calibre/recipes/psych.recipe
2025-01-24 11:14:14 +01:00

76 lines
2.9 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
from calibre.web.feeds.recipes import BasicNewsRecipe
def absurl(url):
if url.startswith('//'):
return 'https:' + url
if url.startswith('/'):
return 'https://www.psychologytoday.com' + url
return url
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
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_stylesheets = True
publication_type = 'magazine'
remove_attributes = ['style', 'height', 'width']
extra_css = '''
.image-article_inline_full, .image-article-inline-half { text-align:center; font-size:small; }
em, blockquote { color:#202020; }
.blog-entry__date--full { font-size:small; }
'''
recipe_specific_options = {
'date': {
'short': 'The date of the Past Edition to download (YYYY/MM format)',
'long': 'For example, 2024/07'
}
}
keep_only_tags = [dict(attrs={'id': 'block-pt-content'})]
remove_tags = [classes('pt-social-media')]
def parse_index(self):
soup = self.index_to_soup('https://www.psychologytoday.com/us/magazine/archive')
a = soup.find(**classes('magazine-thumbnail')).a
url = a['href']
past_edition = self.recipe_specific_options.get('date')
if past_edition and isinstance(past_edition, str):
url = '/us/magazine/archive/' + past_edition
soup = self.index_to_soup(absurl(url))
cov = soup.find(**classes('content-header--cover-image'))
if cov:
self.cover_url = cov.img['src']
self.timefmt = ' [%s]' % cov.img['alt'].replace(' magazine cover', '')
articles = []
for article in soup.findAll('div', attrs={'class':'article-text'}):
title = self.tag_to_string(article.find(attrs={'class':['h2','h3']})).strip()
url = absurl(article.find(attrs={'class':['h2','h3']}).a['href'])
self.log('\n', title, 'at', url)
desc = self.tag_to_string(article.find('p',**classes('description'))).strip()
author = self.tag_to_string(article.find('p',**classes('byline')).a).strip()
if desc:
self.log(desc)
else:
desc = ''
articles.append({'title': title, 'url': url, 'description': desc, 'author': author})
return [('Articles', articles)]