova3/engines/torrentreactor.png
View file

Binary file not shown.
Side by side Swipe Overlay

Before

Width:  |  Height:  |  Size: 252 B

After

Width:  |  Height:  |  Size: 951 B

Before After
Before After

149
src/searchengine/nova3/engines/torrentreactor.py
View file

@ -1,4 +1,4 @@
#VERSION: 1.33 #VERSION: 1.36
#AUTHORS: Gekko Dam Beer (gekko04@users.sourceforge.net) #AUTHORS: Gekko Dam Beer (gekko04@users.sourceforge.net)
#CONTRIBUTORS: Christophe Dumez (chris@qbittorrent.org) #CONTRIBUTORS: Christophe Dumez (chris@qbittorrent.org)
# Bruno Barbieri (brunorex@gmail.com) # Bruno Barbieri (brunorex@gmail.com)
@ -28,91 +28,84 @@
# POSSIBILITY OF SUCH DAMAGE. # POSSIBILITY OF SUCH DAMAGE.
from novaprinter import prettyPrinter from novaprinter import prettyPrinter
from helpers import retrieve_url, download_file from helpers import download_file, retrieve_url
from urllib import error, parse from urllib import parse
from html.parser import HTMLParser from html.parser import HTMLParser
import re from re import compile as re_compile
class torrentreactor(object): class torrentreactor(object):
url = 'http://www.torrentreactor.net' url = 'http://www.torrentreactor.net'
name = 'TorrentReactor.Net' name = 'TorrentReactor'
supported_categories = {'all': '', 'movies': '5', 'tv': '8', 'music': '6', 'games': '3', 'anime': '1', 'software': '2'} supported_categories = {'all': '', 'movies': '5', 'tv': '8', 'music': '6', 'games': '3', 'anime': '1', 'software': '2'}
def download_torrent(self, info): def download_torrent(self, info):
print(download_file(info)) print(download_file(info))
class SimpleHTMLParser(HTMLParser): class SimpleHTMLParser(HTMLParser):
def __init__(self, results, url, *args): def __init__(self, results, url, *args):
HTMLParser.__init__(self) HTMLParser.__init__(self)
self.td_counter = None self.td_counter = None
self.current_item = None self.current_item = None
self.results = results self.results = results
self.id = None self.id = None
self.url = url self.url = url
self.dispatcher = { 'a' : self.start_a, 'td' : self.start_td } self.torrents_matcher = re_compile("/torrents/\d+.*")
self.dispatcher = { 'a' : self.start_a, 'td' : self.start_td }
def handle_starttag(self, tag, attrs): def handle_starttag(self, tag, attrs):
if tag in self.dispatcher: if tag in self.dispatcher:
self.dispatcher[tag](attrs) self.dispatcher[tag](attrs)
def start_a(self, attr): def start_a(self, attr):
params = dict(attr) params = dict(attr)
if re.match("/torrents/\d+.*", params['href']): if self.torrents_matcher.match(params['href']):
self.current_item = {} self.current_item = {}
self.current_item['desc_link'] = self.url+params['href'].strip() self.current_item['desc_link'] = self.url+params['href'].strip()
elif 'torrentreactor.net/download.php' in params['href']: elif 'torrentreactor.net/download.php' in params['href']:
self.td_counter = 0 self.td_counter = 0
self.current_item['link'] = params['href'].strip() self.current_item['link'] = params['href'].strip()
self.current_item['name'] = parse.unquote_plus(params['href'].split('&')[1].split('name=')[1]) self.current_item['name'] = parse.unquote_plus(params['href'].split('&')[1].split('name=')[1])
def handle_data(self, data): def handle_data(self, data):
if self.td_counter == 1: if self.td_counter == 1:
if 'size' not in self.current_item: if 'size' not in self.current_item:
self.current_item['size'] = '' self.current_item['size'] = ''
self.current_item['size']+= data.strip() self.current_item['size']+= data.strip()
elif self.td_counter == 2: elif self.td_counter == 2:
if 'seeds' not in self.current_item: if 'seeds' not in self.current_item:
self.current_item['seeds'] = '' self.current_item['seeds'] = ''
self.current_item['seeds']+= data.strip() self.current_item['seeds']+= data.strip()
elif self.td_counter == 3: elif self.td_counter == 3:
if 'leech' not in self.current_item: if 'leech' not in self.current_item:
self.current_item['leech'] = '' self.current_item['leech'] = ''
self.current_item['leech']+= data.strip() self.current_item['leech']+= data.strip()
def start_td(self,attr): def start_td(self,attr):
if isinstance(self.td_counter,int): if isinstance(self.td_counter,int):
self.td_counter += 1 self.td_counter += 1
if self.td_counter > 3: if self.td_counter > 3:
self.td_counter = None self.td_counter = None
# add item to results # add item to results
if self.current_item: if self.current_item:
self.current_item['engine_url'] = self.url self.current_item['engine_url'] = self.url
if not self.current_item['seeds'].isdigit(): if not self.current_item['seeds'].isdigit():
self.current_item['seeds'] = 0 self.current_item['seeds'] = 0
if not self.current_item['leech'].isdigit(): if not self.current_item['leech'].isdigit():
self.current_item['leech'] = 0 self.current_item['leech'] = 0
prettyPrinter(self.current_item) prettyPrinter(self.current_item)
self.has_results = True self.has_results = True
self.results.append('a') self.results.append('a')
def __init__(self): def search(self, what, cat='all'):
self.results = [] i = 0
self.parser = self.SimpleHTMLParser(self.results, self.url) dat = ''
def search(self, what, cat='all'): while i < 11:
i = 0 results = []
dat = '' parser = self.SimpleHTMLParser(results, self.url)
while True and i<11: dat = retrieve_url('%s/torrent-search/%s/%s?sort=seeders.desc&type=all&period=none&categories=%s'%(self.url, what, (i*35), self.supported_categories[cat]))
results = [] parser.feed(dat)
parser = self.SimpleHTMLParser(results, self.url) parser.close()
if len(results) <= 0:
try: break
dat = retrieve_url(self.url+'/torrent-search/%s/%s?sort=seeders.desc&type=all&period=none&categories=%s'%(what, (i*35), self.supported_categories[cat])) i += 1
except error.HTTPError:
break
parser.feed(dat)
parser.close()
if len(results) <= 0:
break
i += 1

