# -*- coding: utf-8 -*-

__license__   = 'GPL v3'
__copyright__ = '2011, Attis <attis@attis.one.pl>'
__version__ = 'v. 0.1'

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

class KorespondentPL(BasicNewsRecipe):
    title          = u'Korespondent.pl'
    publisher      = u'Korespondent.pl'
    description    = u'Centrum wolnorynkowe - serwis ludzi wolnych'
    encoding       = 'utf-8'
    __author__     = 'Attis'
    language       = 'pl'
    oldest_article = 15
    max_articles_per_feed = 100
    remove_javascript     = True
    no_stylesheets        = True

    keep_only_tags = [dict(name='div', attrs={'class':'publicystyka'})]
    remove_tags    = [{'name': 'meta'}, {'name':'div', 'attrs': {'class': 'zdjecie'} }]
    extra_css      = '.naglowek {font-size: small}\n .tytul {font-size: x-large; padding-bottom: 10px; padding-top: 30px} \n .external {font-size: small}'

    preprocess_regexps = [
                        (re.compile(u'<a href="index\.php.*>(.*)</a>'),
                        lambda match: match.group(1) ),
                        (re.compile(u'<i>'),
                        lambda match:'<i class="external">' ),
                        (re.compile(u'<p></p>Więcej'),
                        lambda match:'Więcej' ),
                        (re.compile(u'target="_blank"'),
                        lambda match:'target="_blank" class="external"' ),
                        (re.compile(u'<p align="center">\nPoczytaj inne teksty w <a href="http://www.korespondent.pl">Serwisie wolnorynkowym Korespondent.pl</a>.*</body>', re.DOTALL|re.IGNORECASE),
                        lambda match: '</div></body>'),
                        ]

    feeds = [(u'Serwis informacyjny', u'http://korespondent.pl/rss.xml')]