calibre/recipes/kosmonauta_pl.recipe
2013-03-28 21:47:00 +01:00

33 lines
1.4 KiB
Plaintext

# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from calibre.web.feeds.news import BasicNewsRecipe
class Kosmonauta(BasicNewsRecipe):
title = u'Kosmonauta.net'
__author__ = 'fenuks'
description = u'polskojęzyczny portal w całości dedykowany misjom kosmicznym i badaniom kosmosu.'
category = 'astronomy'
language = 'pl'
cover_url = 'http://bi.gazeta.pl/im/4/10393/z10393414X,Kosmonauta-net.jpg'
extra_css = '.thumbnail {float:left;margin-right:5px;}'
no_stylesheets = True
INDEX = 'http://www.kosmonauta.net'
oldest_article = 7
no_stylesheets = True
remove_javascript = True
remove_attributes = ['style']
max_articles_per_feed = 100
keep_only_tags = [dict(name='div', attrs={'class':'item-page'})]
remove_tags = [dict(attrs={'class':['article-tools clearfix', 'cedtag', 'nav clearfix', 'jwDisqusForm']}), dict(attrs={'alt':['Poprzednia strona', 'Następna strona']})]
remove_tags_after = dict(name='div', attrs={'class':'cedtag'})
feeds = [(u'Kosmonauta.net', u'http://www.kosmonauta.net/?format=feed&type=atom')]
def print_version(self, url):
return url + '?tmpl=component&print=1&layout=default&page='
def preprocess_html(self, soup):
for a in soup.findAll(name='a'):
if a.has_key('href'):
href = a['href']
if not href.startswith('http'):
a['href'] = self.INDEX + href
return soup