# -*- mode: python -*- # -*- coding: utf-8 -*- __license__ = 'GPL v3' __copyright__ = '2017 - 2018, Darko Miletic ' ''' www.elcohetealaluna.com ''' from calibre.web.feeds.news import BasicNewsRecipe class elcohetealaluna(BasicNewsRecipe): title = 'El Cohete a la Luna' __author__ = 'Darko Miletic' description = 'El nuevo portal de Horacio Verbitsky' publisher = 'Horacio Verbitsky' category = 'news, politics, Argentina' oldest_article = 7 no_stylesheets = True encoding = 'utf8' use_embedded_content = False language = 'es_AR' remove_empty_feeds = True publication_type = 'newsportal' auto_cleanup = False resolve_internal_links = True compress_news_images = True masthead_url = 'https://www.elcohetealaluna.com/wp-content/uploads/2018/06/logo-menu.png' extra_css = """ body{font-family: Georgia, Times, "Times New Roman", serif} h1,h2,.post-author-name{font-family: Oswald, sans-serif} h2{color: gray} img{margin-top:1em; margin-bottom: 1em; display:block} """ conversion_options = { 'comment': description, 'tags': category, 'publisher': publisher, 'language': language } keep_only_tags=[ dict(name='div', attrs={'class': lambda x: x and 'post-header' in x.split()}), dict(name='div', attrs={'class': lambda x: x and 'entry-content' in x.split()}), ] feeds = [(u'Articulos', u'https://www.elcohetealaluna.com/feed/')] def preprocess_html(self, soup): for image in soup.findAll(name='img', attrs={'data-src': True}): image['src'] = image['data-src'] return soup