Merge pull request #4781 from DoumanAsh/python_align_search_style

[search engine] Align search engine url getting mechanism. Closes #4778
This commit is contained in:
sledgehammer999 2016-03-04 17:25:05 -06:00
commit 1cfda610cc
10 changed files with 64 additions and 132 deletions

View file

@ -1,4 +1,4 @@
#VERSION: 1.1
#VERSION: 1.2
#AUTHORS: Douman (custparasite@gmx.se)
#CONTRIBUTORS: Diego de las Heras (ngosang@hotmail.es)
@ -27,13 +27,12 @@
# POSSIBILITY OF SUCH DAMAGE.
from HTMLParser import HTMLParser
from httplib import HTTPSConnection as https
from re import compile as re_compile
from re import DOTALL
from itertools import islice
#qBt
from novaprinter import prettyPrinter
from helpers import download_file
from helpers import download_file, retrieve_url
class demonoid(object):
""" Search engine class """
@ -120,18 +119,12 @@ class demonoid(object):
def search(self, what, cat='all'):
""" Performs search """
connection = https("www.demonoid.pw")
#prepare query
cat = self.supported_categories[cat.lower()]
query = "".join(("/files/?category=", cat, "&subcategory=All&quality=All&seeded=2&external=2&query=", what, "&to=1&uid=0&sort=S"))
query = "".join((self.url, "/files/?category=", cat, "&subcategory=All&quality=All&seeded=2&external=2&query=", what, "&to=1&uid=0&sort=S"))
connection.request("GET", query)
response = connection.getresponse()
if response.status != 200:
return
data = retrieve_url(query)
data = response.read().decode("utf-8")
add_res_list = re_compile("/files.*page=[0-9]+")
torrent_list = re_compile("start torrent list -->(.*)<!-- end torrent", DOTALL)
data = torrent_list.search(data).group(0)
@ -144,10 +137,8 @@ class demonoid(object):
if list_results:
for search_query in islice((add_res_list.search(result).group(0) for result in list_results[1].split(" | ")), 0, 5):
connection.request("GET", search_query)
response = connection.getresponse()
parser.feed(torrent_list.search(response.read().decode('utf-8')).group(0))
response = retrieve_url(self.url + search_query)
parser.feed(torrent_list.search(response).group(0))
parser.close()
connection.close()
return

View file

@ -1,4 +1,4 @@
#VERSION: 2.02
#VERSION: 2.03
#AUTHORS: Christophe Dumez (chris@qbittorrent.org)
#CONTRIBUTORS: Diego de las Heras (ngosang@hotmail.es)
@ -27,10 +27,9 @@
# POSSIBILITY OF SUCH DAMAGE.
from HTMLParser import HTMLParser
from httplib import HTTPConnection as http
#qBt
from novaprinter import prettyPrinter
from helpers import download_file
from helpers import download_file, retrieve_url
class extratorrent(object):
""" Search engine class """
@ -140,25 +139,18 @@ class extratorrent(object):
def search(self, what, cat="all"):
""" Performs search """
connection = http("extratorrent.cc")
query = "".join((self.url, "/advanced_search/?with=", what, "&s_cat=", self.supported_categories[cat]))
query = "".join(("/advanced_search/?with=", what, "&s_cat=", self.supported_categories[cat]))
connection.request("GET", query)
response = connection.getresponse()
if response.status != 200:
return
response = retrieve_url(query)
list_searches = []
parser = self.MyHtmlParseWithBlackJack(list_searches, self.url)
parser.feed(response.read().decode('utf-8'))
parser.feed(response)
parser.close()
for search_query in list_searches:
connection.request("GET", search_query)
response = connection.getresponse()
parser.feed(response.read().decode('utf-8'))
response = retrieve_url(self.url + search_query)
parser.feed(response)
parser.close()
connection.close()
return

View file

@ -1,4 +1,4 @@
#VERSION: 2.00
#VERSION: 2.01
#AUTHORS: Christophe Dumez (chris@qbittorrent.org)
#CONTRIBUTORS: Diego de las Heras (ngosang@hotmail.es)
@ -27,9 +27,8 @@
# POSSIBILITY OF SUCH DAMAGE.
from HTMLParser import HTMLParser
from httplib import HTTPConnection as http
from novaprinter import prettyPrinter
from helpers import download_file
from helpers import download_file, retrieve_url
class mininova(object):
""" Search engine class """
@ -123,26 +122,19 @@ class mininova(object):
def search(self, what, cat="all"):
""" Performs search """
connection = http("www.mininova.org")
query = "/".join((self.url, "search", what, self.supported_categories[cat], "seeds"))
query = "/".join(("/search", what, self.supported_categories[cat], "seeds"))
connection.request("GET", query)
response = connection.getresponse()
if response.status != 200:
return
response = retrieve_url(query)
list_searches = []
parser = self.MyHtmlParseWithBlackJack(list_searches, self.url)
parser.feed(response.read().decode('utf-8'))
parser.feed(response)
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'))
response = retrieve_url(self.url + search_query)
parser.feed(response)
parser.close()
connection.close()
return

