import re
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import Tag

class AdvancedUserRecipe1268409464(BasicNewsRecipe):
    title = u'The Sun'
    __author__ = 'Chaz Ralph'
    description = 'News from The Sun'
    oldest_article = 1
    max_articles_per_feed = 100
    language = 'en'
    no_stylesheets = True
    extra_css = '.headline {font-size: x-large;} \n .fact { padding-top: 10pt }'
    encoding= 'iso-8859-1'
    remove_javascript = True

    keep_only_tags = [
            dict(id='column-print')
    ]

    remove_tags = [
        dict(name='div', attrs={'class':[
            'clear text-center small padding-left-right-5 text-999 padding-top-5 padding-bottom-10 grey-solid-line',
            'clear width-625 bg-fff padding-top-10'
            ]}),
        dict(name='video'),
    ]

    def preprocess_html(self, soup):
        h1 = soup.find('h1')
        if h1 is not None:
            text = self.tag_to_string(h1)
            nh = Tag(soup, 'h1')
            nh.insert(0, text)
            h1.replaceWith(nh)

        return soup


    feeds = [(u'News', u'http://www.thesun.co.uk/sol/homepage/feeds/rss/article312900.ece')
,(u'Sport', u'http://www.thesun.co.uk/sol/homepage/feeds/rss/article247732.ece')
,(u'Football', u'http://www.thesun.co.uk/sol/homepage/feeds/rss/article247739.ece')
,(u'Gizmo', u'http://www.thesun.co.uk/sol/homepage/feeds/rss/article247829.ece')
,(u'Bizarre', u'http://www.thesun.co.uk/sol/homepage/feeds/rss/article247767.ece')]

    def print_version(self, url):
        return re.sub(r'\?OTC-RSS&ATTR=[-a-zA-Z]+', '?print=yes', url)