# vim:fileencoding=utf-8

__license__   = 'GPL v3'
__copyright__ = '2009-2013, Darko Miletic <darko.miletic at gmail.com>'
'''
elmundo.es
'''
import time
from calibre.ptempfile import PersistentTemporaryFile
from calibre.web.feeds.news import BasicNewsRecipe

class ElMundo(BasicNewsRecipe):
    title                     = 'El Mundo'
    __author__                = 'Darko Miletic'
    description               = u'Lider de informacion en español'
    publisher                 = 'Unidad Editorial Informacion General S.L.U.'
    category                  = 'news, politics, Spain'
    oldest_article            = 2
    max_articles_per_feed     = 100
    no_stylesheets            = True
    use_embedded_content      = False
    encoding                  = 'iso8859_15'
    remove_javascript         = True
    remove_empty_feeds        = True
    language                  = 'es'
    ignore_duplicate_articles = {'url'}
    masthead_url              = 'http://estaticos03.elmundo.es/assets/desktop/master/img/iconos/elmundo-portada.png'
    publication_type          = 'newspaper'
    articles_are_obfuscated   = True
    temp_files                = []
    needs_subscription        = 'optional'
    LOGIN                     = 'https://seguro.elmundo.es/registro/login.html'
    extra_css                 = """
                                    body{font-family: Arial,Helvetica,sans-serif}
                                    .metadata_noticia{font-size: small}
                                    .pestana_GDP{font-size: small; font-weight:bold}
                                    h1 {color: #333333; font-family: Georgia,"Times New Roman",Times,serif}
                                    .hora{color: red}
                                    .update{color: gray}
                                    """

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

    remove_tags_before = dict(attrs={'class':['titular','antetitulo','entrada']})
    remove_tags_after  = dict(name='div' , attrs={'id':['desarrollo_noticia','tamano']})
    remove_tags        = [
                           dict(name='div', attrs={'class':'comentarios'}),
                           dict(name=['meta', 'link', 'iframe', 'object'])
                         ]
    remove_attributes  = ['lang','border']

    def get_browser(self):
        br = BasicNewsRecipe.get_browser(self)
        if self.username is not None and self.password is not None:
            br.open(self.LOGIN)
            br.select_form(name='login')
            br['nick' ] = self.username
            br['clave'] = self.password
            br.submit()
        return br

    feeds = [
              (u'Portada'         , u'http://elmundo.feedsportal.com/elmundo/rss/portada.xml'       )
             ,(u'Deportes'        , u'http://elmundo.feedsportal.com/elmundodeporte/rss/portada.xml')
             ,(u'Econom\xeda'     , u'http://elmundo.feedsportal.com/elmundo/rss/economia.xml'      )
             ,(u'Espa\xf1a'       , u'http://elmundo.feedsportal.com/elmundo/rss/espana.xml'        )
             ,(u'Internacional'   , u'http://elmundo.feedsportal.com/elmundo/rss/internacional.xml' )
             ,(u'Cultura'         , u'http://elmundo.feedsportal.com/elmundo/rss/internacional.xml'       )
             ,(u'Ciencia/Ecolog\xeda', u'http://elmundo.feedsportal.com/elmundo/rss/ciencia.xml'    )
             ,(u'Comunicaci\xf3n' , u'http://elmundo.feedsportal.com/elmundo/rss/comunicacion.xml'  )
             ,(u'Televisi\xf3n'   , u'http://elmundo.feedsportal.com/elmundo/rss/television.xml'    )

             ,(u'Salud'           , u'http://elmundo.feedsportal.com/elmundosalud/rss/portada.xml'  )
             ,(u'Solidaridad'     , u'http://elmundo.feedsportal.com/elmundo/rss/solidaridad.xml'   )
             ,(u'Su vivienda'     , u'http://elmundo.feedsportal.com/elmundo/rss/suvivienda.xml'    )
             ,(u'Motor'           , u'http://elmundo.feedsportal.com/elmundodeporte/rss/motor.xml'  )

             ,(u'Madrid'          , u'http://elmundo.feedsportal.com/elmundo/rss/madrid.xml'        )
             ,(u'Barcelona'       , u'http://elmundo.feedsportal.com/elmundo/rss/barcelona.xml'     )
             ,(u'Pa\xeds Vasco'   , u'http://elmundo.feedsportal.com/elmundo/rss/paisvasco.xml'     )
             ,(u'Baleares'        , u'http://elmundo.feedsportal.com/elmundo/rss/baleares.xml'      )
             ,(u'Castilla y Le\xf3n' , u'http://elmundo.feedsportal.com/elmundo/rss/castillayleon.xml' )
             ,(u'Valladolid'      , u'http://elmundo.feedsportal.com/elmundo/rss/valladolid.xml'    )
             ,(u'Valencia'        , u'http://elmundo.feedsportal.com/elmundo/rss/valencia.xml'      )
             ,(u'Alicante'        , u'http://elmundo.feedsportal.com/elmundo/rss/alicante.xml'      )
             ,(u'Castell\xf3n'    , u'http://elmundo.feedsportal.com/elmundo/rss/castellon.xml'     )
             ,(u'Andaluc\xeda'    , u'http://elmundo.feedsportal.com/elmundo/rss/andalucia.xml'     )
             ,(u'Sevilla'         , u'http://elmundo.feedsportal.com/elmundo/rss/andalucia_sevilla.xml'  )
             ,(u'M\xe1laga'       , u'http://elmundo.feedsportal.com/elmundo/rss/andalucia_malaga.xml'   )
            ]

    def get_article_url(self, article):
        realurl = article.get('guid',  None)
        if '/album/' in realurl or '/envivos/' in realurl:
            return None
        return realurl

    # Obtener la imagen de portada
    def get_cover_url(self):
       cover = self.masthead_url
       st = time.localtime()
       year = str(st.tm_year)
       month = "%.2d" % st.tm_mon
       day = "%.2d" % st.tm_mday
       cover='http://img.kiosko.net/'+ year + '/' +  month + '/' + day +'/es/elmundo.750.jpg'
       try:
           self.browser.open(cover)
       except:
           self.log("\nPortada no disponible")
       return cover

    def get_obfuscated_article(self, url):
        count = 0
        tries = 5
        html  = None
        while (count < tries):
            try:
                response = self.browser.open(url)
                html = response.read()
                count = tries
            except:
                print "Retrying download..."
            count += 1
        if html is not None:
            tfile = PersistentTemporaryFile('_fa.html')
            tfile.write(html)
            tfile.close()
            self.temp_files.append(tfile)
            return tfile.name
        return None

    def image_url_processor(self, baseurl, url):
        if url.startswith('//'):
           return 'http:' + url
        return url