from calibre.web.feeds.news import BasicNewsRecipe
class PC_Arena(BasicNewsRecipe):
    title          = u'PCArena'
    oldest_article = 7
    max_articles_per_feed = 100
    __author__        = 'fenuks'
    description   = u'Najnowsze informacje z branży IT - testy, recenzje, aktualności, rankingi, wywiady. Twoje źródło informacji o sprzęcie komputerowym.'
    category       = 'IT'
    language       = 'pl'
    index='http://pcarena.pl'
    masthead_url='http://pcarena.pl/pcarena/img/logo.png'
    cover_url= 'http://pcarena.pl/pcarena/img/logo.png'
    no_stylesheets = True
    remove_empty_feeds=True
    #keep_only_tags=[dict(attrs={'class':['artHeader', 'art']})]
    #remove_tags=[dict(attrs={'class':'pages'})]
    feeds          = [(u'Aktualności', u'http://pcarena.pl/aktualnosci/feeds.rss'), (u'Testy', u'http://pcarena.pl/testy/feeds.rss'), (u'Software', u'http://pcarena.pl/oprogramowanie/feeds.rss'), (u'Poradniki', u'http://pcarena.pl/poradniki/feeds.rss'), (u'Mobile', u'http://pcarena.pl/mobile/feeds.rss')]
    
    def print_version(self, url):
        return url.replace('show', 'print')

    def image_url_processor(self, baseurl, url):
        if 'http' not in url:
            return 'http://pcarena.pl' + url
        else:
            return url

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