2
src/searchengine/nova3/engines/torrentz.py
View file

@ -1,4 +1,4 @@
#VERSION: 2.13 #VERSION: 2.14
#AUTHORS: Diego de las Heras (diegodelasheras@gmail.com) #AUTHORS: Diego de las Heras (diegodelasheras@gmail.com)
# Redistribution and use in source and binary forms, with or without # Redistribution and use in source and binary forms, with or without

11
src/searchengine/nova3/engines/versions.txt
View file

@ -1,8 +1,9 @@
torrentreactor: 1.33
mininova: 1.51
piratebay: 2.11
extratorrent: 1.2 extratorrent: 1.2
torrentreactor: 1.36
mininova: 2.00
piratebay: 2.11
extratorrent: 2.0
kickasstorrents: 1.26 kickasstorrents: 1.26
btdigg: 1.23 btdigg: 1.23
legittorrents: 1.03 torrentz: 2.14
torrentz: 2.13 legittorrents: 1.04

216
src/searchengine/nova3/nova2.py
View file

@ -26,7 +26,7 @@
# POSSIBILITY OF SUCH DAMAGE. # POSSIBILITY OF SUCH DAMAGE.
#VERSION: 1.24 #VERSION: 1.40
# Author: # Author:
# Fabien Devaux <fab AT gnux DOT info> # Fabien Devaux <fab AT gnux DOT info>
@ -37,14 +37,14 @@
# #
# Licence: BSD # Licence: BSD
import sys
import threading
import os
import glob
import urllib.parse import urllib.parse
from os import path, cpu_count
from glob import glob
from sys import argv
from multiprocessing import Pool
THREADED = True THREADED = True
CATEGORIES = ('all', 'movies', 'tv', 'music', 'games', 'anime', 'software', 'pictures', 'books') CATEGORIES = {'all', 'movies', 'tv', 'music', 'games', 'anime', 'software', 'pictures', 'books'}
################################################################################ ################################################################################
# Every engine should have a "search" method taking # Every engine should have a "search" method taking
@ -54,105 +54,129 @@ CATEGORIES = ('all', 'movies', 'tv', 'music', 'games', 'anime', 'software', 'pic
# As a convention, try to list results by decrasing number of seeds or similar # As a convention, try to list results by decrasing number of seeds or similar
################################################################################ ################################################################################
supported_engines = [] def initialize_engines():
""" Import available engines
engines = glob.glob(os.path.join(os.path.dirname(__file__), 'engines','*.py')) Return list of available engines
for engine in engines: """
e = engine.split(os.sep)[-1][:-3] supported_engines = []
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): engines = glob(path.join(path.dirname(__file__), 'engines', '*.py'))
xml = "<%s>\n"%short_name for engine in engines:
exec("search_engine = %s()"%short_name, globals()) engi = path.basename(engine).split('.')[0].strip()
xml += "<name>%s</name>\n"%search_engine.name if len(engi) == 0 or engi.startswith('_'):
xml += "<url>%s</url>\n"%search_engine.url continue
xml += "<categories>" try:
if hasattr(search_engine, 'supported_categories'): #import engines.[engine]
supported_categories = list(search_engine.supported_categories.keys()) engine_module = __import__(".".join(("engines", engi)))
supported_categories.remove('all') #get low-level module
xml += " ".join(supported_categories) engine_module = getattr(engine_module, engi)
xml += "</categories>\n" #bind class name
xml += "</%s>\n"%short_name globals()[engi] = getattr(engine_module, engi)
return xml supported_engines.append(engi)
except:
pass
def displayCapabilities(): return supported_engines
"""
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 engines_to_xml(supported_engines):
def __init__(self, engine, what, cat='all'): """ Generates xml for supported engines """
threading.Thread.__init__(self) tab = " " * 4
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 list(self.engine.supported_categories.keys()):
self.engine.search(self.what, self.cat)
elif self.cat == 'all':
self.engine.search(self.what)
if __name__ == '__main__': for short_name in supported_engines:
if len(sys.argv) < 2: search_engine = globals()[short_name]()
raise SystemExit('./nova2.py [all|engine1[,engine2]*] <category> <keywords>\navailable engines: %s'%
(','.join(supported_engines)))
if len(sys.argv) == 2: supported_categories = ""
if sys.argv[1] == "--capabilities": if hasattr(search_engine, "supported_categories"):
displayCapabilities() supported_categories = " ".join((key for key in search_engine.supported_categories.keys()
sys.exit(0) if key is not "all"))
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(',')] yield "".join((tab, "<", short_name, ">\n",
tab, tab, "<name>", search_engine.name, "</name>\n",
tab, tab, "<url>", search_engine.url, "</url>\n",
tab, tab, "<categories>", supported_categories, "</categories>\n",
tab, "</", short_name, ">\n"))
