Browse Source

[search engine] engines update

adaptive-webui-19844
DoumanAsh 10 years ago
parent
commit
d6d0f422f5
  1. 193
      src/searchengine/nova/engines/extratorrent.py
  2. 6
      src/searchengine/nova/engines/legittorrents.py
  3. 182
      src/searchengine/nova/engines/mininova.py
  4. 34
      src/searchengine/nova/engines/torrentreactor.py
  5. 9
      src/searchengine/nova/engines/versions.txt
  6. 191
      src/searchengine/nova3/engines/extratorrent.py
  7. 6
      src/searchengine/nova3/engines/legittorrents.py
  8. 180
      src/searchengine/nova3/engines/mininova.py
  9. 25
      src/searchengine/nova3/engines/torrentreactor.py
  10. 9
      src/searchengine/nova3/engines/versions.txt

193
src/searchengine/nova/engines/extratorrent.py

@ -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 +25,135 @@
# 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):
""" Search engine class """
url = 'http://extratorrent.cc' url = 'http://extratorrent.cc'
name = 'extratorrent' name = 'ExtraTorrent'
supported_categories = {'all': '', 'movies': '4', 'tv': '8', 'music': '5', 'games': '3', 'anime': '1', 'software': '7', 'books': '2', 'pictures': '6'} supported_categories = {'all' : '0',
'movies' : '4',
def __init__(self): 'tv' : '8',
self.results = [] 'music' : '5',
self.parser = self.SimpleSGMLParser(self.results, self.url) 'games' : '3',
'anime' : '1',
'software' : '7',
'books' : '2',
'pictures' : '6'}
def download_torrent(self, info): def download_torrent(self, info):
print download_file(info) """ Downloader """
print(download_file(info))
class SimpleSGMLParser(sgmllib.SGMLParser): class MyHtmlParseWithBlackJack(HTMLParser):
def __init__(self, results, url, *args): """ Parser class """
sgmllib.SGMLParser.__init__(self) def __init__(self, list_searches, url):
HTMLParser.__init__(self)
self.url = url self.url = url
self.td_counter = None self.list_searches = list_searches
self.current_item = None self.current_item = None
self.start_name = False self.cur_item_name = None
self.results = results self.pending_size = False
self.next_queries = True
def start_a(self, attr): self.pending_next_queries = False
params = dict(attr)
#print params def handle_starttag(self, tag, attrs):
if params.has_key('href') and params['href'].startswith("/torrent_download/"): if self.current_item:
self.current_item = {} if tag == "a":
self.td_counter = 0 params = dict(attrs)
self.start_name = False link = params['href']
torrent_id = '/'.join(params['href'].split('/')[2:])
self.current_item['link']=self.url+'/download/'+torrent_id if not link.startswith("/torrent"):
elif params.has_key('href') and params['href'].startswith("/torrent/") and params['href'].endswith(".html"): return
self.current_item['desc_link'] = self.url + params['href'].strip()
self.start_name = True if link[8] == "/":
#description
self.current_item["desc_link"] = "".join((self.url, link))
#remove view at the beginning
self.current_item["name"] = params["title"][5:]
self.pending_size = True
elif link[8] == "_":
#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)
self.list_searches.append(params['href'])
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): def handle_data(self, data):
if self.td_counter == 2: if self.cur_item_name:
if not self.current_item.has_key('name') and self.start_name: temp = self.current_item[self.cur_item_name]
self.current_item['name'] = data.strip() self.current_item[self.cur_item_name] = " ".join((temp, data))
elif self.td_counter == 3: #Due to utf-8 we need to handle data two times if there is space
if not self.current_item.has_key('size'): if not self.cur_item_name == "size":
self.current_item['size'] = '' self.cur_item_name = None
self.current_item['size']+= data.replace(" ", " ").strip()
elif self.td_counter == 4: def handle_endtag(self, tag):
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 == "tr":
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) prettyPrinter(self.current_item)
self.results.append('a') self.current_item = None
def search(self, what, cat='all'): def search(self, what, cat="all"):
ret = [] """ Performs search """
i = 1 connection = http("extratorrent.cc")
while True and i<11:
results = [] query = "".join(("/search/?new=1&search=", what, "&s_cat=", self.supported_categories[cat]))
parser = self.SimpleSGMLParser(results, self.url)
dat = retrieve_url(self.url+'/advanced_search/?with=%s&s_cat=%s&page=%d'%(what, self.supported_categories[cat], i)) connection.request("GET", query)
results_re = re.compile('(?s)<table class="tl"><thead>.*') response = connection.getresponse()
for match in results_re.finditer(dat): if response.status != 200:
res_tab = match.group(0) return
parser.feed(res_tab)
list_searches = []
parser = self.MyHtmlParseWithBlackJack(list_searches, self.url)
parser.feed(response.read().decode('utf-8'))
parser.close()
for search_query in list_searches:
connection.request("GET", search_query)
response = connection.getresponse()
parser.feed(response.read().decode('utf-8'))
parser.close() parser.close()
break
if len(results) <= 0:
break
i += 1
connection.close()
return

