__license__   = 'GPL v3'
__copyright__ = '2008-2011, Darko Miletic <darko.miletic at gmail.com>'
'''
spiegel.de
'''

from calibre.web.feeds.news import BasicNewsRecipe

class Spiegel_int(BasicNewsRecipe):
    title                 = 'Spiegel Online International'
    __author__            = 'Darko Miletic and Sujata Raman'
    description           = "Daily news, analysis and opinion from Europe's leading newsmagazine and Germany's top news Web site"
    oldest_article        = 7
    max_articles_per_feed = 100
    language              = 'en_DE'
    no_stylesheets        = True
    use_embedded_content  = False
    encoding              = 'cp1252'
    publisher             = 'SPIEGEL ONLINE GmbH'
    category              = 'news, politics, Germany'
    masthead_url          = 'http://www.spiegel.de/static/sys/v9/spiegelonline_logo.png'
    publication_type      = 'magazine'

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

    extra_css = '''
                   #spArticleContent{font-family: Verdana,Arial,Helvetica,Geneva,sans-serif}
                   h1{color:#666666; font-weight:bold;}
                   h2{color:#990000;}
                   h3{color:#990000;}
                   h4 {color:#990000;}
                   a{color:#990000;}
                   .spAuthor{font-style:italic;}
                   #spIntroTeaser{font-weight:bold}
                   .spCredit{color:#666666; font-size:x-small;}
                   .spShortDate{font-size:x-small;}
                   .spArticleImageBox {font-size:x-small;}
                   .spPhotoGallery{font-size:x-small; color:#990000 ;}
                '''

    keep_only_tags    = [dict(attrs={'id':'spArticleContent'})]
    remove_tags_after = dict(attrs={'id':'spArticleBody'})
    remove_tags       = [dict(name=['meta','base','iframe','embed','object'])]
    remove_attributes = ['clear']
    feeds             = [(u'Spiegel Online', u'http://www.spiegel.de/international/index.rss')]

    def print_version(self, url):
        main, sep, rest = url.rpartition(',')
        rmain, rsep, rrest = main.rpartition(',')
        return rmain + ',druck-' + rrest + ',' + rest

    def preprocess_html(self, soup):
        for item in soup.findAll(style=True):
            del item['style']
        for item in soup.findAll('a'):
            if item.string is not None:
               str = item.string
               item.replaceWith(str)
            else:
               str = self.tag_to_string(item)
               item.replaceWith(str)
        return soup