#!/usr/bin/env python # vim:fileencoding=utf-8 from calibre.web.feeds.news import BasicNewsRecipe class Bellingcat(BasicNewsRecipe): title = 'Debunking Denialism' __author__ = 'bugmen00t' description = 'Debunking Denialism is a website dedicated to the refutation of pseudoscience and denialism by applying scientific skepticism and defending evidence-based science. Fighting pseudoscience and quackery with reason and evidence.' # noqa: E501 publisher = 'Debunking Denialism' category = 'blog' cover_url = u'https://i0.wp.com/debunkingdenialism.com/wp-content/uploads/2017/06/cropped-newestblavatar.jpg' language = 'en' no_stylesheets = True remove_javascript = False auto_cleanup = False oldest_article = 60 max_articles_per_feed = 10 remove_tags_before = dict(name='article') remove_tags_after = dict(name='article') remove_tags = [ dict(name='div', attrs={'class': 'above-entry-meta'}), dict(name='time', attrs={'class': 'updated'}), dict(name='p', attrs={'class': 'ddtag'}), dict(name='div', attrs={'class': 'sharedaddy sd-sharing-enabled'}), dict( name='div', attrs={ 'class': 'sharedaddy sd-block sd-like jetpack-likes-widget-wrapper jetpack-likes-widget-unloaded' } ) ] feeds = [('Debunking Denialism', 'https://debunkingdenialism.com/feed/')] def preprocess_html(self, soup): for img in soup.findAll('img', attrs={'data-orig-file': True}): img['src'] = img['data-orig-file'] return soup