# vim:fileencoding=UTF-8:ts=4:sw=4:sta:et:sts=4:ai
from __future__ import unicode_literals
from calibre.web.feeds.recipes import BasicNewsRecipe
import re


class aktualneRecipe(BasicNewsRecipe):
    __author__ = 'bubak'
    title = u'aktualne.cz'
    publisher = u'Centrum holdings'
    description = 'aktuálně.cz'
    oldest_article = 1
    max_articles_per_feed = 20
    encoding = 'utf-8'

    feeds = [
        (u'Domácí', u'http://aktualne.centrum.cz/feeds/rss/domaci/?photo=0'),
        (u'Zprávy', u'http://aktualne.centrum.cz/feeds/rss/zpravy/?photo=0'),
        (u'Praha', u'http://aktualne.centrum.cz/feeds/rss/domaci/regiony/praha/?photo=0'),
        (u'Ekonomika', u'http://aktualne.centrum.cz/feeds/rss/ekonomika/?photo=0'),
        (u'Finance', u'http://aktualne.centrum.cz/feeds/rss/finance/?photo=0'),
        (u'Blogy a názory', u'http://blog.aktualne.centrum.cz/export-all.php')
    ]

    language = 'cs'
    cover_url = 'http://img.aktualne.centrum.cz/design/akt4/o/l/logo-akt-ciste.png'
    remove_javascript = True
    no_stylesheets = True

    remove_attributes = []
    remove_tags_before = dict(name='h1', attrs={'class': ['titulek-clanku']})
    filter_regexps = [r'img.aktualne.centrum.cz']
    remove_tags = [dict(name='div',   attrs={'id': ['social-bookmark']}),
                   dict(name='div', attrs={'class': ['box1', 'svazane-tagy']}),
                   dict(name='div', attrs={'class': 'itemcomment id0'}),
                   dict(name='div', attrs={'class': 'hlavicka'}),
                   dict(name='div', attrs={'class': 'hlavni-menu'}),
                   dict(name='div', attrs={
                        'class': 'top-standard-brand-obal'}),
                   dict(name='div', attrs={'class': 'breadcrumb'}),
                   dict(name='div', attrs={'id': 'start-standard'}),
                   dict(name='div', attrs={'id': 'forum'}),
                   dict(name='span', attrs={'class': 'akce'}),
                   dict(name='span', attrs={'class': 'odrazka vetsi'}),
                   dict(name='div', attrs={'class': 'boxP'}),
                   dict(name='div', attrs={'class': 'box2'})]
    preprocess_regexps = [
        (re.compile(r'<div class="(contenttitle"|socialni-site|wiki|facebook-promo|facebook-like-button"|meta-akce).*',
                    re.DOTALL | re.IGNORECASE), lambda match: '</body>'),
        (re.compile(r'<div class="[^"]*poutak-clanek-trojka".*', re.DOTALL | re.IGNORECASE), lambda match: '</body>')]

    keep_only_tags = []

    visited_urls = {}

    def get_article_url(self, article):
        url = BasicNewsRecipe.get_article_url(self, article)
        if url in self.visited_urls:
            self.log.debug('Ignoring duplicate: ' + url)
            return None
        else:
            self.visited_urls[url] = True
            self.log.debug('Accepting: ' + url)
            return url