from calibre.web.feeds.recipes import BasicNewsRecipe

class GryOnlinePl(BasicNewsRecipe):
    title          = u'Gry-Online.pl'
    __author__        = 'fenuks'
    description   = 'Gry-Online.pl - computer games'
    category       = 'games'
    language       = 'pl'
    oldest_article = 13
    INDEX= 'http://www.gry-online.pl/'
    masthead_url='http://www.gry-online.pl/im/gry-online-logo.png'
    cover_url='http://www.gry-online.pl/im/gry-online-logo.png'
    max_articles_per_feed = 100
    no_stylesheets= True
    keep_only_tags=[dict(name='div', attrs={'class':['gc660', 'gc660 S013']})]
    remove_tags=[dict({'class':['nav-social', 'add-info', 'smlb', 'lista lista3 lista-gry', 'S013po', 'S013-npb', 'zm_gfx_cnt_bottom', 'ocen-txt', 'wiecej-txt', 'wiecej-txt2']})]
    feeds          = [(u'Newsy', 'http://www.gry-online.pl/rss/news.xml'), ('Teksty', u'http://www.gry-online.pl/rss/teksty.xml')]


    def append_page(self, soup, appendtag):
        tag = appendtag.find('div', attrs={'class':'n5p'})
        if tag:
            nexturls=tag.findAll('a')
            url_part = soup.find('link', attrs={'rel':'canonical'})['href']
            url_part = url_part[25:].rpartition('?')[0]
            for nexturl in nexturls[1:-1]:
                soup2 = self.index_to_soup('http://www.gry-online.pl/' + url_part + nexturl['href'])
                pagetext = soup2.find(attrs={'class':'gc660'})
                for r in pagetext.findAll(name='header'):
                    r.extract()
                for r in pagetext.findAll(attrs={'itemprop':'description'}):
                    r.extract()
                pos = len(appendtag.contents)
                appendtag.insert(pos, pagetext)
            for r in appendtag.findAll(attrs={'class':['n5p', 'add-info', 'twitter-share-button', 'lista lista3 lista-gry']}):
                r.extract()


    def preprocess_html(self, soup):
         self.append_page(soup, soup.body)
         return soup