#!/usr/bin/env python # -*- coding: utf-8 -*- __license__ = 'GPL v3' __copyright__ = u'2011, Silviu Cotoar\u0103' ''' onemagazine.ro ''' from calibre.web.feeds.news import BasicNewsRecipe class Onemagazine(BasicNewsRecipe): title = u'The ONE' __author__ = u'Silviu Cotoar\u0103' description = u'Be the ONE, not anyone ..' publisher = u'The ONE' oldest_article = 25 language = 'ro' max_articles_per_feed = 100 no_stylesheets = True use_embedded_content = False category = 'Ziare,Reviste,Femei' encoding = 'utf-8' cover_url = 'http://www.onemagazine.ro/images/logo_rss.jpg' conversion_options = { 'comments': description, 'tags': category, 'language': language, 'publisher': publisher } extra_css = ''' h1{font-family:Arial,Helvetica,sans-serif; font-weight:bold;font-size:large;} h2{font-family:Arial,Helvetica,sans-serif; font-weight:normal;font-size:small;} .byline {font-family:Arial,Helvetica,sans-serif; font-size:xx-small;} .date {font-family:Arial,Helvetica,sans-serif; font-size:xx-small;} p{font-family:Arial,Helvetica,sans-serif;font-size:small;} .copyright {font-family:Arial,Helvetica,sans-serif;font-size:xx-small;text-align:center} .story{font-family:Arial,Helvetica,sans-serif;font-size:small;} .entry-asset asset hentry{font-family:Arial,Helvetica,sans-serif;font-size:small;} .pagebody{font-family:Arial,Helvetica,sans-serif;font-size:small;} .maincontentcontainer{font-family:Arial,Helvetica,sans-serif;font-size:small;} .story-body{font-family:Arial,Helvetica,sans-serif;font-size:small;} body{font-family:Helvetica,Arial,sans-serif;font-size:small;} ''' keep_only_tags = [ dict(name='div', attrs={'class': 'article'}), dict(name='div', attrs={ 'class': 'gallery clearfix'}), dict(name='div', attrs={'align': 'justify'}) ] remove_tags = [ dict(name='p', attrs={'class': ['info']}), dict(name='table', attrs={'class': ['connect_widget_interactive_area']}), dict(name='span', attrs={'class': ['photo']}), dict(name='div', attrs={'class': ['counter']}), dict(name='div', attrs={'class': ['carousel']}), dict(name='div', attrs={'class': ['jcarousel-container jcarousel-container-horizontal']}) # noqa ] remove_tags_after = [ dict(name='table', attrs={ 'class': ['connect_widget_interactive_area']}) ] feeds = [ (u'Feeds', u'http://www.onemagazine.ro/rss') ] def preprocess_html(self, soup): return self.adeify_images(soup)