if 'all' in engines_list: def displayCapabilities(supported_engines):
engines_list = supported_engines """
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 = "".join(("<capabilities>\n",
"".join(engines_to_xml(supported_engines)),
"</capabilities>"))
print(xml)
cat = sys.argv[2].lower() def run_search(engine_list):
""" Run search in engine
if cat not in CATEGORIES: @param engine_list List with engine, query and category
raise SystemExit('Invalid category!')
what = urllib.parse.quote(' '.join(sys.argv[3:])) @retval False if any exceptions occured
@retval True otherwise
"""
engine, what, cat = engine_list
try:
engine = engine()
#avoid exceptions due to invalid category
if hasattr(engine, 'supported_categories'):
cat = cat if cat in engine.supported_categories else "all"
engine.search(what, cat)
else:
engine.search(what)
threads = [] return True
for engine in engines_list: except:
try: return False
if THREADED:
exec("l = EngineLauncher(%s(), what, cat)"%engine) def main(args):
threads.append(l) supported_engines = initialize_engines()
l.start()
else: if not args:
exec("e = %s()"%engine) raise SystemExit("./nova2.py [all|engine1[,engine2]*] <category> <keywords>\n"
if hasattr(engine, 'supported_categories'): "available engines: %s" % (','.join(supported_engines)))
if cat == 'all' or cat in list(e.supported_categories.keys()):
e.search(what, cat) elif args[0] == "--capabilities":
elif self.cat == 'all': displayCapabilities(supported_engines)
e.search(what) return
engine().search(what, cat)
except: elif len(args) < 3:
pass raise SystemExit("./nova2.py [all|engine1[,engine2]*] <category> <keywords>\n"
if THREADED: "available engines: %s" % (','.join(supported_engines)))
for t in threads:
t.join() #get only unique engines with set
engines_list = set(e.lower() for e in args[0].strip().split(','))
if 'all' in engines_list:
engines_list = supported_engines
else:
#discard un-supported engines
engines_list = [engine for engine in engines_list
if engine in supported_engines]
if not engines_list:
#engine list is empty. Nothing to do here
return
cat = args[1].lower()
if cat not in CATEGORIES:
raise SystemExit(" - ".join(('Invalid category', cat)))
what = urllib.parse.quote(' '.join(args[2:]))
if THREADED:
#child process spawning is controlled min(number of searches, number of cpu)
with Pool(min(len(engines_list), cpu_count())) as pool:
pool.map(run_search, ([globals()[engine], what, cat] for engine in engines_list))
else:
#py3 note: map is needed to be evaluated for content to be executed
all(map(run_search, ([globals()[engine], what, cat] for engine in engines_list)))
if __name__ == "__main__":
main(argv[1:])

44
src/searchengine/nova3/nova2dl.py
View file

@ -25,7 +25,7 @@
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE # ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE. # POSSIBILITY OF SUCH DAMAGE.
#VERSION: 1.10 #VERSION: 1.20
# Author: # Author:
# Christophe DUMEZ (chris@qbittorrent.org) # Christophe DUMEZ (chris@qbittorrent.org)
@ -39,26 +39,26 @@ supported_engines = dict()
engines = glob.glob(os.path.join(os.path.dirname(__file__), 'engines','*.py')) engines = glob.glob(os.path.join(os.path.dirname(__file__), 'engines','*.py'))
for engine in engines: for engine in engines:
e = engine.split(os.sep)[-1][:-3] e = engine.split(os.sep)[-1][:-3]
if len(e.strip()) == 0: continue if len(e.strip()) == 0: continue
if e.startswith('_'): continue if e.startswith('_'): continue
try: try:
exec("from engines.%s import %s"%(e,e)) exec("from engines.%s import %s"%(e,e))
exec("engine_url = %s.url"%e) exec("engine_url = %s.url"%e)
supported_engines[engine_url] = e supported_engines[engine_url] = e
except: except:
pass pass
if __name__ == '__main__': if __name__ == '__main__':
if len(sys.argv) < 3: if len(sys.argv) < 3:
raise SystemExit('./nova2dl.py engine_url download_parameter') raise SystemExit('./nova2dl.py engine_url download_parameter')
engine_url = sys.argv[1].strip() engine_url = sys.argv[1].strip()
download_param = sys.argv[2].strip() download_param = sys.argv[2].strip()
if engine_url not in list(supported_engines.keys()): if engine_url not in list(supported_engines.keys()):
raise SystemExit('./nova2dl.py: this engine_url was not recognized') raise SystemExit('./nova2dl.py: this engine_url was not recognized')
exec("engine = %s()"%supported_engines[engine_url]) exec("engine = %s()"%supported_engines[engine_url])
if hasattr(engine, 'download_torrent'): if hasattr(engine, 'download_torrent'):
engine.download_torrent(download_param) engine.download_torrent(download_param)
else: else:
print(download_file(download_param)) print(download_file(download_param))
sys.exit(0) sys.exit(0)

