calibre/recipes/psych.recipe
2018-06-23 09:22:49 +05:30

56 lines
2.1 KiB
Python

#!/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'
__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(name='div', attrs={'data-type': 'article'})
]
remove_tags = [
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.find('h4').find('a')
self.timefmt = ' [%s]' % self.tag_to_string(a).capitalize()
soup = self.index_to_soup('http://www.psychologytoday.com' + a['href'])
div = soup.find(role='main')
self.cover_url = div.find(
'img', src=lambda x: x and '/field_magazine_cover/' in x)['src'].partition('?')[0]
articles = []
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 = 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)]