from __future__ import absolute_import, division, print_function, unicode_literals from calibre.web.feeds.news import BasicNewsRecipe def classes(classes): q = frozenset(classes.split(' ')) return dict(attrs={'class': lambda x: x and frozenset(x.split()).intersection(q)}) class Forbes(BasicNewsRecipe): title = u'Forbes' description = 'Business and Financial News' __author__ = 'Kovid Goyal' oldest_article = 30 max_articles_per_feed = 20 language = 'en' encoding = 'utf-8' no_stylesheets = True ignore_duplicate_articles = {'title', 'url'} remove_empty_feeds = True extra_css = ''' div.fb-captioned-img { font-size: smaller; margin-top: 1em; margin-bottom: 1em; } div.fb-captioned-img img { display:block; margin-left: auto; margin-right: auto; } ''' feeds = [ (u'Latest', u'https://www.forbes.com/news/index.xml'), (u'Most Popular', u'https://www.forbes.com/feeds/popstories.xml'), (u'Technology', u'https://www.forbes.com/technology/index.xml'), (u'Business', u'https://www.forbes.com/business/index.xml'), (u'Sports Money', u'https://www.forbes.com/sportsmoney/index.xml'), (u'Leadership', u'https://www.forbes.com/leadership/index.xml'), ] keep_only_tags = [ classes('article-headline-container hero-image-block article-body bottom-contrib-block') ] remove_tags = [ classes('article-sharing'), dict(name='button'), ] def preprocess_html(self, soup): h = soup.find(**classes('hero-image-block')) if h is not None: h1 = soup.find(**classes('article-headline-container')) h.extract() h1.append(h) return soup def get_browser(self): br = BasicNewsRecipe.get_browser(self) br.set_cookie('dailyWelcomeCookie', 'true', '.forbes.com') br.set_cookie('welcomeAd', 'true', '.forbes.com') return br # def parse_index(self): # return [('Articles', [{'title':'Test', 'url': # 'http://www.forbes.com/sites/hamdiraini/2016/04/25/bazin-seeks-startups-to-accelerate-accorhotels-transformation/'}])]