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

@ -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)

182
src/searchengine/nova/engines/mininova.py

@ -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 +26,124 @@
# 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',
def __init__(self): 'tv' : '8',
self.results = [] 'music' : '5',
self.parser = self.SimpleSGMLParser(self.results, self.url) 'games' : '3',
'anime' : '1',
'software' : '7',
'pictures' : '6',
'books' : '2'}
def download_torrent(self, info): def download_torrent(self, info):
print download_file(info) print(download_file(info))
class SimpleSGMLParser(sgmllib.SGMLParser): class MyHtmlParseWithBlackJack(HTMLParser):
def __init__(self, results, url, *args): """ Parser class """
sgmllib.SGMLParser.__init__(self) def __init__(self, list_searches, url):
HTMLParser.__init__(self)
self.list_searches = list_searches
self.url = url self.url = url
self.td_counter = None self.table_results = False
self.current_item = None self.current_item = None
self.results = results self.cur_item_name = None
self.next_queries = True
def start_a(self, attr):
params = dict(attr)
#print params
if params.has_key('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): def handle_starttag_tr(self, _):
if self.td_counter == 0: """ Handler of tr start tag """
if not self.current_item.has_key('name'): self.current_item = dict()
self.current_item['name'] = ''
self.current_item['name']+= data def handle_starttag_a(self, attrs):
elif self.td_counter == 1: """ Handler of a start tag """
if not self.current_item.has_key('size'): params = dict(attrs)
self.current_item['size'] = '' link = params["href"]
self.current_item['size']+= data.strip()
elif self.td_counter == 2: if link.startswith("/get/"):
if not self.current_item.has_key('seeds'): #download link
self.current_item['seeds'] = '' self.current_item["link"] = "".join((self.url, link))
self.current_item['seeds']+= data.strip() elif link.startswith("/tor/"):
elif self.td_counter == 3: #description
if not self.current_item.has_key('leech'): self.current_item["desc_link"] = "".join((self.url, link))
self.current_item['leech'] = '' self.cur_item_name = "name"
self.current_item['leech']+= data.strip() self.current_item["name"] = ""
elif self.next_queries and link.startswith("/search"):
def start_td(self,attr): if params["title"].startswith("Page"):
if isinstance(self.td_counter,int): self.list_searches.append(link)
self.td_counter += 1
if self.td_counter > 4: def handle_starttag_td(self, attrs):
self.td_counter = None """ Handler of td start tag """
# Display item if ("align", "right") in attrs:
if self.current_item: if not "size" in self.current_item.keys():
self.current_item['engine_url'] = self.url self.cur_item_name = "size"
if not self.current_item['seeds'].isdigit(): self.current_item["size"] = ""
self.current_item['seeds'] = 0
if not self.current_item['leech'].isdigit(): def handle_starttag_span(self, attrs):
self.current_item['leech'] = 0 """ Handler of span start tag """
if ("class", "g") in attrs:
self.cur_item_name = "seeds"
self.current_item["seeds"] = ""
elif ("class", "b") in attrs:
self.cur_item_name = "leech"
self.current_item["leech"] = ""
def handle_starttag(self, tag, attrs):
""" 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) prettyPrinter(self.current_item)
self.results.append('a') self.current_item = None
elif self.cur_item_name:
def search(self, what, cat='all'): if tag == "a" or tag == "span":
ret = [] self.cur_item_name = None
i = 1
while True and i<11: def handle_data(self, data):
results = [] """ Parser's data handler """
parser = self.SimpleSGMLParser(results, self.url) if self.cur_item_name:
dat = retrieve_url(self.url+'/search/%s/%s/seeds/%d'%(what, self.supported_categories[cat], i)) temp = self.current_item[self.cur_item_name]
results_re = re.compile('(?s)<h1>Search results for.*') self.current_item[self.cur_item_name] = " ".join((temp, data))
for match in results_re.finditer(dat):
res_tab = match.group(0) def search(self, what, cat="all"):
parser.feed(res_tab) """ 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.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() parser.close()
break
if len(results) <= 0:
break
i += 1
connection.close()
return

