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

[piratebay] unescape title

Browse source
This commit is contained in:
Julien Veyssier 2013-03-17 18:43:22 +01:00
commit a7b42940b0
2 changed files with 6 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

2
modules/imdb/browser.py
View file

@ -219,6 +219,8 @@ dict_hex = {'á': u'á',
'À': u'À', 'À': u'À',
'â': u'â', 'â': u'â',
'É': u'É', 'É': u'É',
'ë': u'ë',
'ô': u'ô',
'ç': u'ç' 'ç': u'ç'
} }

6
modules/piratebay/pages/torrents.py
View file

@ -22,6 +22,8 @@ from weboob.tools.browser import BasePage,BrokenPageError
from weboob.capabilities.torrent import Torrent from weboob.capabilities.torrent import Torrent
from weboob.capabilities.base import NotAvailable, NotLoaded from weboob.capabilities.base import NotAvailable, NotLoaded
from html2text import unescape
__all__ = ['TorrentsPage'] __all__ = ['TorrentsPage']
@ -50,7 +52,7 @@ class TorrentsPage(BasePage):
td = tr.getchildren()[1] td = tr.getchildren()[1]
div = td.getchildren()[0] div = td.getchildren()[0]
link = div.find('a').attrib['href'] link = div.find('a').attrib['href']
title = unicode(div.find('a').text) title = unicode(unescape(div.find('a').text))
idt = link.split('/')[2] idt = link.split('/')[2]
a = td.getchildren()[1] a = td.getchildren()[1]
@ -80,7 +82,7 @@ class TorrentPage(BasePage):
magnet = NotAvailable magnet = NotAvailable
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 = unicode(div.text.strip()) title = unicode(unescape(div.text.strip()))
elif div.attrib.get('class', '') == 'download': elif div.attrib.get('class', '') == 'download':
for link in self.parser.select(div, 'a'): for link in self.parser.select(div, 'a'):
href = link.attrib.get('href', '') href = link.attrib.get('href', '')