# -*- mode: python -*-
# -*- coding: utf-8 -*-

__license__ = 'GPL v3'
__copyright__ = '2008-2018, Darko Miletic <darko.miletic at gmail.com>'
'''
pagina12.com.ar
'''
from calibre import strftime
from calibre.web.feeds.news import BasicNewsRecipe
from calibre.ptempfile import PersistentTemporaryFile


class Pagina12(BasicNewsRecipe):
    title                = 'Pagina - 12'
    __author__           = 'Darko Miletic'
    description          = 'Noticias de Argentina y el resto del mundo'
    publisher            = 'La Pagina S.A.'
    category             = 'news, politics, Argentina'
    oldest_article       = 2
    no_stylesheets       = True
    encoding             = 'utf8'
    use_embedded_content = False
    language             = 'es_AR'
    remove_empty_feeds   = True
    publication_type     = 'newspaper'
    auto_cleanup         = False
    delay                  = 1
    simultaneous_downloads = 1
    timeout                = 8
    ignore_duplicate_articles = {'url'}
    articles_are_obfuscated = True
    temp_files              = []
    fetch_retries           = 10
    extra_css            = """
        body{font-family: "Open Sans", sans-serif}
        .article-date{font-size: small; margin-bottom: 1em;}
        .article-title{font-size: x-large; font-weight: bold; display: block; margin-bottom: 1em; margin-top: 1em;}
        .article-main-media{display: block; margin-bottom: 1em;}
        .article-summary{margin-top:1em; margin-bottom: 1em; display:block}
        .article-author{font-family: "Archivo Narrow",Helvetica,sans-serif; color: gray; font-size: small; margin-top:1em; margin-bottom: 1em}
        img{margin-top:1em; margin-bottom: 1em; display:block}
        .article-text p:first-letter{display: inline; font-size: xx-large; font-weight: bold}
        .article-prefix{font-family: "Archivo Narrow",Helvetica,sans-serif; font-size: small; text-transform: uppercase;}
    """

    conversion_options = {
        'comment': description, 'tags': category, 'publisher': publisher, 'language': language
    }

    remove_tags = [
        dict(name=['meta', 'link']),
        dict(attrs={'class':'article-main-media-social show-for-medium'})
    ]

    keep_only_tags=[
       dict(name='div', attrs={'class':[
                                        'article-info',
                                        'article-titles',
                                        'article-main-media-header',
                                        'article-main-media',
                                        'article-text'
                                       ]})
    ]

    feeds = [
      (u'Diario de hoy'     , u'https://www.pagina12.com.ar/rss/edicion-impresa'),
      (u'El Pais'           , u'https://www.pagina12.com.ar/rss/secciones/el-pais/notas'),
      (u'Economia'          , u'https://www.pagina12.com.ar/rss/secciones/economia/notas'),
      (u'Sociedad'          , u'https://www.pagina12.com.ar/rss/secciones/sociedad/notas'),
      (u'El Mundo'          , u'https://www.pagina12.com.ar/rss/secciones/el-mundo/notas'),
      (u'Deportes'          , u'https://www.pagina12.com.ar/rss/secciones/deportes/notas'),
      (u'Cultura'           , u'https://www.pagina12.com.ar/rss/secciones/cultura/notas'),
      (u'Universidad'       , u'https://www.pagina12.com.ar/rss/secciones/universidad/notas'),
      (u'Ciencia'           , u'https://www.pagina12.com.ar/rss/secciones/ciencia/notas'),
      (u'Psicologia'        , u'https://www.pagina12.com.ar/rss/secciones/psicologia/notas'),
      (u'Ajedrez'           , u'https://www.pagina12.com.ar/rss/secciones/ajedrez/notas'),
      (u'La Ventana'        , u'https://www.pagina12.com.ar/rss/secciones/la-ventana/notas'),
      (u'Dialogos'          , u'https://www.pagina12.com.ar/rss/secciones/dialogos/notas'),
      (u'Hoy'               , u'https://www.pagina12.com.ar/rss/secciones/hoy/notas'),
      (u'Plastica'          , u'https://www.pagina12.com.ar/rss/secciones/plastica/notas'),
      (u'Cartas de Lectores', u'https://www.pagina12.com.ar/rss/secciones/cartas-de-lectores/notas'),
      (u'Espectaculos'      , u'https://www.pagina12.com.ar/rss/suplementos/cultura-y-espectaculos/notas'),
      (u'Radar'             , u'https://www.pagina12.com.ar/rss/suplementos/radar/notas'),
      (u'Radar libros'      , u'https://www.pagina12.com.ar/rss/suplementos/radar-libros/notas'),
      (u'Cash'              , u'https://www.pagina12.com.ar/rss/suplementos/cash/notas'),
      (u'Turismo'           , u'https://www.pagina12.com.ar/rss/suplementos/turismo/notas'),
      (u'Libero'            , u'https://www.pagina12.com.ar/rss/suplementos/libero/notas'),
      (u'NO'                , u'https://www.pagina12.com.ar/rss/suplementos/no/notas'),
      (u'Las 12'            , u'https://www.pagina12.com.ar/rss/suplementos/las12/notas'),
      (u'Soy'               , u'https://www.pagina12.com.ar/rss/suplementos/soy/notas'),
      (u'M2'                , u'https://www.pagina12.com.ar/rss/suplementos/m2/notas'),
      (u'Rosario 12'        , u'https://www.pagina12.com.ar/rss/suplementos/rosario12/notas')
    ]

    def get_cover_url(self):
        lurl = strftime('https://www.pagina12.com.ar/edicion-impresa/%d-%m-%Y')
        soup = self.index_to_soup(lurl)
        mydiv = soup.find('div', {'class' : lambda x: x and 'printed-edition-cover' in x.split()})
        if mydiv:
            for image in mydiv.findAll('img'):
                if image['data-src'].startswith('https://images.pagina12.com.ar/styles/width700/public/'):
                    return image['data-src']
        return None

    def get_obfuscated_article(self, url):
        result = None
        count = 0
        while (count < self.fetch_retries):
            try:
                response = self.browser.open(url, timeout=self.timeout)
                html = response.read()
                count = self.fetch_retries
                tfile = PersistentTemporaryFile('_fa.html')
                tfile.write(html)
                tfile.close()
                self.temp_files.append(tfile)
                result = tfile.name
            except:
                self.info("Retrying download...")
            count += 1
        return result