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

class Dobreprogramy_pl(BasicNewsRecipe):
    title = 'Dobreprogramy.pl'
    __author__  = 'fenuks'
    __licence__ ='GPL v3'
    category       = 'IT'
    masthead_url='http://static.dpcdn.pl/css/Black/Images/header_logo_napis_fullVersion.png'
    cover_url = 'http://userlogos.org/files/logos/Karmody/dobreprogramy_01.png'
    description = u'Aktualności i blogi z dobreprogramy.pl'
    encoding = 'utf-8'
    index='http://www.dobreprogramy.pl/'
    no_stylesheets = True
    language       = 'pl'
    extra_css      = '.title {font-size:22px;}'
    oldest_article = 8
    max_articles_per_feed = 100
    preprocess_regexps = [(re.compile(ur'<div id="\S+360pmp4">Twoja przeglądarka nie obsługuje Flasha i HTML5 lub wyłączono obsługę JavaScript...</div>'), lambda match: '') ]
    keep_only_tags=[dict(attrs={'class':['news', 'entry single']})]
    remove_tags = [dict(attrs={'class':['newsOptions', 'noPrint', 'komentarze', 'tags  font-heading-master']}), dict(id='komentarze')]
    #remove_tags = [dict(name='div', attrs={'class':['komentarze', 'block', 'portalInfo', 'menuBar', 'topBar']})]
    feeds = [(u'Aktualności', 'http://feeds.feedburner.com/dobreprogramy/Aktualnosci'),
                 ('Blogi', 'http://feeds.feedburner.com/dobreprogramy/BlogCzytelnikow')]


    def preprocess_html(self, soup):
        for a in soup('a'):
            if a.has_key('href') and 'http://' not in a['href'] and 'https://' not in a['href']:
                a['href']=self.index + a['href']
        return soup