#!/usr/bin/env  python

__license__   = 'GPL v3'
__copyright__ = u'2010, Tomasz Dlugosz <tomek3d@gmail.com>'
'''
frazpc.pl
'''

from calibre.web.feeds.news import BasicNewsRecipe
import re
class FrazPC(BasicNewsRecipe):
    title          = u'frazpc.pl'
    publisher      = u'frazpc.pl'
    description    = u'Tw\xf3j Vortal Technologiczny'
    language = 'pl'
    __author__ = u'Tomasz D\u0142ugosz'
    oldest_article = 7
    max_articles_per_feed = 100
    use_embedded_content = False
    no_stylesheets = True

    feeds          = [(u'Aktualno\u015bci', u'http://www.frazpc.pl/feed'), (u'Recenzje', u'http://www.frazpc.pl/kat/recenzje-2/feed') ]

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

    remove_tags = [dict(name='p', attrs={'class':'gray tagsP fs11'})]

    preprocess_regexps = [
        (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in
            [(r'<div id="post-[0-9]*"', lambda match: '<div id="FRAZ_CONTENT"'),
             (r'href="/f/news/', lambda match: 'href="http://www.frazpc.pl/f/news/'),
             (r' &nbsp; <a href="http://www.frazpc.pl/[^>]*?">(Skomentuj|Komentarz(e)?\([0-9]*\))</a>&nbsp; \|', lambda match: '')]
    ]

    remove_attributes = [ 'width', 'height' ]