from calibre.web.feeds.recipes import BasicNewsRecipe class PsychologyToday(BasicNewsRecipe): title = 'Psychology Today' __author__ = 'Kovid Goyal' description = ('This magazine takes information from the latest research' ' in the field of psychology and makes it useful to people in their everyday' ' lives. Its coverage encompasses self-improvement, relationships, the mind-body' ' connection, health, family, the workplace and culture.') language = 'en' encoding = 'UTF-8' no_javascript = True no_stylesheets = True keep_only_tags = [ dict(role='main'), ] remove_tags = [ dict(attrs={'class':['pt-social-media', 'fb-like-button']}), ] def parse_index(self): soup = self.index_to_soup('http://www.psychologytoday.com/magazine') div = soup.find(id='block-views-magazine-issues-block') a = div.findAll('h3', attrs={'class':'magazine-published-date'})[1].find('a') self.timefmt = ' [%s]' % self.tag_to_string(a).capitalize() soup = self.index_to_soup('http://www.psychologytoday.com' + a['href']) self.cover_url = soup.find(role='main').find('img', src=lambda x:x and '/field_magazine_cover/' in x)['src'].partition('?')[0] div = soup.find(id='block-system-main') articles = [] for x in div.findAll(attrs={'class':'field__item'}): h2 = x.find('h2') title = self.tag_to_string(h2) url = 'http://www.psychologytoday.com' + h2.find('a')['href'] self.log('\n', title, 'at', url) desc = '' for y in x.findAll(attrs={'class':['subtext', 'collection__subtitle']}): desc += self.tag_to_string(y) + ' ' if desc: self.log(desc) articles.append({'title':title, 'url':url, 'description':desc}) return [('Current Issue', articles)]