d4708
/
qBittorrent
mirror of https://github.com/d47081/qBittorrent.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
Browse Source

[search engine] Update Legit Torrent to remove sgmllib

adaptive-webui-19844
DoumanAsh 10 years ago
parent
f3dd93a42c
commit
033817f70b
4 changed files with 126 additions and 134 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Unified View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 128
      src/searchengine/nova/engines/legittorrents.py
  2. 2
      src/searchengine/nova/engines/versions.txt
  3. 128
      src/searchengine/nova3/engines/legittorrents.py
  4. 2
      src/searchengine/nova3/engines/versions.txt

128
src/searchengine/nova/engines/legittorrents.py
Unescape View File

@ -1,5 +1,6 @@
#VERSION: 1.05 #VERSION: 2.00
#AUTHORS: Christophe Dumez (chris@qbittorrent.org) #AUTHORS: Christophe Dumez (chris@qbittorrent.org)
# Douman (custparasite@gmx.se)
# Redistribution and use in source and binary forms, with or without # Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met: # modification, are permitted provided that the following conditions are met:
@ -28,78 +29,73 @@
from novaprinter import prettyPrinter from novaprinter import prettyPrinter
from helpers import retrieve_url, download_file from helpers import retrieve_url, download_file
import sgmllib from HTMLParser import HTMLParser
import re from re import compile as re_compile
class legittorrents(object): class legittorrents(object):
url = 'http://www.legittorrents.info' url = 'http://www.legittorrents.info'
name = 'Legit Torrents' name = 'Legit Torrents'
supported_categories = {'all': '', 'movies': '1', 'tv': '13', 'music': '2', 'games': '3', 'anime': '5', 'books': '6'} supported_categories = {'all': '0', 'movies': '1', 'tv': '13', 'music': '2', 'games': '3', 'anime': '5', 'books': '6'}
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, url):
self.url = url HTMLParser.__init__(self)
self.td_counter = None self.url = url
self.current_item = None self.current_item = None
self.start_name = False self.save_item_key = None
self.results = results
def start_a(self, attr): def handle_starttag(self, tag, attrs):
params = dict(attr) """ Parser's start tag handler """
if params.has_key('href') and params['href'].startswith('download.php?'): if self.current_item:
self.current_item['link'] = self.url + '/' + params['href'].strip() params = dict(attrs)
elif params.has_key('href') and params['href'].startswith('index.php?page=torrent-details'): if tag == "a":
self.current_item = {} link = params["href"]
self.td_counter = 0 if link.startswith("index") and "title" in params:
self.current_item['desc_link'] = self.url + '/' + params['href'].strip() #description link
self.current_item["name"] = params["title"][14:]
self.current_item["desc_link"] = "/".join((self.url, link))
elif link.startswith("download"):
self.current_item["link"] = "/".join((self.url, link))
elif tag == "td":
if "class" in params and params["class"].startswith("#FF"):
self.save_item_key = "leech" if "seeds" in self.current_item else "seeds"
def handle_data(self, data): elif tag == "tr":
if self.td_counter == 0: self.current_item = {}
if not self.current_item.has_key('name'): self.current_item["size"] = ""
self.current_item['name'] = data.strip() self.current_item["engine_url"] = self.url
elif self.td_counter == 3:
if not self.current_item.has_key('seeds'):
self.current_item['seeds'] = ''
self.current_item['seeds']+= data.strip()
elif self.td_counter == 4:
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_endtag(self, tag):
if isinstance(self.td_counter,int): """ Parser's end tag handler """
self.td_counter += 1 if self.current_item and tag == "tr":
if self.td_counter > 5: if len(self.current_item) > 4:
self.td_counter = None prettyPrinter(self.current_item)
# Display item self.current_item = None
if self.current_item:
self.current_item['engine_url'] = self.url def handle_data(self, data):
if not self.current_item['seeds'].isdigit(): """ Parser's data handler """
self.current_item['seeds'] = 0 if self.save_item_key:
if not self.current_item['leech'].isdigit(): self.current_item[self.save_item_key] = data.strip()
self.current_item['leech'] = 0 self.save_item_key = None
self.current_item['size'] = ''
prettyPrinter(self.current_item) def search(self, what, cat='all'):
self.results.append('a') """ Performs search """
query = "".join((self.url, "/index.php?page=torrents&search=", what, "&category=", self.supported_categories.get(cat, '0'), "&active=1"))
get_table = re_compile('(?s)<table\sclass="lista".*>(.*)</table>')
data = get_table.search(retrieve_url(query)).group(0)
#extract first ten pages of next results
next_pages = re_compile('(?m)<option value="(.*)">[0-9]+</option>')
next_pages = ["".join((self.url, page)) for page in next_pages.findall(data)[:10]]
def search(self, what, cat='all'): parser = self.MyHtmlParseWithBlackJack(self.url)
ret = [] parser.feed(data)
i = 1
while True and i<11:
results = []
parser = self.SimpleSGMLParser(results, self.url)
dat = retrieve_url(self.url+'/index.php?page=torrents&search=%s&category=%s&active=1&order=3&by=2&pages=%d'%(what, self.supported_categories[cat], i))
results_re = re.compile('(?s)<table width="100%" class="lista">.*')
for match in results_re.finditer(dat):
res_tab = match.group(0)
parser.feed(res_tab)
parser.close() parser.close()
break
if len(results) <= 0:
break
i += 1
for page in next_pages:
parser.feed(get_table.search(retrieve_url(page)).group(0))
parser.close()

2
src/searchengine/nova/engines/versions.txt
Unescape View File

@ -2,7 +2,7 @@ btdigg: 1.25
demonoid: 1.1 demonoid: 1.1
extratorrent: 2.0 extratorrent: 2.0
kickasstorrents: 1.27 kickasstorrents: 1.27
legittorrents: 1.05 legittorrents: 2.00
mininova: 2.00 mininova: 2.00
piratebay: 2.11 piratebay: 2.11
torrentreactor: 1.36 torrentreactor: 1.36

128
src/searchengine/nova3/engines/legittorrents.py
Unescape View File

@ -1,5 +1,6 @@
#VERSION: 1.05 #VERSION: 2.00
#AUTHORS: Christophe Dumez (chris@qbittorrent.org) #AUTHORS: Christophe Dumez (chris@qbittorrent.org)
# Douman (custparasite@gmx.se)
# Redistribution and use in source and binary forms, with or without # Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met: # modification, are permitted provided that the following conditions are met:
@ -28,78 +29,73 @@
from novaprinter import prettyPrinter from novaprinter import prettyPrinter
from helpers import retrieve_url, download_file from helpers import retrieve_url, download_file
import sgmllib3 as sgmllib from html.parser import HTMLParser
import re from re import compile as re_compile
class legittorrents(object): class legittorrents(object):
url = 'http://www.legittorrents.info' url = 'http://www.legittorrents.info'
name = 'Legit Torrents' name = 'Legit Torrents'
supported_categories = {'all': '', 'movies': '1', 'tv': '13', 'music': '2', 'games': '3', 'anime': '5', 'books': '6'} supported_categories = {'all': '0', 'movies': '1', 'tv': '13', 'music': '2', 'games': '3', 'anime': '5', 'books': '6'}
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, url):
self.url = url HTMLParser.__init__(self)
self.td_counter = None self.url = url
self.current_item = None self.current_item = None
self.start_name = False self.save_item_key = None
self.results = results
def start_a(self, attr): def handle_starttag(self, tag, attrs):
params = dict(attr) """ Parser's start tag handler """
if 'href' in params and params['href'].startswith('download.php?'): if self.current_item:
self.current_item['link'] = self.url + '/' + params['href'].strip() params = dict(attrs)
elif 'href' in params and params['href'].startswith('index.php?page=torrent-details'): if tag == "a":
self.current_item = {} link = params["href"]
self.td_counter = 0 if link.startswith("index") and "title" in params:
self.current_item['desc_link'] = self.url + '/' + params['href'].strip() #description link
self.current_item["name"] = params["title"][14:]
self.current_item["desc_link"] = "/".join((self.url, link))
elif link.startswith("download"):
self.current_item["link"] = "/".join((self.url, link))
elif tag == "td":
if "class" in params and params["class"].startswith("#FF"):
self.save_item_key = "leech" if "seeds" in self.current_item else "seeds"
def handle_data(self, data): elif tag == "tr":
if self.td_counter == 0: self.current_item = {}