66
src/searchengine/nova3/novaprinter.py
View file

@ -26,41 +26,39 @@
def prettyPrinter(dictionary): def prettyPrinter(dictionary):
outtext = '' dictionary['size'] = anySizeToBytes(dictionary['size'])
dictionary['size'] = anySizeToBytes(dictionary['size']) outtext = "|".join((dictionary["link"], dictionary["name"].replace("|", " "), str(dictionary["size"]), str(dictionary["seeds"]), str(dictionary["leech"]), dictionary["engine_url"]))
if 'desc_link' in dictionary: if 'desc_link' in dictionary:
outtext = '%s|%s|%s|%s|%s|%s|%s'%(dictionary['link'],dictionary['name'].replace('|',' '),dictionary['size'],dictionary['seeds'],dictionary['leech'],dictionary['engine_url'],dictionary['desc_link']) outtext = "|".join((outtext, dictionary["desc_link"]))
else:
outtext = '%s|%s|%s|%s|%s|%s'%(dictionary['link'],dictionary['name'].replace('|',' '),dictionary['size'],dictionary['seeds'],dictionary['leech'],dictionary['engine_url'])
# fd 1 is stdout # fd 1 is stdout
with open(1, 'w', encoding='utf-8', closefd=False) as utf8stdout: with open(1, 'w', encoding='utf-8', closefd=False) as utf8stdout:
print(outtext, file=utf8stdout) print(outtext, file=utf8stdout)
def anySizeToBytes(size_string): def anySizeToBytes(size_string):
""" """
Convert a string like '1 KB' to '1024' (bytes) Convert a string like '1 KB' to '1024' (bytes)
""" """
# separate integer from unit # separate integer from unit
try: try:
size, unit = size_string.split() size, unit = size_string.split()
except: except:
try: try:
size = size_string.strip() size = size_string.strip()
unit = ''.join([c for c in size if c.isalpha()]) unit = ''.join([c for c in size if c.isalpha()])
if len(unit) > 0: if len(unit) > 0:
size = size[:-len(unit)] size = size[:-len(unit)]
except: except:
return -1 return -1
if len(size) == 0: if len(size) == 0:
return -1 return -1
size = float(size) size = float(size)
if len(unit) == 0: if len(unit) == 0:
return int(size) return int(size)
short_unit = unit.upper()[0] short_unit = unit.upper()[0]
# convert # convert
units_dict = { 'T': 40, 'G': 30, 'M': 20, 'K': 10 } units_dict = {'T': 40, 'G': 30, 'M': 20, 'K': 10}
if short_unit in units_dict: if short_unit in units_dict:
size = size * 2**units_dict[short_unit] size = size * 2**units_dict[short_unit]
return int(size) return int(size)

