__copyright__ = '2011-2013, Darko Miletic ' ''' www.iprofesional.com ''' from calibre.web.feeds.news import BasicNewsRecipe class iProfesional(BasicNewsRecipe): title = 'iProfesional.com' __author__ = 'Darko Miletic' description = 'Las ultimas noticias sobre profesionales' publisher = 'Emprendimientos Corporativos S.A.' category = 'news, IT, impuestos, negocios, politics, Argentina' oldest_article = 2 max_articles_per_feed = 200 no_stylesheets = True encoding = 'utf8' use_embedded_content = False language = 'es_AR' remove_empty_feeds = True publication_type = 'newsportal' masthead_url = 'http://www.iprofesional.com/img/header/logoiprofesional.png' extra_css = """ body{font-family: 'Droid Sans',Arial,sans-serif } img{margin-bottom: 0.4em; display:block} .titulo{font-family: WhitneyBoldWhitneyBold,Arial,Helvetica,sans-serif; color: blue} .fecha-archivo{font-weight: bold; color: rgb(205, 150, 24)} .description{font-weight: bold; color: gray } .firma{font-size: small} """ conversion_options = { 'comment': description, 'tags': category, 'publisher': publisher, 'language': language } keep_only_tags = [dict(attrs={'class': 'desarrollo'})] remove_tags = [ dict(name=['meta', 'link', 'base', 'embed', 'object', 'iframe'])] feeds = [ (u'Ultimas noticias', u'http://feeds.feedburner.com/iprofesional-principales-noticias'), (u'Finanzas', u'http://feeds.feedburner.com/iprofesional-finanzas'), (u'Impuestos', u'http://feeds.feedburner.com/iprofesional-impuestos'), (u'Negocios', u'http://feeds.feedburner.com/iprofesional-economia'), (u'Comercio Exterior', u'http://feeds.feedburner.com/iprofesional-comercio-exterior'), (u'Tecnologia', u'http://feeds.feedburner.com/iprofesional-tecnologia'), (u'Management', u'http://feeds.feedburner.com/iprofesional-managment'), (u'Marketing', u'http://feeds.feedburner.com/iprofesional-marketing'), (u'Legales', u'http://feeds.feedburner.com/iprofesional-legales'), (u'Autos', u'http://feeds.feedburner.com/iprofesional-autos'), (u'Vinos', u'http://feeds.feedburner.com/iprofesional-vinos-bodegas') ] def preprocess_html(self, soup): for item in soup.findAll(style=True): del item['style'] for item in soup.findAll('a'): limg = item.find('img') if item.string is not None: str = item.string item.replaceWith(str) else: if limg: item.name = 'div' item.attrs = [] else: str = self.tag_to_string(item) item.replaceWith(str) for item in soup.findAll('img'): if 'alt' not in item: item['alt'] = 'image' return soup