#!/usr/bin/env python

__license__ = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
www.tijd.be
'''
from calibre.ebooks.BeautifulSoup import Tag
from calibre.web.feeds.news import BasicNewsRecipe


def new_tag(soup, name, attrs=()):
    impl = getattr(soup, 'new_tag', None)
    if impl is not None:
        return impl(name, attrs=dict(attrs))
    return Tag(soup, name, attrs=attrs or None)


class DeTijd(BasicNewsRecipe):
    title = 'De Tijd'
    __author__ = 'Darko Miletic'
    description = 'News from Belgium in Dutch'
    publisher = 'De Tijd'
    category = 'news, politics, Belgium'
    oldest_article = 2
    max_articles_per_feed = 100
    no_stylesheets = True
    use_embedded_content = False
    encoding = 'utf-8'
    language = 'nl_BE'

    lang = 'nl-BE'
    direction = 'ltr'

    keep_only_tags = [
        dict(name='div', attrs={'id': 'lcol'}), dict(
            name='div', attrs={'class': 'l-main-container-article__asset-container'}
        ), dict(
            name='div',
            attrs={
                'class': 'l-main-container-article__body clearfix highlightable '
            }
        ), dict(
            name='div',
            attrs={'class': 'l-main-container-article__intro highlightable '}
        ), dict(
            name='div', attrs={'class': 'l-main-container-article__sidebar-inline'}
        ), dict(name='div', attrs={'class': 'l-main-container-article__title '})
    ]
    remove_tags = [
        dict(name=['embed', 'object']),
        dict(name='div', attrs={'id': 'art_reactwrap'})
    ]
    remove_tags_after = dict(name='div', attrs={'id': 'art_author'})

    feeds = [(u'Volledig nieuwsaanbod', u'https://www.tijd.be/rss/nieuws.xml'),
             (u'Ondernemen', u'https://www.tijd.be/rss/ondernemen.xml'),
             (u'Politiek en Economie', u'https://www.tijd.be/rss/politiek.xml'),
             (u'Markten', u'https://www.tijd.be/rss/markten_live.xml'),
             (u'Opinie', u'https://www.tijd.be/rss/opinie.xml'),
             (u'Cultuur', u'https://www.tijd.be/rss/cultuur.xml'),
             (u'Netto', u'https://www.tijd.be/rss/netto.xml'),
             (u'Sabato', u'https://www.tijd.be/rss/sabato.xml')]

    def preprocess_html(self, soup):
        del soup.body['onload']
        for item in soup.findAll(style=True):
            del item['style']
        soup.html['lang'] = self.lang
        soup.html['dir'] = self.direction
        mlang = new_tag(
            soup, 'meta', [('http-equiv', 'Content-Language'),
                           ('content', self.lang)]
        )
        mcharset = new_tag(
            soup, 'meta', [('http-equiv', 'Content-Type'),
                           ('content', 'text/html; charset=utf-8')]
        )
        soup.head.insert(0, mlang)
        soup.head.insert(1, mcharset)
        return soup