#!/usr/bin/env  python2

__license__ = 'GPL v3'

from calibre.web.feeds.news import BasicNewsRecipe


class SATKurier(BasicNewsRecipe):
    title = u'SATKurier.pl'
    __author__ = 'Artur Stachecki <artur.stachecki@gmail.com>'
    language = 'pl'
    description = u'Serwis poświęcony telewizji cyfrowej'
    oldest_article = 7
    masthead_url = 'http://satkurier.pl/img/header_sk_logo.gif'
    max_articles_per_feed = 100
    simultaneous_downloads = 5
    remove_javascript = True
    no_stylesheets = True

    keep_only_tags = []
    keep_only_tags.append(
        dict(name='div', attrs={'id': ['single_news', 'content']}))

    remove_tags = []
    remove_tags.append(dict(attrs={'id': ['news_info', 'comments']}))
    remove_tags.append(dict(attrs={'href': '#czytaj'}))
    remove_tags.append(dict(attrs={'align': 'center'}))
    remove_tags.append(dict(attrs={'class': [
                       'date', 'category', 'right mini-add-comment', 'socialLinks', 'commentlist']}))

    remove_tags_after = [(dict(id='entry'))]

    feeds = [(u'Najnowsze wiadomości', u'http://feeds.feedburner.com/satkurierpl?format=xml'),
             (u'Sport w telewizji',
              u'http://feeds.feedburner.com/satkurier/sport?format=xml'),
             (u'Blog', u'http://feeds.feedburner.com/satkurier/blog?format=xml')]

    def preprocess_html(self, soup):
        image = soup.find(attrs={'id': 'news_mini_photo'})
        if image:
            image.extract()
            header = soup.find('h1')
            header.replaceWith(header.prettify() + image.prettify())
        for alink in soup.findAll('a'):
            if alink.string is not None:
                tstr = alink.string
                alink.replaceWith(tstr)
        return soup