Fix descopera

This commit is contained in:
Kovid Goyal 2011-10-02 17:50:29 -06:00
parent 5219a61557
commit 093beec421

View File

@ -22,6 +22,10 @@ class Descopera(BasicNewsRecipe):
category = 'Ziare,Reviste,Descopera'
encoding = 'utf-8'
cover_url = 'http://www.descopera.ro/images/header_images/logo.gif'
use_embedded_content = False
no_stylesheets = True
auto_cleanup = True
conversion_options = {
'comments' : description
@ -30,28 +34,6 @@ class Descopera(BasicNewsRecipe):
,'publisher' : publisher
}
keep_only_tags = [
dict(name='h1', attrs={'style':'font-family: Arial,Helvetica,sans-serif; font-size: 18px; color: rgb(51, 51, 51); font-weight: bold; margin: 10px 0pt; clear: both; float: left;width: 610px;'})
,dict(name='div', attrs={'style':'margin-right: 15px; margin-bottom: 15px; float: left;'})
, dict(name='p', attrs={'id':'itemDescription'})
,dict(name='div', attrs={'id':'itemBody'})
]
remove_tags = [
dict(name='div', attrs={'class':['tools']})
, dict(name='div', attrs={'class':['share']})
, dict(name='div', attrs={'class':['category']})
, dict(name='div', attrs={'id':['comments']})
]
remove_tags_after = [
dict(name='div', attrs={'id':'comments'})
]
feeds = [
(u'Feeds', u'http://www.descopera.ro/rss')
]
def preprocess_html(self, soup):
return self.adeify_images(soup)