__license__ = 'GPL v3' __copyright__ = '2010, Darko Miletic ' ''' sarajevo-x.com ''' import re from calibre.web.feeds.recipes import BasicNewsRecipe from calibre.ebooks.BeautifulSoup import Tag, NavigableString def new_tag(soup, name, attrs=()): impl = getattr(soup, 'new_tag', None) if impl is not None: return impl(name, attrs=dict(attrs)) return Tag(soup, name, attrs=attrs or None) class SarajevoX(BasicNewsRecipe): title = 'Sarajevo-x.com' __author__ = 'Darko Miletic' description = 'Sarajevo-x.com - najposjeceniji bosanskohercegovacki internet portal' publisher = 'InterSoft d.o.o.' category = 'news, politics, Bosnia and Herzegovina,Sarajevo-x.com, internet, portal, vijesti, bosna i hercegovina, sarajevo' oldest_article = 2 delay = 1 max_articles_per_feed = 100 no_stylesheets = True encoding = 'cp1250' use_embedded_content = False language = 'bs' extra_css = ' @font-face {font-family: "sans1";src:url(res:///opt/sony/ebook/FONT/tt0003m_.ttf)} body{font-family: Arial,Verdana,Helvetica,sans1,sans-serif} .article_description{font-family: sans1, sans-serif} div#fotka{display: block} img{margin-bottom: 0.5em} ' # noqa conversion_options = { 'comment': description, 'tags': category, 'publisher': publisher, 'language': language } preprocess_regexps = [(re.compile(u'\u0110'), lambda match: u'\u00D0')] keep_only_tags = [dict(name='div', attrs={'class': 'content-bg'})] remove_tags_after = dict(name='div', attrs={'class': 'izvor'}) remove_tags = [dict(name=['object', 'link', 'base', 'table'])] remove_attributes = ['height', 'width', 'alt', 'border'] feeds = [ (u'BIH', u'http://www.sarajevo-x.com/rss/bih'), (u'Svijet', u'http://www.sarajevo-x.com/rss/svijet'), (u'Biznis', u'http://www.sarajevo-x.com/rss/biznis'), (u'Sport', u'http://www.sarajevo-x.com/rss/sport'), (u'Showtime', u'http://www.sarajevo-x.com/rss/showtime'), (u'Scitech', u'http://www.sarajevo-x.com/rss/scitech'), (u'Lifestyle', u'http://www.sarajevo-x.com/rss/lifestyle'), (u'Kultura', u'http://www.sarajevo-x.com/rss/kultura'), (u'Zanimljivosti', u'http://www.sarajevo-x.com/rss/zanimljivosti') ] def preprocess_html(self, soup): dtag = soup.find('div', attrs={'id': 'fotka'}) if dtag: sp = soup.find('div', attrs={'id': 'opisslike'}) img = soup.find('img') if sp: sp else: mtag = new_tag(soup, 'div', [ ("id", "opisslike"), ("class", "opscitech")]) mopis = NavigableString("Opis") mtag.insert(0, mopis) img.append(mtag) return soup