34
src/searchengine/nova/engines/torrentreactor.py

@ -1,4 +1,4 @@
#VERSION: 1.33 #VERSION: 1.35
#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)
@ -28,10 +28,10 @@
# 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
from urllib2 import HTTPError
from HTMLParser import HTMLParser
import urllib import urllib
from HTMLParser import HTMLParser
from httplib import HTTPConnection as http
import re import re
class torrentreactor(object): class torrentreactor(object):
@ -40,7 +40,7 @@ class torrentreactor(object):
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):
@ -68,15 +68,15 @@ class torrentreactor(object):
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()
@ -96,24 +96,26 @@ class torrentreactor(object):
self.has_results = True self.has_results = True
self.results.append('a') self.results.append('a')
def __init__(self):
self.results = []
self.parser = self.SimpleHTMLParser(self.results, self.url)
def search(self, what, cat='all'): def search(self, what, cat='all'):
i = 0 i = 0
dat = '' dat = ''
connection = http("www.torrentreactor.net")
while True and i<11: while True and i<11:
results = [] results = []
parser = self.SimpleHTMLParser(results, self.url) parser = self.SimpleHTMLParser(results, self.url)
query = '/torrents-search/%s/%d?sort=seeders.desc&type=all&period=none&categories=%s'%(what, (i*35), self.supported_categories[cat])
try: connection.request("GET", query)
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])) response = connection.getresponse()
except HTTPError: if response.status != 200:
break break
dat = response.read().decode('utf-8')
parser.feed(dat) parser.feed(dat)
parser.close() parser.close()
if len(results) <= 0: if len(results) <= 0:
break break
i += 1 i += 1
connection.close()

9
src/searchengine/nova/engines/versions.txt

@ -1,8 +1,9 @@
torrentreactor: 1.33
mininova: 1.51
piratebay: 2.11
extratorrent: 1.2 extratorrent: 1.2
torrentreactor: 1.35
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: 2.13 torrentz: 2.13
legittorrents: 1.03