628
src/searchengine/nova3/socks.py
View file

@ -42,350 +42,350 @@ _defaultproxy = None
_orgsocket = socket.socket _orgsocket = socket.socket
class ProxyError(Exception): class ProxyError(Exception):
def __init__(self, value): def __init__(self, value):
self.value = value self.value = value
def __str__(self): def __str__(self):
return repr(self.value) return repr(self.value)
class GeneralProxyError(ProxyError): class GeneralProxyError(ProxyError):
def __init__(self, value): def __init__(self, value):
self.value = value self.value = value
def __str__(self): def __str__(self):
return repr(self.value) return repr(self.value)
class Socks5AuthError(ProxyError): class Socks5AuthError(ProxyError):
def __init__(self, value): def __init__(self, value):
self.value = value self.value = value
def __str__(self): def __str__(self):
return repr(self.value) return repr(self.value)
class Socks5Error(ProxyError): class Socks5Error(ProxyError):
def __init__(self, value): def __init__(self, value):
self.value = value self.value = value
def __str__(self): def __str__(self):
return repr(self.value) return repr(self.value)
class Socks4Error(ProxyError): class Socks4Error(ProxyError):
def __init__(self, value): def __init__(self, value):
self.value = value self.value = value
def __str__(self): def __str__(self):
return repr(self.value) return repr(self.value)
class HTTPError(ProxyError): class HTTPError(ProxyError):
def __init__(self, value): def __init__(self, value):
self.value = value self.value = value
def __str__(self): def __str__(self):
return repr(self.value) return repr(self.value)
_generalerrors = ("success", _generalerrors = ("success",
"invalid data", "invalid data",
"not connected", "not connected",
"not available", "not available",
"bad proxy type", "bad proxy type",
"bad input") "bad input")
_socks5errors = ("succeeded", _socks5errors = ("succeeded",
"general SOCKS server failure", "general SOCKS server failure",
"connection not allowed by ruleset", "connection not allowed by ruleset",
"Network unreachable", "Network unreachable",
"Host unreachable", "Host unreachable",
"Connection refused", "Connection refused",
"TTL expired", "TTL expired",
"Command not supported", "Command not supported",
"Address type not supported", "Address type not supported",
"Unknown error") "Unknown error")
_socks5autherrors = ("succeeded", _socks5autherrors = ("succeeded",
"authentication is required", "authentication is required",
"all offered authentication methods were rejected", "all offered authentication methods were rejected",
"unknown username or invalid password", "unknown username or invalid password",
"unknown error") "unknown error")
_socks4errors = ("request granted", _socks4errors = ("request granted",
"request rejected or failed", "request rejected or failed",
"request rejected because SOCKS server cannot connect to identd on the client", "request rejected because SOCKS server cannot connect to identd on the client",
"request rejected because the client program and identd report different user-ids", "request rejected because the client program and identd report different user-ids",
"unknown error") "unknown error")
def setdefaultproxy(proxytype=None,addr=None,port=None,rdns=True,username=None,password=None): def setdefaultproxy(proxytype=None,addr=None,port=None,rdns=True,username=None,password=None):
"""setdefaultproxy(proxytype, addr[, port[, rdns[, username[, password]]]]) """setdefaultproxy(proxytype, addr[, port[, rdns[, username[, password]]]])
Sets a default proxy which all further socksocket objects will use, Sets a default proxy which all further socksocket objects will use,
unless explicitly changed. unless explicitly changed.
""" """
global _defaultproxy global _defaultproxy
_defaultproxy = (proxytype,addr,port,rdns,username,password) _defaultproxy = (proxytype,addr,port,rdns,username,password)
class socksocket(socket.socket): class socksocket(socket.socket):
"""socksocket([family[, type[, proto]]]) -> socket object """socksocket([family[, type[, proto]]]) -> socket object
Open a SOCKS enabled socket. The parameters are the same as Open a SOCKS enabled socket. The parameters are the same as
those of the standard socket init. In order for SOCKS to work, those of the standard socket init. In order for SOCKS to work,
you must specify family=AF_INET, type=SOCK_STREAM and proto=0. 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): def __init__(self, family=socket.AF_INET, type=socket.SOCK_STREAM, proto=0, _sock=None):
_orgsocket.__init__(self,family,type,proto,_sock) _orgsocket.__init__(self,family,type,proto,_sock)
if _defaultproxy != None: if _defaultproxy != None:
self.__proxy = _defaultproxy self.__proxy = _defaultproxy
else: else:
self.__proxy = (None, None, None, None, None, None) self.__proxy = (None, None, None, None, None, None)
self.__proxysockname = None self.__proxysockname = None
self.__proxypeername = None self.__proxypeername = None
def __recvall(self, bytes): def __recvall(self, bytes):
"""__recvall(bytes) -> data """__recvall(bytes) -> data
Receive EXACTLY the number of bytes requested from the socket. Receive EXACTLY the number of bytes requested from the socket.
Blocks until the required number of bytes have been received. Blocks until the required number of bytes have been received.
""" """
data = "" data = ""
while len(data) < bytes: while len(data) < bytes:
