from calibre.web.feeds.recipes import BasicNewsRecipe class Tijolaco(BasicNewsRecipe): title = u'Tijolaco.com' __author__ = u'Diniz Bortolotto' description = u'Posts do Blog Tijola\xe7o.com' oldest_article = 7 max_articles_per_feed = 50 encoding = 'utf8' publisher = u'Brizola Neto' category = 'politics, Brazil' language = 'pt_BR' publication_type = 'politics portal' use_embedded_content = False no_stylesheets = True remove_javascript = True feeds = [(u'Blog Tijola\xe7o.com', u'http://feeds.feedburner.com/Tijolacoblog')] reverse_article_order = True keep_only_tags = [dict(name='div', attrs={'class':'post'})] remove_tags = [dict(name='span', attrs={'class':'com'})]
import re class VioMundo(BasicNewsRecipe): title = 'Blog VioMundo' __author__ = 'Diniz Bortolotto' description = 'Posts do Blog VioMundo' publisher = 'Luiz Carlos Azenha' oldest_article = 5 max_articles_per_feed = 20 category = 'news, politics, Brazil' language = 'pt_BR' publication_type = 'news and politics portal' use_embedded_content = False no_stylesheets = True remove_javascript = True feeds = [(u'Blog VioMundo', u'http://www.viomundo.com.br/feed')] reverse_article_order = True def print_version(self, url): return url + '/print/' remove_tags_after = dict(id='BlogContent') preprocess_regexps = [ (re.compile(r'\|\ <u>.*</p>'), lambda match: '</p>') ]