from calibre.web.feeds.news import BasicNewsRecipe


class INFRA(BasicNewsRecipe):
    title = u'INFRA'
    oldest_article = 7
    max_articles_per_feed = 100
    __author__ = 'fenuks'
    description = u'Serwis Informacyjny INFRA - UFO, Zjawiska Paranormalne, Duchy, Tajemnice świata.'
    cover_url = 'http://i.imgur.com/j7hJT.jpg'
    category = 'UFO'
    index = 'http://infra.org.pl'
    language = 'pl'
    max_articles_per_feed = 100
    remove_empty_feeds = True
    remove_attrs = ['style']
    no_stylesheets = True
    keep_only_tags = [dict(id='ja-current-content')]
    feeds = [(u'Najnowsze wiadomo\u015bci', u'http://www.infra.org.pl/rss')]

    def preprocess_html(self, soup):
        for item in soup.findAll(style=True):
            del item['style']
        for a in soup.findAll('a', href=True):
            if 'http://' not in a['href'] and 'https://' not in a['href']:
                a['href'] = self.index + a['href']
        return soup