simplify and factorize code, remove dead code, follow conventions, use new-style classes

This commit is contained in:
Christophe Benz 2010-12-09 15:27:06 +01:00 committed by Romain Bignon
commit f1b3264a67
28 changed files with 202 additions and 251 deletions

View file

@ -31,10 +31,6 @@ class KickassBackend(BaseBackend, ICapTorrent):
VERSION = '0.5'
DESCRIPTION = 'kickasstorrent.com bittorrent tracker'
LICENSE = 'GPLv3'
#CONFIG = ValuesDict(Value('domain', label='Domain (example "ssl.what.cd")'),
# Value('protocol', label='Protocol to use', choices=('http', 'https')),
# Value('username', label='Username'),
# Value('password', label='Password', masked=True))
BROWSER = KickassBrowser
def create_default_browser(self):

View file

@ -30,43 +30,19 @@ class KickassBrowser(BaseBrowser):
ENCODING = 'utf-8'
USER_AGENT = BaseBrowser.USER_AGENTS['wget']
PAGES = {
'http://fr.kickasstorrents.com/new/.*field=seeders&sorder=desc' : TorrentsPage,
'http://fr.kickasstorrents.com/.*.html' : TorrentPage
}
def __init__(self, *args, **kwargs):
#self.DOMAIN = domain
#self.PROTOCOL = protocol
#self.PAGES = {}
#for key, value in PiratebayBrowser.PAGES.iteritems():
# self.PAGES[key % domain] = value
BaseBrowser.__init__(self, *args, **kwargs)
#def login(self):
# if not self.is_on_page(LoginPage):
# self.home()
# self.page.login(self.username, self.password)
#def is_logged(self):
# if not self.page or self.is_on_page(LoginPage):
# return False
# if self.is_on_page(IndexPage):
# return self.page.is_logged()
# return True
'http://fr.kickasstorrents.com/new/.*field=seeders&sorder=desc': TorrentsPage,
'http://fr.kickasstorrents.com/.*.html': TorrentPage,
}
def home(self):
return self.location('http://kickasstorrents.com')
def iter_torrents(self, pattern):
#self.location(self.buildurl('/torrents.php', searchstr=pattern))
self.location('http://fr.kickasstorrents.com/new/?q=%s&field=seeders&sorder=desc' % pattern)
assert self.is_on_page(TorrentsPage)
return self.page.iter_torrents()
def get_torrent(self, id):
self.location('http://fr.kickasstorrents.com/%s.html' % id)
assert self.is_on_page(TorrentPage)
return self.page.get_torrent(id)

View file

@ -16,28 +16,18 @@
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
from weboob.tools.browser import BasePage
from weboob.capabilities.torrent import Torrent
from weboob.tools.browser import BasePage
from weboob.tools.misc import get_bytes_size
__all__ = ['TorrentsPage']
class TorrentsPage(BasePage):
def unit(self, n, u):
m = {'bytes': 1,
'KB': 1024,
'MB': 1024*1024,
'GB': 1024*1024*1024,
'TB': 1024*1024*1024*1024,
}
return float(n*m[u])
def iter_torrents(self):
for tr in self.document.getiterator('tr'):
if tr.attrib.get('class','') == 'odd' or tr.attrib.get('class','') == ' even':
if tr.attrib.get('class', '') == 'odd' or tr.attrib.get('class', '') == ' even':
title = tr.getchildren()[0].getchildren()[1].getchildren()[1].text
if not title:
title = ''
@ -46,78 +36,67 @@ class TorrentsPage(BasePage):
title += red.text
if red.tail:
title += red.tail
idt = tr.getchildren()[0].getchildren()[1].getchildren()[1].attrib.get('href','').replace('/','').replace('.html','')
url = tr.getchildren()[0].getchildren()[0].getchildren()[0].getchildren()[0].attrib.get('href','')
idt = tr.getchildren()[0].getchildren()[1].getchildren()[1].attrib.get('href', '').replace('/', '') \
.replace('.html', '')
url = tr.getchildren()[0].getchildren()[0].getchildren()[0].getchildren()[0].attrib.get('href', '')
size = tr.getchildren()[1].text
u = tr.getchildren()[1].getchildren()[0].text
size = size = size.replace(',','.')
size = size = size.replace(',', '.')
size = float(size)
seed = tr.getchildren()[4].text
leech = tr.getchildren()[5].text
torrent = Torrent(idt,
title,
url=url,
size=self.unit(size,u),
seeders=int(seed),
leechers=int(leech))
yield torrent
yield Torrent(idt,
title,
url=url,
size=get_bytes_size(size, u),
seeders=int(seed),
leechers=int(leech))
class TorrentPage(BasePage):
def unit(self, n, u):
m = {'bytes': 1,
'KB': 1024,
'MB': 1024*1024,
'GB': 1024*1024*1024,
'TB': 1024*1024*1024*1024,
}
return float(n*m[u])
def get_torrent(self, id):
seed = 0
leech = 0
description = "No description"
description = 'No description'
url = 'No Url found'
for div in self.document.getiterator('div'):
if div.attrib.get('id','') == 'desc':
if div.attrib.get('id', '') == 'desc':
description = div.text.strip()
for ch in div.getchildren():
if ch.tail != None:
description += ' '+ch.tail.strip()
if div.attrib.get('class','') == 'seedBlock':
if div.attrib.get('class', '') == 'seedBlock':
seed = int(div.getchildren()[1].text)
if div.attrib.get('class','') == 'leechBlock':
if div.attrib.get('class', '') == 'leechBlock':
leech = int(div.getchildren()[1].text)
for h in self.document.getiterator('h1'):
if h.attrib.get('class','') == 'torrentName':
if h.attrib.get('class', '') == 'torrentName':
title = h.getchildren()[0].getchildren()[0].text
for a in self.document.getiterator('a'):
if ('Download' in a.attrib.get('title','')) and ('torrent file' in a.attrib.get('title','')):
url = a.attrib.get('href','')
if ('Download' in a.attrib.get('title', '')) and ('torrent file' in a.attrib.get('title', '')):
url = a.attrib.get('href', '')
size = 0
for span in self.document.getiterator('span'):
if span.attrib.get('class','') == "folder" or span.attrib.get('class','') == "folderopen":
if span.attrib.get('class', '') == 'folder' or span.attrib.get('class', '') == 'folderopen':
size = span.getchildren()[1].tail
u = span.getchildren()[2].text
size = float(size.split(': ')[1].replace(',','.'))
size = float(size.split(': ')[1].replace(',', '.'))
files = []
for td in self.document.getiterator('td'):
if td.attrib.get('class','') == 'torFileName':
if td.attrib.get('class', '') == 'torFileName':
files.append(td.text)
torrent = Torrent(id, title)
torrent = Torrent(id, title)
torrent.url = url
torrent.size = self.unit(size,u)
torrent.size = get_bytes_size(size, u)
torrent.seeders = int(seed)
torrent.leechers = int(leech)
torrent.description = description
torrent.files = files
return torrent