calibre/recipes/nezavisne_novine.recipe

60 lines
2.8 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2013, Darko Miletic <darko.miletic at gmail.com>'
'''
www.nezavisne.com
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
class NezavisneNovine(BasicNewsRecipe):
title = 'Nezavisne novine'
__author__ = 'Darko Miletic'
description = 'Nezavisne novine - Najnovije vijesti iz BiH, Srbije, Hrvatske, Crne Gore i svijeta'
publisher = 'NIGP "DNN"'
category = 'news, politics, Bosnia, Balcans'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'sr'
remove_empty_feeds = True
publication_type = 'newspaper'
cover_url = strftime('http://pdf.nezavisne.com/slika/novina/nezavisne_novine.jpg?v=%Y%m%d')
masthead_url = 'http://www.nezavisne.com/slika/osnova/nezavisne-novine-logo.gif'
extra_css = """
body{font-family: Arial,Helvetica,sans-serif }
img{margin-bottom: 0.4em; display:block}
"""
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags = [dict(name='div', attrs={'class':'vijest'})]
remove_tags_after = dict(name='div', attrs={'id':'wrap'})
remove_tags = [
dict(name=['meta','link','iframe','object'])
,dict(name='div', attrs={'id':'wrap'})
]
remove_attributes=['lang','xmlns:fb','xmlns:og']
feeds = [
(u'Novosti' , u'http://feeds.feedburner.com/Novosti-NezavisneNovine' )
,(u'Posao' , u'http://feeds.feedburner.com/Posao-NezavisneNovine' )
,(u'Sport' , u'http://feeds.feedburner.com/Sport-NezavisneNovine' )
,(u'Komentar' , u'http://feeds.feedburner.com/Komentari-NezavisneNovine' )
,(u'Umjetnost i zabava' , u'http://feeds.feedburner.com/UmjetnostIZabava-NezavisneNovine' )
,(u'Život i stil' , u'http://feeds.feedburner.com/ZivotIStil-NezavisneNovine' )
,(u'Auto' , u'http://feeds.feedburner.com/Auto-NezavisneNovine' )
,(u'Nauka i tehnologija', u'http://feeds.feedburner.com/NaukaITehnologija-NezavisneNovine')
]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup