__license__ = 'GPL v3'
__copyright__ = '2012, Darko Miletic <darko.miletic at gmail.com>'
'''
www.novilist.hr
'''

import re
from calibre.web.feeds.news import BasicNewsRecipe


class NoviList_Portal_hr(BasicNewsRecipe):
    title = 'Novi List - online portal'
    __author__ = 'Darko Miletic'
    description = 'Portal Novog Lista'
    publisher = 'NOVI LIST d.d.'
    category = 'Novi list, politika, hrvatski dnevnik, Novine, Hrvatska, Croatia, News, newspaper, Hrvatski,Primorje, dnevni list, Rijeka'
    oldest_article = 2
    max_articles_per_feed = 200
    no_stylesheets = True
    encoding = 'utf8'
    use_embedded_content = False
    language = 'hr'
    publication_type = 'newsportal'
    masthead_url = 'http://www.novilist.hr/extension/novilist/design/novilist/images/logo-print.gif'
    extra_css             = """
                               @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)}
                               @font-face {font-family: "serif1";src:url(res:///opt/sony/ebook/FONT/tt0011m_.ttf)}
                               body{font-family: Geneva,Arial,Helvetica,Swiss,sans1,sans-serif }
                               h1{font-family: Georgia,serif1,serif}
                               img{display:block; margin-bottom: 0.4em; margin-top: 0.4em}
                            """

    preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')]

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

    keep_only_tags = [dict(name='div', attrs={'id': 'content'})]

    remove_tags = [
        dict(name=['meta', 'link', 'iframe', 'embed', 'object']),
        dict(name='div', attrs={
             'class': lambda x: x and 'embed-object' in x.split()})
    ]
    remove_attributes = ['border', 'lang']

    feeds = [(u'Vijesti', u'http://www.novilist.hr/rss/feed/sve.xml')]

    def get_article_url(self, article):
        url = BasicNewsRecipe.get_article_url(self, article)
        filter = ['/Foto/', '/Informator/']
        for item in filter:
            if item in url:
                return None
        return url

    def print_version(self, url):
        return url.replace('http://www.novilist.hr/', 'http://www.novilist.hr/layout/set/print/')