View file

@ -1,4 +1,4 @@
#VERSION: 2.13
#VERSION: 2.14
#AUTHORS: Fabien Devaux (fab@gnux.info)
#CONTRIBUTORS: Christophe Dumez (chris@qbittorrent.org)
# Arthur (custparasite@gmx.se)
@ -29,10 +29,9 @@
# POSSIBILITY OF SUCH DAMAGE.
from HTMLParser import HTMLParser
from httplib import HTTPSConnection as https
#qBt
from novaprinter import prettyPrinter
from helpers import download_file
from helpers import download_file, retrieve_url
class piratebay(object):
""" Search engine class """
@ -141,10 +140,8 @@ class piratebay(object):
if self.save_item == "size":
temp_data = data.split()
if "Size" in temp_data:
self.current_item[self.save_item] = temp_data[2]
elif "ULed" in temp_data:
temp_string = self.current_item[self.save_item]
self.current_item[self.save_item] = " ".join((temp_string, temp_data[0][:-1]))
indx = temp_data.index("Size")
self.current_item[self.save_item] = temp_data[indx + 1] + " " + temp_data[indx + 2]
elif self.save_item == "name":
# names with special characters like '&' are splitted in several pieces
@ -159,28 +156,21 @@ class piratebay(object):
def search(self, what, cat='all'):
""" Performs search """
connection = https("thepiratebay.se")
#prepare query. 7 is filtering by seeders
cat = cat.lower()
query = "/".join(("/search", what, "0", "7", self.supported_categories[cat]))
query = "/".join((self.url, "search", what, "0", "7", self.supported_categories[cat]))
connection.request("GET", query)
response = connection.getresponse()
if response.status != 200:
return
response = retrieve_url(query)
list_searches = []
parser = self.MyHtmlParseWithBlackJack(list_searches, self.url)
parser.feed(response.read().decode('utf-8'))
parser.feed(response)
parser.close()
parser.add_query = False
for search_query in list_searches:
connection.request("GET", search_query)
response = connection.getresponse()
parser.feed(response.read().decode('utf-8'))
response = retrieve_url(self.url + search_query)
parser.feed(response)
parser.close()
connection.close()
return

View file

@ -1,9 +1,9 @@
btdigg: 1.30
demonoid: 1.1
extratorrent: 2.02
demonoid: 1.2
extratorrent: 2.03
kickasstorrents: 1.28
legittorrents: 2.00
mininova: 2.00
piratebay: 2.13
mininova: 2.01
piratebay: 2.14
torrentreactor: 1.40
torrentz: 2.17

View file

@ -1,4 +1,4 @@
#VERSION: 1.1
#VERSION: 1.2
#AUTHORS: Douman (custparasite@gmx.se)
#CONTRIBUTORS: Diego de las Heras (ngosang@hotmail.es)
@ -27,13 +27,12 @@
# POSSIBILITY OF SUCH DAMAGE.
from html.parser import HTMLParser
from http.client import HTTPSConnection as https
from re import compile as re_compile
from re import DOTALL
from itertools import islice
#qBt
from novaprinter import prettyPrinter
from helpers import download_file
from helpers import download_file, retrieve_url
class demonoid(object):
""" Search engine class """
@ -120,18 +119,12 @@ class demonoid(object):
def search(self, what, cat='all'):
""" Performs search """
connection = https("www.demonoid.pw")
#prepare query
cat = self.supported_categories[cat.lower()]
query = "".join(("/files/?category=", cat, "&subcategory=All&quality=All&seeded=2&external=2&query=", what, "&to=1&uid=0&sort=S"))
query = "".join((self.url, "/files/?category=", cat, "&subcategory=All&quality=All&seeded=2&external=2&query=", what, "&to=1&uid=0&sort=S"))
connection.request("GET", query)
response = connection.getresponse()
if response.status != 200:
return
data = retrieve_url(query)
data = response.read().decode("utf-8")
add_res_list = re_compile("/files.*page=[0-9]+")
torrent_list = re_compile("start torrent list -->(.*)<!-- end torrent", DOTALL)
data = torrent_list.search(data).group(0)
@ -144,10 +137,8 @@ class demonoid(object):
if list_results:
for search_query in islice((add_res_list.search(result).group(0) for result in list_results[1].split(" | ")), 0, 5):
connection.request("GET", search_query)
response = connection.getresponse()
parser.feed(torrent_list.search(response.read().decode('utf-8')).group(0))
response = retrieve_url(self.url + search_query)
parser.feed(torrent_list.search(response).group(0))
parser.close()
connection.close()
return