191
src/searchengine/nova3/engines/extratorrent.py

@ -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 +25,135 @@
# 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):
""" Search engine class """
url = 'http://extratorrent.cc' url = 'http://extratorrent.cc'
name = 'extratorrent' name = 'ExtraTorrent'
supported_categories = {'all': '', 'movies': '4', 'tv': '8', 'music': '5', 'games': '3', 'anime': '1', 'software': '7', 'books': '2', 'pictures': '6'} supported_categories = {'all' : '0',
'movies' : '4',
def __init__(self): 'tv' : '8',
self.results = [] 'music' : '5',
self.parser = self.SimpleSGMLParser(self.results, self.url) 'games' : '3',
'anime' : '1',
'software' : '7',
'books' : '2',
'pictures' : '6'}
def download_torrent(self, info): def download_torrent(self, info):
""" Downloader """
print(download_file(info)) print(download_file(info))
class SimpleSGMLParser(sgmllib3.SGMLParser): class MyHtmlParseWithBlackJack(HTMLParser):
def __init__(self, results, url, *args): """ Parser class """
sgmllib3.SGMLParser.__init__(self) def __init__(self, list_searches, url):
HTMLParser.__init__(self)
self.url = url self.url = url
self.td_counter = None self.list_searches = list_searches
self.current_item = None self.current_item = None
self.start_name = False self.cur_item_name = None
self.results = results self.pending_size = False
self.next_queries = True
def start_a(self, attr): self.pending_next_queries = False
params = dict(attr)
#print params def handle_starttag(self, tag, attrs):
if 'href' in params and params['href'].startswith("/torrent_download/"): if self.current_item:
self.current_item = {} if tag == "a":
self.td_counter = 0 params = dict(attrs)
self.start_name = False link = params['href']
torrent_id = '/'.join(params['href'].split('/')[2:])
self.current_item['link']=self.url+'/download/'+torrent_id if not link.startswith("/torrent"):
elif 'href' in params and params['href'].startswith("/torrent/") and params['href'].endswith(".html"): return
self.current_item['desc_link'] = self.url + params['href'].strip()
self.start_name = True if link[8] == "/":
#description
self.current_item["desc_link"] = "".join((self.url, link))
#remove view at the beginning
self.current_item["name"] = params["title"][5:]
self.pending_size = True
elif link[8] == "_":
#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)
self.list_searches.append(params['href'])
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): def handle_data(self, data):
if self.td_counter == 2: if self.cur_item_name:
if 'name' not in self.current_item and self.start_name: temp = self.current_item[self.cur_item_name]
self.current_item['name'] = data.strip() self.current_item[self.cur_item_name] = " ".join((temp, data))
elif self.td_counter == 3: #Due to utf-8 we need to handle data two times if there is space
if 'size' not in self.current_item: if not self.cur_item_name == "size":
self.current_item['size'] = '' self.cur_item_name = None
self.current_item['size']+= data.replace("&nbsp;", " ").strip()
elif self.td_counter == 4: def handle_endtag(self, tag):
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 == "tr":
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) prettyPrinter(self.current_item)
self.results.append('a') self.current_item = None
def search(self, what, cat='all'): def search(self, what, cat="all"):
ret = [] """ Performs search """
i = 1 connection = http("extratorrent.cc")
while True and i<11:
results = [] query = "".join(("/search/?new=1&search=", what, "&s_cat=", self.supported_categories[cat]))
parser = self.SimpleSGMLParser(results, self.url)
dat = retrieve_url(self.url+'/advanced_search/?with=%s&s_cat=%s&page=%d'%(what, self.supported_categories[cat], i)) connection.request("GET", query)
results_re = re.compile('(?s)<table class="tl"><thead>.*') response = connection.getresponse()
for match in results_re.finditer(dat): if response.status != 200:
res_tab = match.group(0) return
parser.feed(res_tab)
list_searches = []
parser = self.MyHtmlParseWithBlackJack(list_searches, self.url)
parser.feed(response.read().decode('utf-8'))
parser.close()
for search_query in list_searches:
connection.request("GET", search_query)
response = connection.getresponse()
parser.feed(response.read().decode('utf-8'))
parser.close() parser.close()
break
if len(results) <= 0:
break
i += 1
connection.close()
return

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

@ -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))

