calibre/recipes/e_novine.recipe

56 lines
2.0 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
'''
e-novine.com
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class E_novine(BasicNewsRecipe):
title = 'E-Novine'
__author__ = 'Darko Miletic'
description = 'News from Serbia'
publisher = 'E-novine'
category = 'news, politics, Balcans'
oldest_article = 2
max_articles_per_feed = 100
no_stylesheets = True
encoding = 'utf-8'
use_embedded_content = False
language = 'sr'
publication_type = 'newsportal'
masthead_url = 'http://www.e-novine.com/themes/e_novine/img/logo.gif'
extra_css = ' @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} .article_description,body{font-family: Arial,Helvetica,sans1,sans-serif} img{float: none; margin-bottom: 0.8em} '
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]
keep_only_tags = [
dict(name='div', attrs={'class':'article_head'})
,dict(name='div', attrs={'id':'article_body'})
]
remove_tags = [
dict(name=['object','link','embed','iframe'])
,dict(attrs={'id':'box_article_tools'})
]
remove_attributes = ['height','width','lang']
feeds = [(u'Sve vesti', u'http://www.e-novine.com/feed/index.1.rss' )]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return self.adeify_images(soup)
def print_version(self, url):
return url + '?print'