d = self.recv(bytes-len(data)) d = self.recv(bytes-len(data))
if not d: if not d:
raise GeneralProxyError("connection closed unexpectedly") raise GeneralProxyError("connection closed unexpectedly")
data = data + d data = data + d
return data return data
def setproxy(self,proxytype=None,addr=None,port=None,rdns=True,username=None,password=None): def setproxy(self,proxytype=None,addr=None,port=None,rdns=True,username=None,password=None):
"""setproxy(proxytype, addr[, port[, rdns[, username[, password]]]]) """setproxy(proxytype, addr[, port[, rdns[, username[, password]]]])
Sets the proxy to be used. Sets the proxy to be used.
proxytype - The type of the proxy to be used. Three types proxytype - The type of the proxy to be used. Three types
are supported: PROXY_TYPE_SOCKS4 (including socks4a), are supported: PROXY_TYPE_SOCKS4 (including socks4a),
PROXY_TYPE_SOCKS5 and PROXY_TYPE_HTTP PROXY_TYPE_SOCKS5 and PROXY_TYPE_HTTP
addr - The address of the server (IP or DNS). addr - The address of the server (IP or DNS).
port - The port of the server. Defaults to 1080 for SOCKS port - The port of the server. Defaults to 1080 for SOCKS
servers and 8080 for HTTP proxy servers. servers and 8080 for HTTP proxy servers.
rdns - Should DNS queries be preformed on the remote side rdns - Should DNS queries be preformed on the remote side
(rather than the local side). The default is True. (rather than the local side). The default is True.
Note: This has no effect with SOCKS4 servers. Note: This has no effect with SOCKS4 servers.
username - Username to authenticate with to the server. username - Username to authenticate with to the server.
The default is no authentication. The default is no authentication.
password - Password to authenticate with to the server. password - Password to authenticate with to the server.
Only relevant when username is also provided. Only relevant when username is also provided.
""" """
self.__proxy = (proxytype,addr,port,rdns,username,password) self.__proxy = (proxytype,addr,port,rdns,username,password)
def __negotiatesocks5(self,destaddr,destport): def __negotiatesocks5(self,destaddr,destport):
"""__negotiatesocks5(self,destaddr,destport) """__negotiatesocks5(self,destaddr,destport)
Negotiates a connection through a SOCKS5 server. Negotiates a connection through a SOCKS5 server.
""" """
# First we'll send the authentication packages we support. # First we'll send the authentication packages we support.
if (self.__proxy[4]!=None) and (self.__proxy[5]!=None): if (self.__proxy[4]!=None) and (self.__proxy[5]!=None):
# The username/password details were supplied to the # The username/password details were supplied to the
# setproxy method so we support the USERNAME/PASSWORD # setproxy method so we support the USERNAME/PASSWORD
# authentication (in addition to the standard none). # authentication (in addition to the standard none).
self.sendall("\x05\x02\x00\x02") self.sendall("\x05\x02\x00\x02")
else: else:
# No username/password were entered, therefore we # No username/password were entered, therefore we
# only support connections with no authentication. # only support connections with no authentication.
self.sendall("\x05\x01\x00") self.sendall("\x05\x01\x00")
# We'll receive the server's response to determine which # We'll receive the server's response to determine which
# method was selected # method was selected
chosenauth = self.__recvall(2) chosenauth = self.__recvall(2)
if chosenauth[0] != "\x05": if chosenauth[0] != "\x05":
self.close() self.close()
raise GeneralProxyError((1,_generalerrors[1])) raise GeneralProxyError((1,_generalerrors[1]))
# Check the chosen authentication method # Check the chosen authentication method
if chosenauth[1] == "\x00": if chosenauth[1] == "\x00":
# No authentication is required # No authentication is required
pass pass
elif chosenauth[1] == "\x02": elif chosenauth[1] == "\x02":
# Okay, we need to perform a basic username/password # Okay, we need to perform a basic username/password
# authentication. # authentication.
self.sendall("\x01" + chr(len(self.__proxy[4])) + self.__proxy[4] + chr(len(self.__proxy[5])) + self.__proxy[5]) self.sendall("\x01" + chr(len(self.__proxy[4])) + self.__proxy[4] + chr(len(self.__proxy[5])) + self.__proxy[5])
authstat = self.__recvall(2) authstat = self.__recvall(2)
if authstat[0] != "\x01": if authstat[0] != "\x01":
# Bad response # Bad response
self.close() self.close()
raise GeneralProxyError((1,_generalerrors[1])) raise GeneralProxyError((1,_generalerrors[1]))
if authstat[1] != "\x00": if authstat[1] != "\x00":
# Authentication failed # Authentication failed
self.close() self.close()
raise Socks5AuthError((3,_socks5autherrors[3])) raise Socks5AuthError((3,_socks5autherrors[3]))
# Authentication succeeded # Authentication succeeded
else: else:
# Reaching here is always bad # Reaching here is always bad
self.close() self.close()
if chosenauth[1] == "\xFF": if chosenauth[1] == "\xFF":
raise Socks5AuthError((2,_socks5autherrors[2])) raise Socks5AuthError((2,_socks5autherrors[2]))
else: else:
raise GeneralProxyError((1,_generalerrors[1])) raise GeneralProxyError((1,_generalerrors[1]))
# Now we can request the actual connection # Now we can request the actual connection
req = "\x05\x01\x00" req = "\x05\x01\x00"
