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

Fix piratebay

Browse source 
Move to .se, remove https for downloads, use the correct link for
downloads.
And some cosmetic enhancements
This commit is contained in:
Laurent Bachelier 2012-02-05 16:40:43 +01:00
commit 988542463d
4 changed files with 30 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

14
modules/piratebay/browser.py
View file

@ -30,26 +30,26 @@ __all__ = ['PiratebayBrowser']
class PiratebayBrowser(BaseBrowser): class PiratebayBrowser(BaseBrowser):
DOMAIN = 'thepiratebay.org' DOMAIN = 'thepiratebay.se'
PROTOCOL = 'https' PROTOCOL = 'https'
ENCODING = 'utf-8' ENCODING = 'utf-8'
USER_AGENT = BaseBrowser.USER_AGENTS['wget'] USER_AGENT = BaseBrowser.USER_AGENTS['wget']
PAGES = {'https://thepiratebay.org' : IndexPage, PAGES = {'https://thepiratebay.se': IndexPage,
'https://thepiratebay.org/search/.*/0/7/0' : TorrentsPage, 'https://thepiratebay.se/search/.*/0/7/0': TorrentsPage,
'https://thepiratebay.org/torrent/.*' : TorrentPage 'https://thepiratebay.se/torrent/.*': TorrentPage
} }
def home(self): def home(self):
return self.location('https://thepiratebay.org') return self.location('https://thepiratebay.se')
def iter_torrents(self, pattern): def iter_torrents(self, pattern):
self.location('https://thepiratebay.org/search/%s/0/7/0' % urllib.quote_plus(pattern.encode('utf-8'))) self.location('https://thepiratebay.se/search/%s/0/7/0' % urllib.quote_plus(pattern.encode('utf-8')))
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):
self.location('https://thepiratebay.org/torrent/%s/' % id) self.location('https://thepiratebay.se/torrent/%s/' % id)
assert self.is_on_page(TorrentPage) assert self.is_on_page(TorrentPage)
return self.page.get_torrent(id) return self.page.get_torrent(id)

1
modules/piratebay/pages/index.py
View file

@ -27,4 +27,3 @@ __all__ = ['IndexPage']
class IndexPage(BasePage): class IndexPage(BasePage):
def is_logged(self): def is_logged(self):
return 'id' in self.document.find('body').attrib return 'id' in self.document.find('body').attrib

13
modules/piratebay/pages/torrents.py
View file

@ -18,7 +18,6 @@
# along with weboob. If not, see <http://www.gnu.org/licenses/>. # along with weboob. If not, see <http://www.gnu.org/licenses/>.
from weboob.tools.browser import BasePage from weboob.tools.browser import BasePage
from weboob.capabilities.torrent import Torrent from weboob.capabilities.torrent import Torrent
@ -34,7 +33,6 @@ class TorrentsPage(BasePage):
'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 * m[u]) return float(n * m[u])
def iter_torrents(self): def iter_torrents(self):
@ -65,13 +63,18 @@ class TorrentsPage(BasePage):
leechers=int(leech)) leechers=int(leech))
yield torrent yield torrent
class TorrentPage(BasePage): class TorrentPage(BasePage):
def get_torrent(self, id): def get_torrent(self, id):
for div in self.document.getiterator('div'): for div in self.document.getiterator('div'):
if div.attrib.get('id', '') == 'title': if div.attrib.get('id', '') == 'title':
title = div.text.strip() title = div.text.strip()
elif div.attrib.get('class', '') == 'download': elif div.attrib.get('class', '') == 'download':
url = div.getchildren()[0].attrib.get('href','') # the last link is now the one with http
url = self.parser.select(div, 'a')[-1].attrib.get('href', '')
# https fails on the download server, so strip it
if url.startswith('https://'):
url = url.replace('https://', 'http://', 1)
elif div.attrib.get('id', '') == 'details': elif div.attrib.get('id', '') == 'details':
size = float(div.getchildren()[0].getchildren()[5].text.split('(')[1].split('Bytes')[0]) size = float(div.getchildren()[0].getchildren()[5].text.split('(')[1].split('Bytes')[0])
if len(div.getchildren()) > 1 \ if len(div.getchildren()) > 1 \
@ -91,11 +94,11 @@ class TorrentPage(BasePage):
elif div.attrib.get('class', '') == 'nfo': elif div.attrib.get('class', '') == 'nfo':
description = div.getchildren()[0].text description = div.getchildren()[0].text
torrent = Torrent(id, title) torrent = Torrent(id, title)
torrent.url = url torrent.url = url or None
torrent.size = size torrent.size = size
torrent.seeders = int(seed) torrent.seeders = int(seed)
torrent.leechers = int(leech) torrent.leechers = int(leech)
torrent.description = description torrent.description = description.strip()
torrent.files = ['NYI'] torrent.files = ['NYI']
return torrent return torrent