# vim:fileencoding=utf-8
from __future__ import unicode_literals, division, absolute_import, print_function
from calibre.web.feeds.news import BasicNewsRecipe
__license__   = 'GPL v3'
__copyright__ = '2008-2011, Kovid Goyal <kovid at kovidgoyal.net>, Darko Miletic <darko at gmail.com>'


class FazNet(BasicNewsRecipe):
    # Version 9.1
    # Update 2022-05-29
    # Armin Geller
    # new page layout

    title                 = 'FAZ.NET'
    __author__            = 'Kovid Goyal, Darko Miletic, Armin Geller'
    description           = 'Frankfurter Allgemeine Zeitung'
    publisher             = 'Frankfurter Allgemeine Zeitung GmbH'
    category              = 'news, politics, Germany'

    encoding              = 'utf-8'
    language              = 'de'

    max_articles_per_feed = 30
    no_stylesheets        = True
    remove_javascript     = True

    extra_css      =  '''
                      .atc-headlineemphasis, h1, h2 {font-size:1.6em; text-align:left}
                      .atc-HeadlineEmphasisText {font-size:0.6em; text-align:left; display:block; text-transform:uppercase;}
                      .atc-IntroText {font-size:1em; font-style:italic; font-weight:bold;margin-bottom:1em}
                      h3 {font-size:1.3em;text-align:left}
                      h4, h5, h6 {font-size:1em;text-align:left}
                      .textbox-wide {font-size:1.3em; font-style:italic}
                      .atc-ImageDescriptionText, .atc-ImageDescriptionCopyright {font-size: 0.75em; font-style:italic; font-weight:normal}
                      .atc-MetaItem {
                        font-size:0.6em; font-weight:normal; margin-bottom:0.75em; text-align:left;
                        list-style-type:none; text-transform:uppercase; display:inline-block}
                      .aut-Teaser_Avatar {font-size:0.6em; font-weight:bold; margin-bottom:0.75em; text-align:left}
                      .aut-Teaser_Name {font-size:0.6em; font-weight:bold; margin-bottom:0.75em; float:left; text-align:left}
                      .aut-Teaser_Description {font-size:0.6em; font-weight: normal; margin-bottom:0.75em; text-align:left; display:block}
                      .atc-Footer{font-size:0.6em; font-weight: normal; margin-bottom:0.75em; display:block}
                      '''

    keep_only_tags = [dict(name='article', attrs={'class':'atc'}),
                      dict(name='div', attrs={'id':'FAZContent'})
                     ]

    remove_tags_after = [dict(name='article', attrs={'class':'atc'})]

    remove_tags = [
                   dict(name='div', attrs={'class':[
                       'atc-ContainerSocialMedia',
                       'atc-ContainerFunctions_Interaction ',
                       'ctn-PlaceholderContent ctn-PlaceholderContent-is-in-article-medium',
                       'ctn-PlaceholderContent ctn-PlaceholderContent-is-in-article-medium ctn-PlaceholderContent-has-centered-content',
                       'ctn-PlaceholderBox ctn-PlaceholderBox-is-in-article-text-right',
                       'ctn-PlaceholderContent ctn-PlaceholderContent-is-in-article-text-left ctn-PlaceholderContent-is-in-article-small',
                       'aut-Follow aut-Follow-is-small-teaser',
                       'aut-Follow aut-Follow-is-teaser',
                       'js-ctn-PaywallTeasers ctn-PaywallTeasers',
                       'ctn-PaywallInfo_TeaserImageContainer',
                       'ctn-PaywallInfo_OfferContainer'
                   ]}),
                   dict(name='aside', attrs={'class':['atc-ContainerMore',
                                                     'atc-ContainerMoreOneTeaser'
                                                    ]}),
                   dict(name='span', attrs={'class':['data-button',
                                                     'o-VisuallyHidden'
                                                    ]}),
                   dict(name='a', attrs={'class':'btn-Base_Link'})
                  ]

    feeds = [
             ('FAZ.NET Aktuell', 'http://www.faz.net/aktuell/?rssview=1'),
             ('Politik', 'http://www.faz.net/aktuell/politik/?rssview=1'),
             ('Wirtschaft', 'http://www.faz.net/aktuell/wirtschaft/?rssview=1'),
             ('Feuilleton', 'http://www.faz.net/aktuell/feuilleton/?rssview=1'),
             ('Sport', 'http://www.faz.net/aktuell/sport/?rssview=1'),
             ('Lebensstil', 'http://www.faz.net/aktuell/lebensstil/?rssview=1'),
             ('Gesellschaft', 'http://www.faz.net/aktuell/gesellschaft/?rssview=1'),
             ('Finanzen', 'http://www.faz.net/aktuell/finanzen/?rssview=1'),
             ('Technik & Motor', 'http://www.faz.net/aktuell/technik-motor/?rssview=1'),
             ('Wissen', 'http://www.faz.net/aktuell/wissen/?rssview=1'),
             ('Reise', 'http://www.faz.net/aktuell/reise/?rssview=1'),
             ('Beruf & Chance', 'http://www.faz.net/aktuell/beruf-chance/?rssview=1'),
             ('Rhein-Main', 'http://www.faz.net/aktuell/rhein-main/?rssview=1')
            ]

    # For multipages:

    INDEX = ''

    def append_page(self, soup, appendtag, position):
        pager = soup.find('li',attrs={'class':'nvg-Paginator_Item nvg-Paginator_Item-to-next-page'})
        if pager:
            nexturl = self.INDEX + pager.a['href']
            soup2 = self.index_to_soup(nexturl)
            texttag = soup2.find('article', attrs={'class':'atc'})
            for cls in (
                    'atc-Header',
                    'atc-ContainerMore',
                    'atc-ContainerFunctions_Interaction',
                    'aut-Follow aut-Follow-is-small-teaser',
                    'aut-Follow aut-Follow-is-teaser'
                    ):
                div = texttag.find(attrs={'class':cls})
                if div is not None:
                    div.extract()
            newpos = len(texttag.contents)
            self.append_page(soup2,texttag,newpos)
            texttag.extract()
            pager.extract()
            appendtag.insert(position,texttag)

    # Find images

    def preprocess_html(self, soup):
        self.append_page(soup, soup.body, 3)
        for img in soup.findAll('img', attrs={'data-retina-src':True}):
            img['src'] = img['data-retina-src']
        for img in soup.findAll('img', attrs={'data-src':True}):
            img['src'] = img['data-src']
        return self.adeify_images(soup)

    # Some last cleanup

    def postprocess_html(self, soup, first_fetch):
        for div in soup.findAll('div',attrs={'class':['atc-ContainerFunctions js-som-Abbinder',
                                                      'ctn-PlaceholderContent ctn-PlaceholderContent-is-in-article-medium'
                                                     ]}):
            div.extract()
        return soup