nojhan/weboob-devel
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[piratebay] search

Browse source
This commit is contained in:
Julien Veyssier 2010-11-26 22:32:45 +01:00
commit 856e55d214
3 changed files with 10 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

2
weboob/backends/piratebay/backend.py
View file

@ -52,4 +52,4 @@ class PiratebayBackend(BaseBackend, ICapTorrent):
return self.browser.openurl(torrent.url.encode('utf-8')).read() return self.browser.openurl(torrent.url.encode('utf-8')).read()
def iter_torrents(self, pattern): def iter_torrents(self, pattern):
return self.browser.iter_torrents(pattern) return self.browser.iter_torrents(pattern.replace(' ','+'))

8
weboob/backends/piratebay/browser.py
View file

@ -19,7 +19,7 @@
from weboob.tools.browser import BaseBrowser from weboob.tools.browser import BaseBrowser
from .pages.index import IndexPage from .pages.index import IndexPage
from .pages.torrents import TorrentsPage from .pages.torrents import TorrentsPage, TorrentPage
__all__ = ['PiratebayBrowser'] __all__ = ['PiratebayBrowser']
@ -27,10 +27,11 @@ __all__ = ['PiratebayBrowser']
class PiratebayBrowser(BaseBrowser): class PiratebayBrowser(BaseBrowser):
PROTOCOL = 'https' PROTOCOL = 'https'
ENCODING = 'utf-8'
USER_AGENT = BaseBrowser.USER_AGENTS['wget'] USER_AGENT = BaseBrowser.USER_AGENTS['wget']
PAGES = {'https://thepiratebay.org' : IndexPage, PAGES = {'https://thepiratebay.org' : IndexPage,
'https://thepiratebay.org/search/.*/0/7/0' : TorrentsPage, 'https://thepiratebay.org/search/.*/0/7/0' : TorrentsPage,
#'https://thepiratebay.org/torrent/.*' : TorrentPage 'https://thepiratebay.org/torrent/.*' : TorrentPage
} }
def __init__(self, *args, **kwargs): def __init__(self, *args, **kwargs):
@ -59,12 +60,13 @@ class PiratebayBrowser(BaseBrowser):
def iter_torrents(self, pattern): def iter_torrents(self, pattern):
#self.location(self.buildurl('/torrents.php', searchstr=pattern)) #self.location(self.buildurl('/torrents.php', searchstr=pattern))
self.location('https://thepiratebay.org/search/%s/0/7/0' % pattern, '') self.location('https://thepiratebay.org/search/%s/0/7/0' % pattern)
assert self.is_on_page(TorrentsPage) assert self.is_on_page(TorrentsPage)
return self.page.iter_torrents() return self.page.iter_torrents()
def get_torrent(self, id): def get_torrent(self, id):
print 'goto:'+id
self.location('https://thepiratebay.org/torrent/%s/' % id) self.location('https://thepiratebay.org/torrent/%s/' % id)
assert self.is_on_page(TorrentPage) assert self.is_on_page(TorrentPage)

12
weboob/backends/piratebay/pages/torrents.py
View file

@ -29,19 +29,14 @@ __all__ = ['TorrentsPage']
class TorrentsPage(BasePage): class TorrentsPage(BasePage):
#TORRENTID_REGEXP = re.compile('torrents\.php\?action=download&id=(\d+)')
def unit(self, n, u): def unit(self, n, u):
m = {'KB': 1024, m = {'KB': 1024,
'MB': 1024*1024, 'MB': 1024*1024,
'GB': 1024*1024*1024, 'GB': 1024*1024*1024,
'TB': 1024*1024*1024*1024, 'TB': 1024*1024*1024*1024,
} }
return float(n.replace(',', '')) * m.get(u, 1) #return float(n.replace(',', '')) * m.get(u, 1)
return float(n*m[u])
#def format_url(self, url):
# return '%s://%s/%s' % (self.browser.PROTOCOL,
# self.browser.DOMAIN,
# url)
def iter_torrents(self): def iter_torrents(self):
@ -73,11 +68,12 @@ class TorrentsPage(BasePage):
torrent = Torrent(idt, torrent = Torrent(idt,
title, title,
url=url, url=url,
size=self.unit(size.replace('.',','),u), size=self.unit(float(size),u),
seeders=int(seed), seeders=int(seed),
leechers=int(leech)) leechers=int(leech))
yield torrent yield torrent
class TorrentPage(BasePage):
def get_torrent(self, id): def get_torrent(self, id):
table = self.document.getroot().cssselect('div.thin') table = self.document.getroot().cssselect('div.thin')
if not table: if not table: