# -*- coding: utf-8 -*- __license__ = 'GPL v3' __copyright__ = '2011 Aurélien Chabot ' ''' Fetch phoronix.com ''' from calibre.web.feeds.news import BasicNewsRecipe class cdnet(BasicNewsRecipe): title = 'Phoronix' __author__ = 'calibre' description = 'Actualités Phoronix' encoding = 'utf-8' publisher = 'Phoronix.com' category = 'news, IT, linux' language = 'en' use_embedded_content = False timefmt = ' [%d %b %Y]' max_articles_per_feed = 25 no_stylesheets = True remove_empty_feeds = True filterDuplicates = True extra_css = ''' h1 {font-size:xx-large; font-family:Arial,Helvetica,sans-serif;} h2 {font-size:xx-small; color:#4D4D4D; font-family:Arial,Helvetica,sans-serif;} .KonaBody {font-size:medium; font-family:Arial,Helvetica,sans-serif;} ''' remove_tags = [] remove_tags_before = dict(id='phxcms_content_phx') remove_tags_after = dict(name='div', attrs={'class':'KonaBody'}) feeds = [('Phoronix', 'http://feeds.feedburner.com/Phoronix')] def preprocess_html(self, soup): for item in soup.findAll(style=True): del item['style'] return soup