180
src/searchengine/nova3/engines/mininova.py

@ -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 +26,124 @@
# 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',
def __init__(self): 'tv' : '8',
self.results = [] 'music' : '5',
self.parser = self.SimpleSGMLParser(self.results, self.url) 'games' : '3',
'anime' : '1',
'software' : '7',
'pictures' : '6',
'books' : '2'}
def download_torrent(self, info): def download_torrent(self, info):
print(download_file(info)) print(download_file(info))
class SimpleSGMLParser(sgmllib3.SGMLParser): class MyHtmlParseWithBlackJack(HTMLParser):
def __init__(self, results, url, *args): """ Parser class """
sgmllib3.SGMLParser.__init__(self) def __init__(self, list_searches, url):
HTMLParser.__init__(self)
self.list_searches = list_searches
self.url = url self.url = url
self.td_counter = None self.table_results = False
self.current_item = None self.current_item = None
self.results = results self.cur_item_name = None
self.next_queries = True
def start_a(self, attr):
params = dict(attr)
#print params
if 'href' in params:
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): def handle_starttag_tr(self, _):
if self.td_counter == 0: """ Handler of tr start tag """
if 'name' not in self.current_item: self.current_item = dict()
self.current_item['name'] = ''
self.current_item['name']+= data def handle_starttag_a(self, attrs):
elif self.td_counter == 1: """ Handler of a start tag """
if 'size' not in self.current_item: params = dict(attrs)
self.current_item['size'] = '' link = params["href"]
self.current_item['size']+= data.strip()
elif self.td_counter == 2: if link.startswith("/get/"):
if 'seeds' not in self.current_item: #download link
self.current_item['seeds'] = '' self.current_item["link"] = "".join((self.url, link))
self.current_item['seeds']+= data.strip() elif link.startswith("/tor/"):
elif self.td_counter == 3: #description
if 'leech' not in self.current_item: self.current_item["desc_link"] = "".join((self.url, link))
self.current_item['leech'] = '' self.cur_item_name = "name"
self.current_item['leech']+= data.strip() self.current_item["name"] = ""
elif self.next_queries and link.startswith("/search"):
def start_td(self,attr): if params["title"].startswith("Page"):
if isinstance(self.td_counter,int): self.list_searches.append(link)
self.td_counter += 1
if self.td_counter > 4: def handle_starttag_td(self, attrs):
self.td_counter = None """ Handler of td start tag """
# Display item if ("align", "right") in attrs:
if self.current_item: if not "size" in self.current_item.keys():
self.current_item['engine_url'] = self.url self.cur_item_name = "size"
if not self.current_item['seeds'].isdigit(): self.current_item["size"] = ""
self.current_item['seeds'] = 0
if not self.current_item['leech'].isdigit(): def handle_starttag_span(self, attrs):
self.current_item['leech'] = 0 """ Handler of span start tag """
if ("class", "g") in attrs:
self.cur_item_name = "seeds"
self.current_item["seeds"] = ""
elif ("class", "b") in attrs:
self.cur_item_name = "leech"
self.current_item["leech"] = ""
def handle_starttag(self, tag, attrs):
""" 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) prettyPrinter(self.current_item)
self.results.append('a') self.current_item = None
elif self.cur_item_name:
def search(self, what, cat='all'): if tag == "a" or tag == "span":
ret = [] self.cur_item_name = None
i = 1
while True and i<11: def handle_data(self, data):
results = [] """ Parser's data handler """
parser = self.SimpleSGMLParser(results, self.url) if self.cur_item_name:
dat = retrieve_url(self.url+'/search/%s/%s/seeds/%d'%(what, self.supported_categories[cat], i)) temp = self.current_item[self.cur_item_name]
results_re = re.compile('(?s)<h1>Search results for.*') self.current_item[self.cur_item_name] = " ".join((temp, data))
for match in results_re.finditer(dat):
res_tab = match.group(0) def search(self, what, cat="all"):
parser.feed(res_tab) """ 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.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() parser.close()
break
if len(results) <= 0:
break
i += 1
connection.close()
return

25
src/searchengine/nova3/engines/torrentreactor.py

@ -1,4 +1,4 @@
#VERSION: 1.33 #VERSION: 1.35
#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)
@ -28,9 +28,10 @@
# 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
from urllib import error, parse from urllib import parse
from html.parser import HTMLParser from html.parser import HTMLParser
from http.client import HTTPConnection as http
import re import re
class torrentreactor(object): class torrentreactor(object):
@ -95,24 +96,26 @@ class torrentreactor(object):
self.has_results = True self.has_results = True
self.results.append('a') self.results.append('a')
def __init__(self):
self.results = []
self.parser = self.SimpleHTMLParser(self.results, self.url)
def search(self, what, cat='all'): def search(self, what, cat='all'):
i = 0 i = 0
dat = '' dat = ''
connection = http("www.torrentreactor.net")
while True and i<11: while True and i<11:
results = [] results = []
parser = self.SimpleHTMLParser(results, self.url) parser = self.SimpleHTMLParser(results, self.url)
query = '/torrents-search/%s/%d?sort=seeders.desc&type=all&period=none&categories=%s'%(what, (i*35), self.supported_categories[cat])
try: connection.request("GET", query)
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])) response = connection.getresponse()
except error.HTTPError: if response.status != 200:
break break
dat = response.read().decode('utf-8')
parser.feed(dat) parser.feed(dat)
parser.close() parser.close()
if len(results) <= 0: if len(results) <= 0:
break break
i += 1 i += 1
connection.close()

9
src/searchengine/nova3/engines/versions.txt

@ -1,8 +1,9 @@
torrentreactor: 1.33
mininova: 1.51
piratebay: 2.11
extratorrent: 1.2 extratorrent: 1.2
torrentreactor: 1.35
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: 2.13 torrentz: 2.13
legittorrents: 1.04

Loading…
Cancel
Save