From e88b9556f9f88b8a9b47e84a1f1f8b43f1f3f94d Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sat, 23 Jun 2018 09:22:49 +0530 Subject: [PATCH] Update Psychology Today --- recipes/psych.recipe | 35 +++++++++++++++++++++-------------- 1 file changed, 21 insertions(+), 14 deletions(-) diff --git a/recipes/psych.recipe b/recipes/psych.recipe index a71bd962c8..a7a6a23894 100644 --- a/recipes/psych.recipe +++ b/recipes/psych.recipe @@ -1,6 +1,13 @@ +#!/usr/bin/env python2 +# vim:fileencoding=utf-8 + from calibre.web.feeds.recipes import BasicNewsRecipe +def check_words(words): + return lambda x: x and frozenset(words.split()).intersection(x.split()) + + class PsychologyToday(BasicNewsRecipe): title = 'Psychology Today' @@ -16,33 +23,33 @@ class PsychologyToday(BasicNewsRecipe): no_stylesheets = True keep_only_tags = [ - dict(role='main'), + dict(name='div', attrs={'data-type': 'article'}) ] remove_tags = [ - dict(attrs={'class': ['pt-social-media', 'fb-like-button']}), + dict(attrs={'id': 'pt-social-media'}), ] 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') + a = div.find('h4').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( + div = soup.find(role='main') + self.cover_url = div.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'] + for x in div.findAll('div', {'class': check_words('collection__item')}): + h = x.find(['h2', 'h3', 'h4', 'h5'], { + 'class': check_words('blog__title blog_entry__title')}) + title = self.tag_to_string(h) + url = 'http://www.psychologytoday.com' + h.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) + ' ' + desc = x.find(['div', 'p'], {'class': check_words( + 'collection__subtitle blog_entry__teaser')}).find(text=True) if desc: self.log(desc) + else: + desc = '' articles.append({'title': title, 'url': url, 'description': desc}) - return [('Current Issue', articles)]