if 'name' not in self.current_item: self.current_item["size"] = ""
self.current_item['name'] = data.strip() self.current_item["engine_url"] = self.url
elif self.td_counter == 3:
if 'seeds' not in self.current_item:
self.current_item['seeds'] = ''
self.current_item['seeds']+= data.strip()
elif self.td_counter == 4:
if 'leech' not in self.current_item:
self.current_item['leech'] = ''
self.current_item['leech']+= data.strip()
def start_td(self,attr): def handle_endtag(self, tag):
if isinstance(self.td_counter,int): """ Parser's end tag handler """
self.td_counter += 1 if self.current_item and tag == "tr":
if self.td_counter > 5: if len(self.current_item) > 4:
self.td_counter = None prettyPrinter(self.current_item)
# Display item self.current_item = None
if self.current_item:
self.current_item['engine_url'] = self.url def handle_data(self, data):
if not self.current_item['seeds'].isdigit(): """ Parser's data handler """
self.current_item['seeds'] = 0 if self.save_item_key:
if not self.current_item['leech'].isdigit(): self.current_item[self.save_item_key] = data.strip()
self.current_item['leech'] = 0 self.save_item_key = None
self.current_item['size'] = ''
prettyPrinter(self.current_item) def search(self, what, cat='all'):
self.results.append('a') """ Performs search """
query = "".join((self.url, "/index.php?page=torrents&search=", what, "&category=", self.supported_categories.get(cat, '0'), "&active=1"))
get_table = re_compile('(?s)<table\sclass="lista".*>(.*)</table>')
data = get_table.search(retrieve_url(query)).group(0)
#extract first ten pages of next results
next_pages = re_compile('(?m)<option value="(.*)">[0-9]+</option>')
next_pages = ["".join((self.url, page)) for page in next_pages.findall(data)[:10]]
def search(self, what, cat='all'): parser = self.MyHtmlParseWithBlackJack(self.url)
ret = [] parser.feed(data)
i = 1
while True and i<11:
results = []
parser = self.SimpleSGMLParser(results, self.url)
dat = retrieve_url(self.url+'/index.php?page=torrents&search=%s&category=%s&active=1&order=3&by=2&pages=%d'%(what, self.supported_categories[cat], i))
results_re = re.compile('(?s)<table width="100%" class="lista">.*')
for match in results_re.finditer(dat):
res_tab = match.group(0)
parser.feed(res_tab)
parser.close() parser.close()
break
if len(results) <= 0:
break
i += 1
for page in next_pages:
parser.feed(get_table.search(retrieve_url(page)).group(0))
parser.close()

2
src/searchengine/nova3/engines/versions.txt
Unescape View File

@ -2,7 +2,7 @@ btdigg: 1.25
demonoid: 1.1 demonoid: 1.1
extratorrent: 2.0 extratorrent: 2.0
kickasstorrents: 1.27 kickasstorrents: 1.27
legittorrents: 1.05 legittorrents: 2.00
mininova: 2.00 mininova: 2.00
piratebay: 2.11 piratebay: 2.11
torrentreactor: 1.36 torrentreactor: 1.36

Write Preview
Loading…
Cancel
Save