# If the given destination address is an IP address, we'll # If the given destination address is an IP address, we'll
# use the IPv4 address request even if remote resolving was specified. # use the IPv4 address request even if remote resolving was specified.
try: try:
ipaddr = socket.inet_aton(destaddr) ipaddr = socket.inet_aton(destaddr)
req = req + "\x01" + ipaddr req = req + "\x01" + ipaddr
except socket.error: except socket.error:
# Well it's not an IP number, so it's probably a DNS name. # Well it's not an IP number, so it's probably a DNS name.
if self.__proxy[3]==True: if self.__proxy[3]==True:
# Resolve remotely # Resolve remotely
ipaddr = None ipaddr = None
req = req + "\x03" + chr(len(destaddr)) + destaddr req = req + "\x03" + chr(len(destaddr)) + destaddr
else: else:
# Resolve locally # Resolve locally
ipaddr = socket.inet_aton(socket.gethostbyname(destaddr)) ipaddr = socket.inet_aton(socket.gethostbyname(destaddr))
req = req + "\x01" + ipaddr req = req + "\x01" + ipaddr
req = req + struct.pack(">H",destport) req = req + struct.pack(">H",destport)
self.sendall(req) self.sendall(req)
# Get the response # Get the response
resp = self.__recvall(4) resp = self.__recvall(4)
if resp[0] != "\x05": if resp[0] != "\x05":
self.close() self.close()
raise GeneralProxyError((1,_generalerrors[1])) raise GeneralProxyError((1,_generalerrors[1]))
elif resp[1] != "\x00": elif resp[1] != "\x00":
# Connection failed # Connection failed
self.close() self.close()
if ord(resp[1])<=8: if ord(resp[1])<=8:
raise Socks5Error((ord(resp[1]),_generalerrors[ord(resp[1])])) raise Socks5Error((ord(resp[1]),_generalerrors[ord(resp[1])]))
else: else:
raise Socks5Error((9,_generalerrors[9])) raise Socks5Error((9,_generalerrors[9]))
# Get the bound address/port # Get the bound address/port
elif resp[3] == "\x01": elif resp[3] == "\x01":
boundaddr = self.__recvall(4) boundaddr = self.__recvall(4)
elif resp[3] == "\x03": elif resp[3] == "\x03":
resp = resp + self.recv(1) resp = resp + self.recv(1)
boundaddr = self.__recvall(ord(resp[4])) boundaddr = self.__recvall(ord(resp[4]))
else: else:
self.close() self.close()
raise GeneralProxyError((1,_generalerrors[1])) raise GeneralProxyError((1,_generalerrors[1]))
boundport = struct.unpack(">H",self.__recvall(2))[0] boundport = struct.unpack(">H",self.__recvall(2))[0]
self.__proxysockname = (boundaddr,boundport) self.__proxysockname = (boundaddr,boundport)
if ipaddr != None: if ipaddr != None:
self.__proxypeername = (socket.inet_ntoa(ipaddr),destport) self.__proxypeername = (socket.inet_ntoa(ipaddr),destport)
else: else:
self.__proxypeername = (destaddr,destport) self.__proxypeername = (destaddr,destport)
def getproxysockname(self): def getproxysockname(self):
"""getsockname() -> address info """getsockname() -> address info
Returns the bound IP address and port number at the proxy. Returns the bound IP address and port number at the proxy.
""" """
return self.__proxysockname return self.__proxysockname
def getproxypeername(self): def getproxypeername(self):
"""getproxypeername() -> address info """getproxypeername() -> address info
Returns the IP and port number of the proxy. Returns the IP and port number of the proxy.
""" """
return _orgsocket.getpeername(self) return _orgsocket.getpeername(self)
def getpeername(self): def getpeername(self):
"""getpeername() -> address info """getpeername() -> address info
Returns the IP address and port number of the destination Returns the IP address and port number of the destination
machine (note: getproxypeername returns the proxy) machine (note: getproxypeername returns the proxy)
""" """
return self.__proxypeername return self.__proxypeername
def __negotiatesocks4(self,destaddr,destport): def __negotiatesocks4(self,destaddr,destport):
"""__negotiatesocks4(self,destaddr,destport) """__negotiatesocks4(self,destaddr,destport)
Negotiates a connection through a SOCKS4 server. Negotiates a connection through a SOCKS4 server.
""" """
# Check if the destination address provided is an IP address # Check if the destination address provided is an IP address
rmtrslv = False rmtrslv = False
try: try:
ipaddr = socket.inet_aton(destaddr) ipaddr = socket.inet_aton(destaddr)
except socket.error: except socket.error:
# It's a DNS name. Check where it should be resolved. # It's a DNS name. Check where it should be resolved.
if self.__proxy[3]==True: if self.__proxy[3]==True:
ipaddr = "\x00\x00\x00\x01" ipaddr = "\x00\x00\x00\x01"
rmtrslv = True rmtrslv = True
else: else:
ipaddr = socket.inet_aton(socket.gethostbyname(destaddr)) ipaddr = socket.inet_aton(socket.gethostbyname(destaddr))
# Construct the request packet # Construct the request packet
req = "\x04\x01" + struct.pack(">H",destport) + ipaddr req = "\x04\x01" + struct.pack(">H",destport) + ipaddr
# The username parameter is considered userid for SOCKS4 # The username parameter is considered userid for SOCKS4
if self.__proxy[4] != None: if self.__proxy[4] != None:
req = req + self.__proxy[4] req = req + self.__proxy[4]
req = req + "\x00" req = req + "\x00"
# DNS name if remote resolving is required # DNS name if remote resolving is required
# NOTE: This is actually an extension to the SOCKS4 protocol # NOTE: This is actually an extension to the SOCKS4 protocol
# called SOCKS4A and may not be supported in all cases. # called SOCKS4A and may not be supported in all cases.
if rmtrslv==True: if rmtrslv==True:
req = req + destaddr + "\x00" req = req + destaddr + "\x00"
self.sendall(req) self.sendall(req)