View file

@ -1,4 +1,4 @@
#VERSION: 2.02
#VERSION: 2.03
#AUTHORS: Christophe Dumez (chris@qbittorrent.org)
#CONTRIBUTORS: Diego de las Heras (ngosang@hotmail.es)
@ -27,10 +27,9 @@
# POSSIBILITY OF SUCH DAMAGE.
from html.parser import HTMLParser
from http.client import HTTPConnection as http
#qBt
from novaprinter import prettyPrinter
from helpers import download_file
from helpers import download_file, retrieve_url
class extratorrent(object):
""" Search engine class """
@ -140,25 +139,18 @@ class extratorrent(object):
def search(self, what, cat="all"):
""" Performs search """
connection = http("extratorrent.cc")
query = "".join((self.url, "/advanced_search/?with=", what, "&s_cat=", self.supported_categories[cat]))
query = "".join(("/advanced_search/?with=", what, "&s_cat=", self.supported_categories[cat]))
connection.request("GET", query)
response = connection.getresponse()
if response.status != 200:
return
response = retrieve_url(query)
list_searches = []
parser = self.MyHtmlParseWithBlackJack(list_searches, self.url)
parser.feed(response.read().decode('utf-8'))
parser.feed(response)
parser.close()
for search_query in list_searches:
connection.request("GET", search_query)
response = connection.getresponse()
parser.feed(response.read().decode('utf-8'))
response = retrieve_url(self.url + search_query)
parser.feed(response)
parser.close()
connection.close()
return

View file

@ -1,4 +1,4 @@
#VERSION: 2.00
#VERSION: 2.01
#AUTHORS: Christophe Dumez (chris@qbittorrent.org)
#CONTRIBUTORS: Diego de las Heras (ngosang@hotmail.es)
@ -27,9 +27,8 @@
# POSSIBILITY OF SUCH DAMAGE.
from html.parser import HTMLParser
from http.client import HTTPConnection as http
from novaprinter import prettyPrinter
from helpers import download_file
from helpers import download_file, retrieve_url
class mininova(object):
""" Search engine class """
@ -123,26 +122,19 @@ class mininova(object):
def search(self, what, cat="all"):
""" Performs search """
connection = http("www.mininova.org")
query = "/".join((self.url, "search", what, self.supported_categories[cat], "seeds"))
query = "/".join(("/search", what, self.supported_categories[cat], "seeds"))
connection.request("GET", query)
response = connection.getresponse()
if response.status != 200:
return
response = retrieve_url(query)
list_searches = []
parser = self.MyHtmlParseWithBlackJack(list_searches, self.url)
parser.feed(response.read().decode('utf-8'))
parser.feed(response)
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'))
response = retrieve_url(self.url + search_query)
parser.feed(response)
parser.close()
connection.close()
return

View file

@ -1,4 +1,4 @@
#VERSION: 2.13
#VERSION: 2.14
#AUTHORS: Fabien Devaux (fab@gnux.info)
#CONTRIBUTORS: Christophe Dumez (chris@qbittorrent.org)
# Arthur (custparasite@gmx.se)
@ -29,10 +29,9 @@
# POSSIBILITY OF SUCH DAMAGE.
from html.parser import HTMLParser
from http.client import HTTPSConnection as https
#qBt
from novaprinter import prettyPrinter
from helpers import download_file
from helpers import download_file, retrieve_url
class piratebay(object):
""" Search engine class """
@ -157,28 +156,21 @@ class piratebay(object):
def search(self, what, cat='all'):
""" Performs search """
connection = https("thepiratebay.se")
#prepare query. 7 is filtering by seeders
cat = cat.lower()
query = "/".join(("/search", what, "0", "7", self.supported_categories[cat]))
query = "/".join((self.url, "search", what, "0", "7", self.supported_categories[cat]))
connection.request("GET", query)
response = connection.getresponse()
if response.status != 200:
return
response = retrieve_url(query)
list_searches = []
parser = self.MyHtmlParseWithBlackJack(list_searches, self.url)
parser.feed(response.read().decode('utf-8'))
parser.feed(response)
parser.close()
parser.add_query = False
for search_query in list_searches:
connection.request("GET", search_query)
response = connection.getresponse()
parser.feed(response.read().decode('utf-8'))
response = retrieve_url(self.url + search_query)
parser.feed(response)
parser.close()
connection.close()
return

View file

@ -1,9 +1,9 @@
btdigg: 1.30
demonoid: 1.1
extratorrent: 2.02
demonoid: 1.2
extratorrent: 2.03
kickasstorrents: 1.28
legittorrents: 2.00
mininova: 2.00
piratebay: 2.13
mininova: 2.01
piratebay: 2.14
torrentreactor: 1.40
torrentz: 2.17