# Get the response from the server # Get the response from the server
resp = self.__recvall(8) resp = self.__recvall(8)
if resp[0] != "\x00": if resp[0] != "\x00":
# Bad data # Bad data
self.close() self.close()
raise GeneralProxyError((1,_generalerrors[1])) raise GeneralProxyError((1,_generalerrors[1]))
if resp[1] != "\x5A": if resp[1] != "\x5A":
# Server returned an error # Server returned an error
self.close() self.close()
if ord(resp[1]) in (91,92,93): if ord(resp[1]) in (91,92,93):
self.close() self.close()
raise Socks4Error((ord(resp[1]),_socks4errors[ord(resp[1])-90])) raise Socks4Error((ord(resp[1]),_socks4errors[ord(resp[1])-90]))
else: else:
raise Socks4Error((94,_socks4errors[4])) raise Socks4Error((94,_socks4errors[4]))
# Get the bound address/port # Get the bound address/port
self.__proxysockname = (socket.inet_ntoa(resp[4:]),struct.unpack(">H",resp[2:4])[0]) self.__proxysockname = (socket.inet_ntoa(resp[4:]),struct.unpack(">H",resp[2:4])[0])
if rmtrslv != None: if rmtrslv != None:
self.__proxypeername = (socket.inet_ntoa(ipaddr),destport) self.__proxypeername = (socket.inet_ntoa(ipaddr),destport)
else: else:
self.__proxypeername = (destaddr,destport) self.__proxypeername = (destaddr,destport)
def __negotiatehttp(self,destaddr,destport): def __negotiatehttp(self,destaddr,destport):
"""__negotiatehttp(self,destaddr,destport) """__negotiatehttp(self,destaddr,destport)
Negotiates a connection through an HTTP server. Negotiates a connection through an HTTP server.
""" """
# If we need to resolve locally, we do this now # If we need to resolve locally, we do this now
if self.__proxy[3] == False: if self.__proxy[3] == False:
addr = socket.gethostbyname(destaddr) addr = socket.gethostbyname(destaddr)
else: else:
addr = destaddr addr = destaddr
self.sendall("CONNECT " + addr + ":" + str(destport) + " HTTP/1.1\r\n" + "Host: " + destaddr + "\r\n\r\n") 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" # We read the response until we get the string "\r\n\r\n"
resp = self.recv(1) resp = self.recv(1)
while resp.find("\r\n\r\n")==-1: while resp.find("\r\n\r\n")==-1:
resp = resp + self.recv(1) resp = resp + self.recv(1)
# We just need the first line to check if the connection # We just need the first line to check if the connection
# was successful # was successful
statusline = resp.splitlines()[0].split(" ",2) statusline = resp.splitlines()[0].split(" ",2)
if statusline[0] not in ("HTTP/1.0","HTTP/1.1"): if statusline[0] not in ("HTTP/1.0","HTTP/1.1"):
self.close() self.close()
raise GeneralProxyError((1,_generalerrors[1])) raise GeneralProxyError((1,_generalerrors[1]))
try: try:
statuscode = int(statusline[1]) statuscode = int(statusline[1])
except ValueError: except ValueError:
self.close() self.close()
raise GeneralProxyError((1,_generalerrors[1])) raise GeneralProxyError((1,_generalerrors[1]))
if statuscode != 200: if statuscode != 200:
self.close() self.close()
raise HTTPError((statuscode,statusline[2])) raise HTTPError((statuscode,statusline[2]))
self.__proxysockname = ("0.0.0.0",0) self.__proxysockname = ("0.0.0.0",0)
self.__proxypeername = (addr,destport) self.__proxypeername = (addr,destport)
def connect(self,destpair): def connect(self,destpair):
"""connect(self,despair) """connect(self,despair)
Connects to the specified destination through a proxy. Connects to the specified destination through a proxy.
destpar - A tuple of the IP/DNS address and the port number. destpar - A tuple of the IP/DNS address and the port number.
(identical to socket's connect). (identical to socket's connect).
To select the proxy server use setproxy(). To select the proxy server use setproxy().
""" """
# Do a minimal input check first # 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): 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])) raise GeneralProxyError((5,_generalerrors[5]))
if self.__proxy[0] == PROXY_TYPE_SOCKS5: if self.__proxy[0] == PROXY_TYPE_SOCKS5:
if self.__proxy[2] != None: if self.__proxy[2] != None:
portnum = self.__proxy[2] portnum = self.__proxy[2]
else: else:
portnum = 1080 portnum = 1080
_orgsocket.connect(self,(self.__proxy[1],portnum)) _orgsocket.connect(self,(self.__proxy[1],portnum))
self.__negotiatesocks5(destpair[0],destpair[1]) self.__negotiatesocks5(destpair[0],destpair[1])
elif self.__proxy[0] == PROXY_TYPE_SOCKS4: elif self.__proxy[0] == PROXY_TYPE_SOCKS4:
if self.__proxy[2] != None: if self.__proxy[2] != None:
portnum = self.__proxy[2] portnum = self.__proxy[2]
else: else:
portnum = 1080 portnum = 1080
_orgsocket.connect(self,(self.__proxy[1],portnum)) _orgsocket.connect(self,(self.__proxy[1],portnum))
self.__negotiatesocks4(destpair[0],destpair[1]) self.__negotiatesocks4(destpair[0],destpair[1])
elif self.__proxy[0] == PROXY_TYPE_HTTP: elif self.__proxy[0] == PROXY_TYPE_HTTP:
if self.__proxy[2] != None: if self.__proxy[2] != None:
portnum = self.__proxy[2] portnum = self.__proxy[2]
else: else:
portnum = 8080 portnum = 8080
_orgsocket.connect(self,(self.__proxy[1],portnum)) _orgsocket.connect(self,(self.__proxy[1],portnum))
self.__negotiatehttp(destpair[0],destpair[1]) self.__negotiatehttp(destpair[0],destpair[1])
elif self.__proxy[0] == None: elif self.__proxy[0] == None:
_orgsocket.connect(self,(destpair[0],destpair[1])) _orgsocket.connect(self,(destpair[0],destpair[1]))
else: else:
raise GeneralProxyError((4,_generalerrors[4])) raise GeneralProxyError((4,_generalerrors[4]))